Integrated analysis of the DNA methylome and RNA transcriptome during the development of skeletal muscle in Duroc pigs.

BACKGROUND: Skeletal muscle development plays a crucial role in yield and quality of pork; however, this process is influenced by various factors. In this study, we employed whole-genome bisulfite sequencing (WGBS) and transcriptome sequencing to comprehensively investigate the longissimus dorsi muscle (LDM), aiming to identify key genes that impact the growth and development of Duroc pigs with different average daily gains (ADGs). RESULTS: Eight pigs were selected and divided into two groups based on ADGs: H (774.89 g) group and L (658.77 g) group. Each pair of the H and L groups were half-siblings. The results of methylation sequencing revealed 2631 differentially methylated genes (DMGs) involved in metabolic processes, signalling, insulin secretion, and other biological activities. Furthermore, a joint analysis was conducted on these DMGs and the differentially expressed genes (DEGs) obtained from transcriptome sequencing of the same individual. This analysis identified 316 differentially methylated and differentially expressed genes (DMEGs), including 18 DMEGs in promoter regions and 294 DMEGs in gene body regions. Finally, LPAR1 and MEF2C were selected as candidate genes associated with muscle development. Bisulfite sequencing PCR (BSP) and quantitative real-time PCR (qRT-PCR) revealed that the promoter region of LPAR1 exhibited significantly lower methylation levels (P < 0.05) and greater expression levels (P < 0.05) in the H group than in the L group. Additionally, hypermethylation was observed in the gene body region of MEF2C, as was a low expression level, in the H group (P < 0.05). CONCLUSIONS: These results suggest that the differences in the ADGs of Duroc pigs fed the same diet may be influenced by the methylation levels and expression levels of genes related to skeletal muscle development.

Low thermal contact resistance boron nitride nanosheets composites enabled by interfacial arc-like phonon bridge.

Two-dimensional materials with ultrahigh in-plane thermal conductivity are ideal for heat spreader applications but cause significant thermal contact resistance in complex interfaces, limiting their use as thermal interface materials. In this study, we present an interfacial phonon bridge strategy to reduce the thermal contact resistance of boron nitride nanosheets-based composites. By using a low-molecular-weight polymer, we are able to manipulate the alignment of boron nitride nanosheets through sequential stacking and cutting, ultimately achieving flexible thin films with a layer of arc-like structure superimposed on perpendicularly aligned ones. Our results suggest that arc-like structure can act as a phonon bridge to lower the contact resistance by 70% through reducing phonon back-reflection and enhancing phonon coupling efficiency at the boundary. The resulting composites exhibit ultralow thermal contact resistance of 0.059 in2 KW-1, demonstrating effective cooling of fast-charging batteries at a thickness 2-5 times thinner than commercial products.

HQG-Net: Unpaired Medical Image Enhancement With High-Quality Guidance.

Unpaired medical image enhancement (UMIE) aims to transform a low-quality (LQ) medical image into a high-quality (HQ) one without relying on paired images for training. While most existing approaches are based on Pix2Pix/CycleGAN and are effective to some extent, they fail to explicitly use HQ information to guide the enhancement process, which can lead to undesired artifacts and structural distortions. In this article, we propose a novel UMIE approach that avoids the above limitation of existing methods by directly encoding HQ cues into the LQ enhancement process in a variational fashion and thus model the UMIE task under the joint distribution between the LQ and HQ domains. Specifically, we extract features from an HQ image and explicitly insert the features, which are expected to encode HQ cues, into the enhancement network to guide the LQ enhancement with the variational normalization module. We train the enhancement network adversarially with a discriminator to ensure the generated HQ image falls into the HQ domain. We further propose a content-aware loss to guide the enhancement process with wavelet-based pixel-level and multiencoder-based feature-level constraints. Additionally, as a key motivation for performing image enhancement is to make the enhanced images serve better for downstream tasks, we propose a bi-level learning scheme to optimize the UMIE task and downstream tasks cooperatively, helping generate HQ images both visually appealing and favorable for downstream tasks. Experiments on three medical datasets verify that our method outperforms existing techniques in terms of both enhancement quality and downstream task performance. The code and the newly collected datasets are publicly available at https://github.com/ChunmingHe/HQG-Net.

Meta-Learning-Based Degradation Representation for Blind Super-Resolution.

Blind image super-resolution (blind SR) aims to generate high-resolution (HR) images from low-resolution (LR) input images with unknown degradations. To enhance the performance of SR, the majority of blind SR methods introduce an explicit degradation estimator, which helps the SR model adjust to unknown degradation scenarios. Unfortunately, it is impractical to provide concrete labels for the multiple combinations of degradations (e. g., blurring, noise, or JPEG compression) to guide the training of the degradation estimator. Moreover, the special designs for certain degradations hinder the models from being generalized for dealing with other degradations. Thus, it is imperative to devise an implicit degradation estimator that can extract discriminative degradation representations for all types of degradations without requiring the supervision of degradation ground-truth. To this end, we propose a Meta-Learning based Region Degradation Aware SR Network (MRDA), including Meta-Learning Network (MLN), Degradation Extraction Network (DEN), and Region Degradation Aware SR Network (RDAN). To handle the lack of ground-truth degradation, we use the MLN to rapidly adapt to the specific complex degradation after several iterations and extract implicit degradation information. Subsequently, a teacher network MRDAT is designed to further utilize the degradation information extracted by MLN for SR. However, MLN requires iterating on paired LR and HR images, which is unavailable in the inference phase. Therefore, we adopt knowledge distillation (KD) to make the student network learn to directly extract the same implicit degradation representation (IDR) as the teacher from LR images. Furthermore, we introduce an RDAN module that is capable of discerning regional degradations, allowing IDR to adaptively influence various texture patterns. Extensive experiments under classic and real-world degradation settings show that MRDA achieves SOTA performance and can generalize to various degradation processes.

Multi-Modal Mutual Attention and Iterative Interaction for Referring Image Segmentation.

We address the problem of referring image segmentation that aims to generate a mask for the object specified by a natural language expression. Many recent works utilize Transformer to extract features for the target object by aggregating the attended visual regions. However, the generic attention mechanism in Transformer only uses the language input for attention weight calculation, which does not explicitly fuse language features in its output. Thus, its output feature is dominated by vision information, which limits the model to comprehensively understand the multi-modal information, and brings uncertainty for the subsequent mask decoder to extract the output mask. To address this issue, we propose Multi-Modal Mutual Attention (M3Att) and Multi-Modal Mutual Decoder ( M3Dec ) that better fuse information from the two input modalities. Based on M3Dec , we further propose Iterative Multi-modal Interaction (IMI) to allow continuous and in-depth interactions between language and vision features. Furthermore, we introduce Language Feature Reconstruction (LFR) to prevent the language information from being lost or distorted in the extracted feature. Extensive experiments show that our proposed approach significantly improves the baseline and outperforms state-of-the-art referring image segmentation methods on RefCOCO series datasets consistently.

GAN Inversion: A Survey.

GAN inversion aims to invert a given image back into the latent space of a pretrained GAN model so that the image can be faithfully reconstructed from the inverted code by the generator. As an emerging technique to bridge the real and fake image domains, GAN inversion plays an essential role in enabling pretrained GAN models, such as StyleGAN and BigGAN, for applications of real image editing. Moreover, GAN inversion interprets GAN's latent space and examines how realistic images can be generated. In this paper, we provide a survey of GAN inversion with a focus on its representative algorithms and its applications in image restoration and image manipulation. We further discuss the trends and challenges for future research. A curated list of GAN inversion methods, datasets, and other related information can be found at https://github.com/weihaox/awesome-gan-inversion.

Global Aligned Structured Sparsity Learning for Efficient Image Super-Resolution.

Efficient image super-resolution (SR) has witnessed rapid progress thanks to novel lightweight architectures or model compression techniques (e.g., neural architecture search and knowledge distillation). Nevertheless, these methods consume considerable resources or/and neglect to squeeze out the network redundancy at a more fine-grained convolution filter level. Network pruning is a promising alternative to overcome these shortcomings. However, structured pruning is known to be tricky when applied to SR networks because the extensive residual blocks demand the pruned indices of different layers to be the same. Besides, the principled determination of proper layerwise sparsities remains challenging too. In this article, we present Global Aligned Structured Sparsity Learning (GASSL) to resolve these problems. GASSL has two major components: Hessian-Aided Regularization (HAIR) and Aligned Structured Sparsity Learning (ASSL). HAIR is a regularization-based sparsity auto-selection algorithm with Hessian considered implicitly. A proven proposition is introduced to justify its design. ASSL is for physically pruning SR networks. Particularly, a new penalty term Sparsity Structure Alignment (SSA) is proposed to align the pruned indices of different layers. With GASSL, we design two new efficient single image SR networks of different architecture genres, pushing the efficiency envelope of SR models one step forward. Extensive results demonstrate the merits of GASSL over other recent counterparts.

Image-Text Embedding Learning via Visual and Textual Semantic Reasoning.

As a bridge between language and vision domains, cross-modal retrieval between images and texts is a hot research topic in recent years. It remains challenging because the current image representations usually lack semantic concepts in the corresponding sentence captions. To address this issue, we introduce an intuitive and interpretable model to learn a common embedding space for alignments between images and text descriptions. Specifically, our model first incorporates the semantic relationship information into visual and textual features by performing region or word relationship reasoning. Then it utilizes the gate and memory mechanism to perform global semantic reasoning on these relationship-enhanced features, select the discriminative information and gradually grow representations for the whole scene. Through the alignment learning, the learned visual representations capture key objects and semantic concepts of a scene as in the corresponding text caption. Experiments on MS-COCO [1] and Flickr30K [2] datasets validate that our method surpasses many recent state-of-the-arts with a clear margin. In addition to the effectiveness, our methods are also very efficient at the inference stage. Thanks to the effective overall representation learning with visual semantic reasoning, our methods can already achieve very strong performance by only relying on the simple inner-product to obtain similarity scores between images and captions. Experiments validate the proposed methods are more than 30-75 times faster than many recent methods with code public available. Instead of following the recent trend of using complex local matching strategies [3], [4], [5], [6] to pursue good performance while sacrificing efficiency, we show that the simple global matching strategy can still be very effective, efficient and achieve even better performance based on our framework.

Lattice Network for Lightweight Image Restoration.

Deep learning has made unprecedented progress in image restoration (IR), where residual block (RB) is popularly used and has a significant effect on promising performance. However, the massive stacked RBs bring about burdensome memory and computation cost. To tackle this issue, we aim to design an economical structure for adaptively connecting pair-wise RBs, thereby enhancing the model representation. Inspired by the topological structure of lattice filter in signal processing theory, we elaborately propose the lattice block (LB), where couple butterfly-style topological structures are utilized to bridge pair-wise RBs. Specifically, each candidate structure of LB relies on the combination coefficients learned through adaptive channel reweighting. As a basic mapping block, LB can be plugged into various IR models, such as image super-resolution, image denoising, image deraining, etc. It can avail the construction of lightweight IR models accompanying half parameter amount reduced, while keeping the considerable reconstruction accuracy compared with RBs. Moreover, a novel contrastive loss is exploited as a regularization constraint, which can further enhance the model representation without increasing the inference expenses. Experiments on several IR tasks illustrate that our method can achieve more favorable performance than other state-of-the-art models with lower storage and computation.

Texture-based Error Analysis for Image Super-Resolution.

Evaluation practices for image super-resolution (SR) use a single-value metric, the PSNR or SSIM, to determine model performance. This provides little insight into the source of errors and model behavior. Therefore, it is beneficial to move beyond the conventional approach and reconceptualize evaluation with interpretability as our main priority. We focus on a thorough error analysis from a variety of perspectives. Our key contribution is to leverage a texture classifier, which enables us to assign patches with semantic labels, to identify the source of SR errors both globally and locally. We then use this to determine (a) the semantic alignment of SR datasets, (b) how SR models perform on each label, (c) to what extent high-resolution (HR) and SR patches semantically correspond, and more. Through these different angles, we are able to highlight potential pitfalls and blindspots. Our overall investigation highlights numerous unexpected insights. We hope this work serves as an initial step for debugging blackbox SR networks.

PFDN: Pyramid Feature Decoupling Network for Single Image Deraining.

Restoring images degraded by rain has attracted more academic attention since rain streaks could reduce the visibility of outdoor scenes. However, most existing deraining methods attempt to remove rain while recovering details in a unified framework, which is an ideal and contradictory target in the image deraining task. Moreover, the relative independence of rain streak features and background features is usually ignored in the feature domain. To tackle these challenges above, we propose an effective Pyramid Feature Decoupling Network (i.e., PFDN) for single image deraining, which could accomplish image deraining and details recovery with the corresponding features. Specifically, the input rainy image features are extracted via a recurrent pyramid module, where the features for the rainy image are divided into two parts, i.e., rain-relevant and rain-irrelevant features. Afterwards, we introduce a novel rain streak removal network for rain-relevant features and remove the rain streak from the rainy image by estimating the rain streak information. Benefiting from lateral outputs, we propose an attention module to enhance the rain-irrelevant features, which could generate spatially accurate and contextually reliable details for image recovery. For better disentanglement, we also enforce multiple causality losses at the pyramid features to encourage the decoupling of rain-relevant and rain-irrelevant features from the high to shallow layers. Extensive experiments demonstrate that our module can well model the rain-relevant information over the domain of the feature. Our framework empowered by PFDN modules significantly outperforms the state-of-the-art methods on single image deraining with multiple widely-used benchmarks, and also shows superiority in the fully-supervised domain.

Identification and functional prediction of long non-coding RNAs related to skeletal muscle development in Duroc pigs.

OBJECTIVE: The growth of pigs involves multiple regulatory mechanisms, and modern molecular breeding techniques can be used to understand the skeletal muscle growth and development to promote the selection process of pigs. This study aims to explore candidate lncRNAs and mRNAs related to skeletal muscle growth and development among Duroc pigs with different average daily gain (ADG). METHODS: A total of 8 pigs were selected and divided into two groups: H group (high-ADG) and L group (low-ADG). And followed by whole transcriptome sequencing to identify differentially expressed (DE) lncRNAs and mRNAs. RESULTS: In RNA-seq, 703 DE mRNAs (263 up-regulated and 440 down-regulated) and 74 DE lncRNAs (45 up-regulated and 29 down-regulated) were identified. In addition, 1,418 Transcription factors (TFs) were found. Compared with mRNAs, lncRNAs had fewer exons, shorter transcript length and open reading frame length. DE mRNAs and DE lncRNAs can form 417 lncRNA-mRNA pairs (antisense, cis and trans). DE mRNAs and target genes of lncRNAs were enriched in cellular processes, biological regulation, and regulation of biological processes. In addition, quantitative trait locus (QTL) analysis was used to detect the functions of DE mRNAs and lncRNAs, the most of DE mRNAs and target genes of lncRNAs were enriched in QTLs related to growth traits and skeletal muscle development. In single-nucleotide polymorphism/insertion-deletion (SNP/INDEL) analysis, 1,081,182 SNP and 131,721 INDEL were found, and transition was more than transversion. Over 60% of percentage were skipped exon events among alternative splicing events. CONCLUSION: The results showed that different ADG among Duroc pigs with the same diet maybe due to the DE mRNAs and DE lncRNAs related to skeletal muscle growth and development.

Vehicle and Person Re-Identification With Support Neighbor Loss.

One of the key tasks for an intelligent visual surveillance system is to automatically re-identify objects of interest, e.g., persons or vehicles, from nonoverlapping camera views. This demand incurs the vast investigation of person re-identification (re-ID) and vehicle re-ID techniques, especially those deep learning-based ones. While most recent algorithms focus on designing new convolutional neural networks, less attention is paid to the loss functions, which are of vital roles as well. Triplet loss and softmax loss are the two losses that are extensively used, both of which, however, have limitations. Triplet loss optimizes the model to produce features with which samples from the same class have higher similarity than those from different classes. The problem of triplet loss is that the number of triplets to be constructed grows cubically with training samples, which causes scalability issue, unstable performance, and slow convergence. Softmax loss has favorable scalable property and is widely used for large-scale classification problems. However, since Softmax loss only aims to separate well training classes, its performance for re-ID tasks is not desirable because the model is tested to measure the similarity of samples from unseen classes. We propose the support neighbor (SN) loss, which avoids the limitations of the abovementioned two losses. Unlike triplet loss that is calculated based on triplets, SN loss is derived from K -nearest neighbors (SNs) of anchor samples. The SNs of an anchor are unique, containing more valuable contextual information and neighborhood structure of the anchor, and thus contribute to more stable performance and reliable embedding from image space to feature space. Based on the SNs, a softmax-like separation term and a squeeze term are proposed, which encourage interclass separation and intraclass compactness, respectively. Experiments show that SN loss surpasses triplet and softmax losses with the same backbone network and reaches the state-of-the-art performance for both person and vehicle re-ID using a ResNet50 backbone when combined with training tricks.

Self-Guided Deep Multiview Subspace Clustering via Consensus Affinity Regularization.

Multiview subspace clustering (MVSC) leverages the complementary information among different views of multiview data and seeks a consensus subspace clustering result better than that using any individual view. Though proved effective in some cases, existing MVSC methods often obtain unsatisfactory results since they perform subspace analysis with raw features that are often of high dimensions and contain noises. To remedy this, we propose a self-guided deep multiview subspace clustering (SDMSC) model that performs joint deep feature embedding and subspace analysis. SDMSC comprehensively explores multiview data and strives to obtain a consensus data affinity relationship agreed by features from not only all views but also all intermediate embedding spaces. With more constraints being cast, the desirable data affinity relationship is supposed to be more reliably recovered. Besides, to secure effective deep feature embedding without label supervision, we propose to use the data affinity relationship obtained with raw features as the supervision signals to self-guide the embedding process. With this strategy, the risk that our deep clustering model being trapped in bad local minima is reduced, bringing us satisfactory clustering results in a higher possibility. The experiments on seven widely used datasets show the proposed method significantly outperforms the state-of-the-art clustering methods. Our code is available at https://github.com/kailigo/dmvsc.git.

Accurate and Fast Image Denoising via Attention Guided Scaling.

Image denoising is a classical topic yet still a challenging problem, especially for reducing noise from the texture information. Feature scaling (e.g., downscale and upscale) is a widely practice in image denoising to enlarge receptive field size and save resources. However, such a common operation would lose some visual informative details. To address those problems, we propose fast and accurate image denoising via attention guided scaling (AGS). We find that the main informative feature channel and visual primitives during the scaling should keep similar. We then propose to extract the global channel-wise attention to maintain main channel information. Moreover, we propose to collect global descriptors by considering the entire spatial feature. And we then distribute the global descriptors to local positions of the scaled feature, based on their specific needs. We further introduce AGS for adversarial training, resulting in a more powerful discriminator. Extensive experiments show the effectiveness of our proposed method, where we clearly surpass all the state-of-the-art methods on most popular synthetic and real-world denoising benchmarks quantitatively and visually. We further show that our network contributes to other high-level vision applications and improves their performances significantly.

Experimental investigation of temperature distribution and spontaneous combustion tendency of coal gangue stockpiles in storage.

In this study, an experimental model about the coal gangue stockpiles in semi-open storage was developed. According to the model's requirements, the corresponding coal gangues were piled up in the factory building, the heat source and collection points were arranged, and the four operating temperatures were selected from 70 to 350 °C for heating. A series of fire experiments concerning the temperature distributions of the coal gangue piles were conducted systematically. The spontaneous combustion tendency of coal gangue samples under kinds of the four heat sources was analyzed using scanning electron microscope (SEM), thermal gravity analysis, and differential thermal gravity (TG-DTG). Under the action of thermal damage, the surface of micropores in coal gangue becomes rough. Heat accumulation is, in nature, most likely to occur near 0.1~0.4 m away from the heat source of coal pile. Simultaneously, on each of the measured flat layers, the greater the horizontal distance from the heat source is, the lower the heated temperature of gangues is, and the lower the temperature change rate is, indicating that the horizontal heat conduction is also gradually weakened. The experimental model provides an empirical basis for studying the distribution of temperature field in the depth of gangue pile and kinetics reaction mechanism of spontaneous combustion.

Residual Dense Network for Image Restoration.

Recently, deep convolutional neural network (CNN) has achieved great success for image restoration (IR) and provided hierarchical features at the same time. However, most deep CNN based IR models do not make full use of the hierarchical features from the original low-quality images; thereby, resulting in relatively-low performance. In this work, we propose a novel and efficient residual dense network (RDN) to address this problem in IR, by making a better tradeoff between efficiency and effectiveness in exploiting the hierarchical features from all the convolutional layers. Specifically, we propose residual dense block (RDB) to extract abundant local features via densely connected convolutional layers. RDB further allows direct connections from the state of preceding RDB to all the layers of current RDB, leading to a contiguous memory mechanism. To adaptively learn more effective features from preceding and current local features and stabilize the training of wider network, we proposed local feature fusion in RDB. After fully obtaining dense local features, we use global feature fusion to jointly and adaptively learn global hierarchical features in a holistic way. We demonstrate the effectiveness of RDN with several representative IR applications, single image super-resolution, Gaussian image denoising, image compression artifact reduction, and image deblurring. Experiments on benchmark and real-world datasets show that our RDN achieves favorable performance against state-of-the-art methods for each IR task quantitatively and visually.

Continual Multiview Task Learning via Deep Matrix Factorization.

The state-of-the-art multitask multiview (MTMV) learning tackles a scenario where multiple tasks are related to each other via multiple shared feature views. However, in many real-world scenarios where a sequence of the multiview task comes, the higher storage requirement and computational cost of retraining previous tasks with MTMV models have presented a formidable challenge for this lifelong learning scenario. To address this challenge, in this article, we propose a new continual multiview task learning model that integrates deep matrix factorization and sparse subspace learning in a unified framework, which is termed deep continual multiview task learning (DCMvTL). More specifically, as a new multiview task arrives, DCMvTL first adopts a deep matrix factorization technique to capture hidden and hierarchical representations for this new coming multiview task while accumulating the fresh multiview knowledge in a layerwise manner. Then, a sparse subspace learning model is employed for the extracted factors at each layer and further reveals cross-view correlations via a self-expressive constraint. For model optimization, we derive a general multiview learning formulation when a new multiview task comes and apply an alternating minimization strategy to achieve lifelong learning. Extensive experiments on benchmark data sets demonstrate the effectiveness of our proposed DCMvTL model compared with the existing state-of-the-art MTMV and lifelong multiview task learning models.

Dynamic High-Pass Filtering and Multi-Spectral Attention for Image Super-Resolution.

Deep convolutional neural networks (CNNs) have pushed forward the frontier of super-resolution (SR) research. However, current CNN models exhibit a major flaw: they are biased towards learning low-frequency signals. This bias becomes more problematic for the image SR task which targets reconstructing all fine details and image textures. To tackle this challenge, we propose to improve the learning of high-frequency features both locally and globally and introduce two novel architectural units to existing SR models. Specifically, we propose a dynamic highpass filtering (HPF) module that locally applies adaptive filter weights for each spatial location and channel group to preserve high-frequency signals. We also propose a matrix multi-spectral channel attention (MMCA) module that predicts the attention map of features decomposed in the frequency domain. This module operates in a global context to adaptively recalibrate feature responses at different frequencies. Extensive qualitative and quantitative results demonstrate that our proposed modules achieve better accuracy and visual improvements against state-of-the-art methods on several benchmark datasets.

Channel Splitting Network for Single MR Image Super-Resolution.

High resolution magnetic resonance (MR) imaging is desirable in many clinical applications due to its contribution to more accurate subsequent analyses and early clinical diagnoses. Single image super-resolution (SISR) is an effective and cost efficient alternative technique to improve the spatial resolution of MR images. In the past few years, SISR methods based on deep learning techniques, especially convolutional neural networks (CNNs), have achieved the state-of-the-art performance on natural images. However, the information is gradually weakened and training becomes increasingly difficult as the network deepens. The problem is more serious for medical images because lacking high quality and effective training samples makes deep models prone to underfitting or overfitting. Nevertheless, many current models treat the hierarchical features on different channels equivalently, which is not helpful for the models to deal with the hierarchical features discriminatively and targetedly. To this end, we present a novel channel splitting network (CSN) to ease the representational burden of deep models. The proposed CSN model divides the hierarchical features into two branches, i.e., residual branch and dense branch, with different information transmissions. The residual branch is able to promote feature reuse, while the dense branch is beneficial to the exploration of new features. Besides, we also adopt the merge-and-run mapping to facilitate information integration between different branches. The extensive experiments on various MR images, including proton density (PD), T1, and T2 images, show that the proposed CSN model achieves superior performance over other state-of-the-art SISR methods.