Spatial and Seasonal Changes in Microbial Community of Hynobius amjiensis Breeding Pools in a Sphagnum-Dominated Peatland.

Peatlands deliver a variety of beneficial ecosystem services, particularly serving as habitats for a diverse array of species. Hynobius amjiensis is a critically endangered amphibian initially discovered in a Sphagnum-dominated peatland in Anji, China. The unique habitat requirements of H. amjiensis make it highly vulnerable to environmental changes. Here, we investigated the different breeding pools of H. amjiensis in the Sphagnum-dominated peatland (the type locality) for a one-year period to evaluate the interactions among the egg sacs present, water quality, and microbial communities (16S and 18S rRNA gene amplicon). The numbers of egg sacs were higher in the breeding pools located at the marginal area than those at the core area of the peatland. Similarly, the α-diversity of bacteria, fungi, and protists were lower in the core region compared to those at the edge of the peatland, perhaps due to water eutrophication. The microbial communities and water quality differed significantly among breeding pools and sampling months. The simpler microbial networks of the breeding pools in the core wetland may impact the numbers and health of the egg sacs. This study contributes to a better understanding of the effect of water quality on biodiversity in peatlands, and it can also guide regulations for wetland conservation and the protection of endangered species.

A Synopsis of Dicranum Hedw. (Dicranaceae, Bryophyta) in China, with Special References to Four Species Newly Reported and Re-Evaluation of Dicranum psathyrum Klazenga.

Dicranum Hedw. is a highly diverse and widely distributed genus within Dicranaceae. The species diversity and distribution of this genus in China, however, remain not well known. A new revision of Dicranum in China using morphological and molecular phylogenetic methods confirms that China has 39 species, including four newly reported species, D. bardunovii Tubanova & Ignatova, D. dispersum Engelmark, D. schljakovii Ignatova & Tubanova, and D. spadiceum J.E.Zetterst. Dicranum psathyrum Klazenga is transferred to Dicranoloma (Renauld) Renauld as a new synonym of Dicranoloma fragile Broth. Two species, Dicranum brevifolium (Lindb.) Lindb. and D. viride (Sull. & Lesq.) Lindb. are excluded from the bryoflora of China. A key to the Chinese Dicranum species is also provided. These results indicate an underestimation of the distribution range of numerous Dicranum species, underscoring the need for further in-depth investigations into the worldwide Dicranum diversity.

Revisiting Computer-Aided Tuberculosis Diagnosis.

Tuberculosis (TB) is a major global health threat, causing millions of deaths annually. Although early diagnosis and treatment can greatly improve the chances of survival, it remains a major challenge, especially in developing countries. Recently, computer-aided tuberculosis diagnosis (CTD) using deep learning has shown promise, but progress is hindered by limited training data. To address this, we establish a large-scale dataset, namely the Tuberculosis X-ray (TBX11 K) dataset, which contains 11 200 chest X-ray (CXR) images with corresponding bounding box annotations for TB areas. This dataset enables the training of sophisticated detectors for high-quality CTD. Furthermore, we propose a strong baseline, SymFormer, for simultaneous CXR image classification and TB infection area detection. SymFormer incorporates Symmetric Search Attention (SymAttention) to tackle the bilateral symmetry property of CXR images for learning discriminative features. Since CXR images may not strictly adhere to the bilateral symmetry property, we also propose Symmetric Positional Encoding (SPE) to facilitate SymAttention through feature recalibration. To promote future research on CTD, we build a benchmark by introducing evaluation metrics, evaluating baseline models reformed from existing detectors, and running an online challenge. Experiments show that SymFormer achieves state-of-the-art performance on the TBX11 K dataset.

The transcription factor NAC102 confers cadmium tolerance by regulating WAKL11 expression and cell wall pectin metabolism in Arabidopsis.

Cadmium (Cd) toxicity severely limits plant growth and development. Moreover, Cd accumulation in vegetables, fruits, and food crops poses health risks to animals and humans. Although the root cell wall has been implicated in Cd stress in plants, whether Cd binding by cell wall polysaccharides contributes to tolerance remains controversial, and the mechanism underlying transcriptional regulation of cell wall polysaccharide biosynthesis in response to Cd stress is unknown. Here, we functionally characterized an Arabidopsis thaliana NAC-type transcription factor, NAC102, revealing its role in Cd stress responses. Cd stress rapidly induced accumulation of NAC102.1, the major transcript encoding functional NAC102, especially in the root apex. Compared to wild type (WT) plants, a nac102 mutant exhibited enhanced Cd sensitivity, whereas NAC102.1-overexpressing plants displayed the opposite phenotype. Furthermore, NAC102 localizes to the nucleus, binds directly to the promoter of WALL-ASSOCIATED KINASE-LIKE PROTEIN11 (WAKL11), and induces transcription, thereby facilitating pectin degradation and decreasing Cd binding by pectin. Moreover, WAKL11 overexpression restored Cd tolerance in nac102 mutants to the WT levels, which was correlated with a lower pectin content and lower levels of pectin-bound Cd. Taken together, our work shows that the NAC102-WAKL11 module regulates cell wall pectin metabolism and Cd binding, thus conferring Cd tolerance in Arabidopsis.

P2T: Pyramid Pooling Transformer for Scene Understanding.

Recently, the vision transformer has achieved great success by pushing the state-of-the-art of various vision tasks. One of the most challenging problems in the vision transformer is that the large sequence length of image tokens leads to high computational cost (quadratic complexity). A popular solution to this problem is to use a single pooling operation to reduce the sequence length. This paper considers how to improve existing vision transformers, where the pooled feature extracted by a single pooling operation seems less powerful. To this end, we note that pyramid pooling has been demonstrated to be effective in various vision tasks owing to its powerful ability in context abstraction. However, pyramid pooling has not been explored in backbone network design. To bridge this gap, we propose to adapt pyramid pooling to Multi-Head Self-Attention (MHSA) in the vision transformer, simultaneously reducing the sequence length and capturing powerful contextual features. Plugged with our pooling-based MHSA, we build a universal vision transformer backbone, dubbed Pyramid Pooling Transformer (P2T). Extensive experiments demonstrate that, when applied P2T as the backbone network, it shows substantial superiority in various vision tasks such as image classification, semantic segmentation, object detection, and instance segmentation, compared to previous CNN- and transformer-based networks. The code will be released at https://github.com/yuhuan-wu/P2T.

EDN: Salient Object Detection via Extremely-Downsampled Network.

Recent progress on salient object detection (SOD) mainly benefits from multi-scale learning, where the high-level and low-level features collaborate in locating salient objects and discovering fine details, respectively. However, most efforts are devoted to low-level feature learning by fusing multi-scale features or enhancing boundary representations. High-level features, which although have long proven effective for many other tasks, yet have been barely studied for SOD. In this paper, we tap into this gap and show that enhancing high-level features is essential for SOD as well. To this end, we introduce an Extremely-Downsampled Network (EDN), which employs an extreme downsampling technique to effectively learn a global view of the whole image, leading to accurate salient object localization. To accomplish better multi-level feature fusion, we construct the Scale-Correlated Pyramid Convolution (SCPC) to build an elegant decoder for recovering object details from the above extreme downsampling. Extensive experiments demonstrate that EDN achieves state-of-the-art performance with real-time speed. Our efficient EDN-Lite also achieves competitive performance with a speed of 316fps. Hence, this work is expected to spark some new thinking in SOD. Code is available at https://github.com/yuhuan-wu/EDN.

Leveraging Instance-, Image- and Dataset-Level Information for Weakly Supervised Instance Segmentation.

Weakly supervised semantic instance segmentation with only image-level supervision, instead of relying on expensive pixel-wise masks or bounding box annotations, is an important problem to alleviate the data-hungry nature of deep learning. In this article, we tackle this challenging problem by aggregating the image-level information of all training images into a large knowledge graph and exploiting semantic relationships from this graph. Specifically, our effort starts with some generic segment-based object proposals (SOP) without category priors. We propose a multiple instance learning (MIL) framework, which can be trained in an end-to-end manner using training images with image-level labels. For each proposal, this MIL framework can simultaneously compute probability distributions and category-aware semantic features, with which we can formulate a large undirected graph. The category of background is also included in this graph to remove the massive noisy object proposals. An optimal multi-way cut of this graph can thus assign a reliable category label to each proposal. The denoised SOP with assigned category labels can be viewed as pseudo instance segmentation of training images, which are used to train fully supervised models. The proposed approach achieves state-of-the-art performance for both weakly supervised instance segmentation and semantic segmentation. The code is available at https://github.com/yun-liu/LIID.

MobileSal: Extremely Efficient RGB-D Salient Object Detection.

The high computational cost of neural networks has prevented recent successes in RGB-D salient object detection (SOD) from benefiting real-world applications. Hence, this article introduces a novel network, MobileSal, which focuses on efficient RGB-D SOD using mobile networks for deep feature extraction. However, mobile networks are less powerful in feature representation than cumbersome networks. To this end, we observe that the depth information of color images can strengthen the feature representation related to SOD if leveraged properly. Therefore, we propose an implicit depth restoration (IDR) technique to strengthen the mobile networks' feature representation capability for RGB-D SOD. IDR is only adopted in the training phase and is omitted during testing, so it is computationally free. Besides, we propose compact pyramid refinement (CPR) for efficient multi-level feature aggregation to derive salient objects with clear boundaries. With IDR and CPR incorporated, MobileSal performs favorably against state-of-the-art methods on six challenging RGB-D SOD datasets with much faster speed (450fps for the input size of 320×320) and fewer parameters (6.5M). The code is released at https://mmcheng.net/mobilesal.

H2A.B is a cancer/testis factor involved in the activation of ribosome biogenesis in Hodgkin lymphoma.

Testis-specific regulators of chromatin function are commonly ectopically expressed in human cancers, but their roles are poorly understood. Examination of 81 primary Hodgkin lymphoma (HL) samples showed that the ectopic expression of the eutherian testis-specific histone variant H2A.B is an inherent feature of HL. In experiments using two HL cell lines derived from different subtypes of HL, H2A.B knockdown inhibited cell proliferation. H2A.B was enriched in both nucleoli of these HL cell lines and primary HL samples. We found that H2A.B enhanced ribosomal DNA (rDNA) transcription, was enriched at the rDNA promoter and transcribed regions, and interacted with RNA Pol I. Depletion of H2A.B caused the loss of RNA Pol I from rDNA chromatin. Remarkably, H2A.B was also required for high levels of ribosomal protein gene expression being located at the transcriptional start site and within the gene body. H2A.B knockdown reduced gene body chromatin accessibility of active RNA Pol II genes concurrent with a decrease in transcription. Taken together, our data show that in HL H2A.B has acquired a new function, the ability to increase ribosome biogenesis.

Regularized Densely-Connected Pyramid Network for Salient Instance Segmentation.

Much of the recent efforts on salient object detection (SOD) have been devoted to producing accurate saliency maps without being aware of their instance labels. To this end, we propose a new pipeline for end-to-end salient instance segmentation (SIS) that predicts a class-agnostic mask for each detected salient instance. To better use the rich feature hierarchies in deep networks and enhance the side predictions, we propose the regularized dense connections, which attentively promote informative features and suppress non-informative ones from all feature pyramids. A novel multi-level RoIAlign based decoder is introduced to adaptively aggregate multi-level features for better mask predictions. Such strategies can be well-encapsulated into the Mask R-CNN pipeline. Extensive experiments on popular benchmarks demonstrate that our design significantly outperforms existing state-of-the-art competitors by 6.3% (58.6% vs. 52.3%) in terms of the AP metric. The code is available at https://github.com/yuhuan-wu/RDPNet.