Localization Distillation for Object Detection.

Previous knowledge distillation (KD) methods for object detection mostly focus on feature imitation instead of mimicking the prediction logits due to its inefficiency in distilling the localization information. In this paper, we investigate whether logit mimicking always lags behind feature imitation. Towards this goal, we first present a novel localization distillation (LD) method which can efficiently transfer the localization knowledge from the teacher to the student. Second, we introduce the concept of valuable localization region that can aid to selectively distill the classification and localization knowledge for a certain region. Combining these two new components, for the first time, we show that logit mimicking can outperform feature imitation and the absence of localization distillation is a critical reason for why logit mimicking under-performs for years. The thorough studies exhibit the great potential of logit mimicking that can significantly alleviate the localization ambiguity, learn robust feature representation, and ease the training difficulty in the early stage. We also provide the theoretical connection between the proposed LD and the classification KD, that they share the equivalent optimization effect. Our distillation scheme is simple as well as effective and can be easily applied to both dense horizontal object detectors and rotated object detectors. Extensive experiments on the MS COCO, PASCAL VOC, and DOTA benchmarks demonstrate that our method can achieve considerable AP improvement without any sacrifice on the inference speed. Our source code and pretrained models are publicly available at https://github.com/HikariTJU/LD.

Multi-View Knowledge Ensemble With Frequency Consistency for Cross-Domain Face Translation.

Cross-domain face translation aims to transfer face images from one domain to another. It can be widely used in practical applications, such as photos/sketches in law enforcement, photos/drawings in digital entertainment, and near-infrared (NIR)/visible (VIS) images in security access control. Restricted by limited cross-domain face image pairs, the existing methods usually yield structural deformation or identity ambiguity, which leads to poor perceptual appearance. To address this challenge, we propose a multi-view knowledge (structural knowledge and identity knowledge) ensemble framework with frequency consistency (MvKE-FC) for cross-domain face translation. Due to the structural consistency of facial components, the multi-view knowledge learned from large-scale data can be appropriately transferred to limited cross-domain image pairs and significantly improve the generative performance. To better fuse multi-view knowledge, we further design an attention-based knowledge aggregation module that integrates useful information, and we also develop a frequency-consistent (FC) loss that constrains the generated images in the frequency domain. The designed FC loss consists of a multidirection Prewitt (mPrewitt) loss for high-frequency consistency and a Gaussian blur loss for low-frequency consistency. Furthermore, our FC loss can be flexibly applied to other generative models to enhance their overall performance. Extensive experiments on multiple cross-domain face datasets demonstrate the superiority of our method over state-of-the-art methods both qualitatively and quantitatively.

Enhancing Geometric Factors in Model Learning and Inference for Object Detection and Instance Segmentation.

Deep learning-based object detection and instance segmentation have achieved unprecedented progress. In this article, we propose complete-IoU (CIoU) loss and Cluster-NMS for enhancing geometric factors in both bounding-box regression and nonmaximum suppression (NMS), leading to notable gains of average precision (AP) and average recall (AR), without the sacrifice of inference efficiency. In particular, we consider three geometric factors, that is: 1) overlap area; 2) normalized central-point distance; and 3) aspect ratio, which are crucial for measuring bounding-box regression in object detection and instance segmentation. The three geometric factors are then incorporated into CIoU loss for better distinguishing difficult regression cases. The training of deep models using CIoU loss results in consistent AP and AR improvements in comparison to widely adopted ln -norm loss and IoU-based loss. Furthermore, we propose Cluster-NMS, where NMS during inference is done by implicitly clustering detected boxes and usually requires fewer iterations. Cluster-NMS is very efficient due to its pure GPU implementation, and geometric factors can be incorporated to improve both AP and AR. In the experiments, CIoU loss and Cluster-NMS have been applied to state-of-the-art instance segmentation (e.g., YOLACT and BlendMask-RT), and object detection (e.g., YOLO v3, SSD, and Faster R-CNN) models. Taking YOLACT on MS COCO as an example, our method achieves performance gains as +1.7 AP and +6.2 AR100 for object detection, and +1.1 AP and +3.5 AR100 for instance segmentation, with 27.1 FPS on one NVIDIA GTX 1080Ti GPU. All the source code and trained models are available at https://github.com/Zzh-tju/CIoU.

Simultaneous Fidelity and Regularization Learning for Image Restoration.

Most existing non-blind restoration methods are based on the assumption that a precise degradation model is known. As the degradation process can only be partially known or inaccurately modeled, images may not be well restored. Rain streak removal and image deconvolution with inaccurate blur kernels are two representative examples of such tasks. For rain streak removal, although an input image can be decomposed into a scene layer and a rain streak layer, there exists no explicit formulation for modeling rain streaks and the composition with scene layer. For blind deconvolution, as estimation error of blur kernel is usually introduced, the subsequent non-blind deconvolution process does not restore the latent image well. In this paper, we propose a principled algorithm within the maximum a posterior framework to tackle image restoration with a partially known or inaccurate degradation model. Specifically, the residual caused by a partially known or inaccurate degradation model is spatially dependent and complexly distributed. With a training set of degraded and ground-truth image pairs, we parameterize and learn the fidelity term for a degradation model in a task-driven manner. Furthermore, the regularization term can also be learned along with the fidelity term, thereby forming a simultaneous fidelity and regularization learning model. Extensive experimental results demonstrate the effectiveness of the proposed model for image deconvolution with inaccurate blur kernels, deconvolution with multiple degradations and rain streak removal.

STAR: A Structure and Texture Aware Retinex Model.

Retinex theory is developed mainly to decompose an image into the illumination and reflectance components by analyzing local image derivatives. In this theory, larger derivatives are attributed to the changes in reflectance, while smaller derivatives are emerged in the smooth illumination. In this paper, we utilize exponentiated local derivatives (with an exponent γ) of an observed image to generate its structure map and texture map. The structure map is produced by been amplified with γ > 1, while the texture map is generated by been shrank with γ < 1. To this end, we design exponential filters for the local derivatives, and present their capability on extracting accurate structure and texture maps, influenced by the choices of exponents γ. The extracted structure and texture maps are employed to regularize the illumination and reflectance components in Retinex decomposition. A novel Structure and Texture Aware Retinex (STAR) model is further proposed for illumination and reflectance decomposition of a single image. We solve the STAR model by an alternating optimization algorithm. Each sub-problem is transformed into a vectorized least squares regression, with closed-form solutions. Comprehensive experiments on commonly tested datasets demonstrate that, the proposed STAR model produce better quantitative and qualitative performance than previous competing methods, on illumination and reflectance decomposition, low-light image enhancement, and color correction. The code is publicly available at https://github.com/csjunxu/STAR.

The deposition of VWOx on the CuCeOy microflower for the selective catalytic reduction of NOx with NH3 at low temperatures.

NOx emissions are a major environmental problem, and the selective catalytic reduction (SCR) is the most effective method to convert NOx in flue gas into harmless N2 and H2O. In this work, a new carrier, CuCeOy microflower assembled from a large number of copper-cerium mixed oxide nanosheets, is firstly developed to load vanadium-tungsten mixed oxides (VWOx) for the SCR of NOx with NH3. The resultant optimal VWOx/CuCeOy catalyst exhibits significantly enhanced low-temperature de-NOx performance with the NOx conversion of 60% at 180 °C, over 90% from 240 °C to 390 °C under the gas hourly space velocity (GHSV) of 36,000 h-1. The reason can be mainly attributed the fact that the transfer of electrons among Ce, Cu and V ions is very easy to occur via the following equations Ce3++Cu2+ â†” Ce4++Cu+, V5+ + Cu+ â†” V4+ + Cu2+, V4+ + Ce4+ â†” V5+ + Ce3+, which effectively decreases the apparent activation energy (Ea = 16.59 kJ/mol) of NH3-SCR de-NOx reaction. In addition, the enhanced reducibility and a large number of Brønsted acid sites also contribute the low-temperature de-NOx performance. Both Eley-Rideal and Langmuir-Hinshelwood mechanisms are included in the NH3-SCR de-NOx reaction over the VWOx/CuCeOy catalyst.

Partial Deconvolution With Inaccurate Blur Kernel.

Most non-blind deconvolution methods are developed under the error-free kernel assumption, and are not robust to inaccurate blur kernel. Unfortunately, despite the great progress in blind deconvolution, estimation error remains inevitable during blur kernel estimation. Consequently, severe artifacts such as ringing effects and distortions are likely to be introduced in the non-blind deconvolution stage. In this paper, we tackle this issue by suggesting: 1) a partial map in the Fourier domain for modeling kernel estimation error, and 2) a partial deconvolution model for robust deblurring with inaccurate blur kernel. The partial map is constructed by detecting the reliable Fourier entries of estimated blur kernel. And partial deconvolution is applied to wavelet-based and learning-based models to suppress the adverse effect of kernel estimation error. Furthermore, an E-M algorithm is developed for estimating the partial map and recovering the latent sharp image alternatively. Experimental results show that our partial deconvolution model is effective in relieving artifacts caused by inaccurate blur kernel, and can achieve favorable deblurring quality on synthetic and real blurry images.

[Effect of Compound Qingre Granule on the Expression of Peripheral Blood Lymphocyte Subsets of Acute Virus Infection Patients].

OBJECTIVE: To observe interventional effects of anti-viral therapy and Compound Qin-gre Granule (CQG) on host cellular immune functions of acute virus infection patients. METHODS: Thirty acute virus infection patients were recruited to detect peripheral lymphocyte subsets. They were randomly assigned to two groups, the Western medicine treatment group (treated with anti-virus Western medicine) and the integrative medicine treatment group (treated with anti-virus Western medicine plus CQG). T-cell subsets were re-examined 7 days later. Changes between before and after treatment were observed. Effect on host cellular immune functions and efficacy were compared between the Western medicine treatment and the integrative medicine treatment. RESULTS: Compared with the normal control group, the percentage of peripheral T cells increased, and the percentage of B/NK cells decreased in acute virus infection patients (P < 0.01). Meanwhile, in T cell subsets, the percentage of CD8+ T cells and CD8+ CD38+ T cells increased (P < 0.05, P < 0.01); and percentages of CD4+ T cells, CD4+ CD28 + T cells, and CD8+ CD28+ T cells decreased (P < 0.05, P < 0.01). After one-week treatment, percentages of CD4+ T cells, CD4+ CD28+ T cells, and CD8+ CD28+ T cells increased (P < 0.05, P < 0.01), while the percentage of CD8+ CD38+ T cells decreased (P < 0.01). More significantly, these changes were greater in the integrative medicine treatment group than in the Western medicine treatment group (P < 0.05). CONCLUSIONS: Disarranged cellular immune functions existed in acute virus infection patients. CQG could significantly improve viral infection induced immunologic derangement and immunologic injury.