Explore the vast range of titles available.

Model filter pruning has shown efficiency in compressing deep convolutional neural networks by removing unimportant filters without sacrificing the performance. However, most existing criteria are empirical, and overlook the relationship between channel saliencies and the non-linear activation functions within the networks. To address these problems, we propose a novel channel pruning method coined gradient flow based saliency (GFBS). Instead of relying on the magnitudes of the entire feature maps, GFBS evaluates the channel saliencies from the gradient flow perspective and only requires the information in normalization and activation layers. Concretely, we first integrate the effects of normalization and ReLU activation layers into convolutional layers based on Taylor expansion. Then, through backpropagation, the derived channel saliency of each layer is indicated by of the first-order Taylor polynomial of the scaling parameter and the signed shifting parameter in the normalization layers. To validate the efficiency and generalization ability of GFBS, we conduct extensive experiments on various tasks, including image classification (CIFAR, ImageNet), image denoising, object detection, and 3D object classification. GFBS could feasibly cooperate with the baseline networks and compress them with only negligible performance drop. Moreover, we extended our method to pruning scratch networks and GFBS is capable to identify subnetworks with comparable performance with the baseline model at an early training stage. Our code has been released at https://github.com/CUHK-AIM-Group/GFBS.

Semantic segmentation is a popular research topic in computer vision, and many efforts have been made on it with impressive results. In this paper, we intend to search an optimal network structure that can run in real-time for this problem. Towards this goal, we jointly search the depth, channel, dilation rate and feature spatial resolution, which results in a search space consisting of about 2.78×10324 possible choices. To handle such a large search space, we leverage differential architecture search methods. However, the architecture parameters searched using existing differential methods need to be discretized, which causes the discretization gap between the architecture parameters found by the differential methods and their discretized version as the final solution for the architecture search. Hence, we relieve the problem of discretization gap from the innovative perspective of solution space regularization. Specifically, a novel Solution Space Regularization (SSR) loss is first proposed to effectively encourage the supernet to converge to its discrete one. Then, a new Hierarchical and Progressive Solution Space Shrinking method is presented to further achieve high efficiency of searching. In addition, we theoretically show that the optimization of SSR loss is equivalent to the L0-norm regularization, which accounts for the improved search-evaluation gap. Comprehensive experiments show that the proposed search scheme can efficiently find an optimal network structure that yields an extremely fast speed (175 FPS) of segmentation with a small model size (1 M) while maintaining comparable accuracy.

There are frequently a large number of strip objects in segmentation scenarios, and the use of conventional square convolution may yield redundant information. Based on our previously proposed SA-FFNet (Zhou et al. in Neurocomputing 453:50–59, 2021), we study the effect of strip sub-region information extraction on semantic segmentation and propose a network. Our method is conducive to extracting multi-scale strip objects that often appear in segmentation scenes, and using strip dilated convolution to further extract contextual dependencies in other directions. First, we propose a multi-scale strip pooling module that enables the backbone network to effectively obtain multi-scale contexts; Then, we introduce a strip dilated convolution module, which supplements the vertical contexts of the strip pooling by using strip dilated convolution; Finally, we construct a novel network integrating the proposed two modules. The method explicitly takes horizontal and vertical contexts of multi-scale strip objects into consideration, so that scene understanding could benefit from long-range dependencies. The experimental results on the widely used PASCAL VOC 2012 and Cityscapes scene analysis benchmark datasets, which are better than the existing OCRNet, DeeplabV3+, SPNet, etc, both qualitatively and quantitatively.

Image semantic segmentation is a meaningful task that requires both accuracy and efficiency in computer vision. At present, most current deep learning based semantic segmentation methods needs extensive computational resources, and knowledge distillation may reduce such a computational burden due to its model compression ability. In this paper, different from previous knowledge distillation methods that directly transfer the knowledge of the teacher network to the student network, we propose a novel intermediate feature refinement method for semantic segmentation based on adversarial learning, which reduces the error and redundant information contained in the teacher network in the process of knowledge distillation, enhances the correct information contained in the teacher network and transfers it to the student network. Then we improve the conventional discriminator in adversarial learning to help the student network align more correct intermediate features in the teacher network. Our method can make the feature distribution of the student network closer to that of the teacher network, and finally improve the segmentation performance of the student network. Finally, we conducted experiments on three popular benchmarks to verify the effectiveness of our proposed method, including Pascal VOC, Cityscapes and CamVid. Compared with the competitive baseline, our proposed method can improve the performance of the student network by up to 1.43% (the mIOU increases from 67.14% to 68.57% on the Cityscapes val set).

The wireless capsule endoscopy (WCE) invented by Given Imaging has been gradually used in hospitals due to its great breakthrough that it can view the entire small bowel for gastrointestinal diseases. However, a tough problem associated with this new technology is that too many images to be examined by eyes cause a huge burden to physicians, so it is significant if we can help physicians do diagnosis using computerized methods. In this paper, a new method aimed for bleeding and ulcer detection in WCE images is proposed. This new approach mainly focuses on color feature, also a very powerful clue used by physicians for diagnosis, to judge the status of gastrointestinal tract. We propose a new idea of chromaticity moment as the features to discriminate normal regions and abnormal regions, which make full use of the Tchebichef polynomials and the illumination invariant of HSI color space, and we verify performances of the proposed features by employing neural network classifier. Experimental results on our present image data of bleeding and ulcer show that it is feasible to exploit the proposed chromaticity moments to detect bleeding and ulcer for WCE images.

This paper is concerned with the problem of designing [Hamiltonian (script capital H)] ∞ filters for a class of two-dimensional (2D) Markov jump systems under asynchronous switching. The problem under consideration is primarily motivated by a realistic situation that the switching of candidate filters may have a lag to the switching of system modes. Different from conventional techniques, by a suitable augmentation, the jumping process of the error system is represented by a two-component Markov chain. Then, the extended transition probabilities are provided for the error system. A stochastic Lyapunov function approach is proposed for the design of desired filters that ensure a prescribed [Hamiltonian (script capital H)] ∞ performance for admissible asynchronous switching. Finally, a numerical example is given to illustrate the effectiveness of the developed method.

This paper is concerned with the problem of designing ℋ∞ filters for a class of two-dimensional (2D) Markov jump systems under asynchronous switching. The problem under consideration is primarily motivated by a realistic situation that the switching of candidate filters may have a lag to the switching of system modes. Different from conventional techniques, by a suitable augmentation, the jumping process of the error system is represented by a two-component Markov chain. Then, the extended transition probabilities are provided for the error system. A stochastic Lyapunov function approach is proposed for the design of desired filters that ensure a prescribed ℋ∞ performance for admissible asynchronous switching. Finally, a numerical example is given to illustrate the effectiveness of the developed method.

This paper is concerned with the problem of designing [hamilt] sub( infinity ) filters for a class of two-dimensional (2D) Markov jump systems under asynchronous switching. The problem under consideration is primarily motivated by a realistic situation that the switching of candidate filters may have a lag to the switching of system modes. Different from conventional techniques, by a suitable augmentation, the jumping process of the error system is represented by a two-component Markov chain. Then, the extended transition probabilities are provided for the error system. A stochastic Lyapunov function approach is proposed for the design of desired filters that ensure a prescribed [hamilt] sub( infinity ) performance for admissible asynchronous switching. Finally, a numerical example is given to illustrate the effectiveness of the developed method.

This article presents a computer-aided detection system for capsule endoscopy (CE) images using contourlet-based color textural features to recognize tumors in the digestive tract. As tumor exhibits rich information in color texture, a novel color texture feature based on contourlet transform is proposed to describe characteristics of tumor in CE images. The proposed features are a hybrid of contourlet transform and uniform local binary pattern, yielding detailed and robust color texture features in multi-directions for CE images. Sequential floating forward search approach is further applied to refine the proposed features. With support vector machine for classification, comprehensive experiments on our present data reveal an encouraging accuracy of 93.6% for tumor detection in CE images using the proposed features.

Cross-domain pedestrian detection aims to generalize pedestrian detectors from one label-rich domain to another label-scarce domain, which is crucial for various real-world applications. Most recent works focus on domain alignment to train domain-adaptive detectors either at the instance level or image level. From a practical point of view, one-stage detectors are faster. Therefore, we concentrate on designing a cross-domain algorithm for rapid one-stage detectors that lacks instance-level proposals and can only perform image-level feature alignment. However, pure image-level feature alignment causes the foreground-background misalignment issue to arise, i.e., the foreground features in the source domain image are falsely aligned with background features in the target domain image. To address this issue, we systematically analyze the importance of foreground and background in image-level cross-domain alignment, and learn that background plays a more critical role in image-level cross-domain alignment. Therefore, we focus on cross-domain background feature alignment while minimizing the influence of foreground features on the cross-domain alignment stage. This paper proposes a novel framework, namely, background-focused distribution alignment (BFDA), to train domain adaptive onestage pedestrian detectors. Specifically, BFDA first decouples the background features from the whole image feature maps and then aligns them via a novel long-short-range discriminator.