Search

Tibetan foxes (Vulpes ferrilata) have been confirmed as the main wild definitive hosts in echinococcosis transmission in the eastern Tibetan Plateau. However, little information is available about the epidemiology in wildlife from the perspective of the Taeniidae family, which is essential knowledge in understanding the epidemiology and phylogeography of cestode species in the Tibetan plateau. Therefore, in this study, we used copro-PCR techniques, by amplifying nad1 and cox1 gene fragments, to detect the taeniid species from Tibetan fox feces collected in Shiqu County, (Sichuan Province, China), eastern Tibetan Plateau. Phylogenetic relationships between amplified sequences and existed Taenia species genotypes were evaluated. Then, the maximum prevalence (positive PCR results from at least one primer pair) and the conservative prevalence (positive PCR results from at least two primer pairs) were calculated. Thirty-six Tibetan fox feces were analyzed. Echinococcus multilocularis (conservative prevalence ± 95% CI: 22.2% ± 13.6%; maximum prevalence ± 95% CI: 33.3% ± 15.4%) and E. shiquicus (2.8 ± 5.4%; 8.3 ± 9.0%) was detected. Meanwhile, DNA fragments of T. polyacantha were detected with high similarity to NCBI sequences (cox1, 94.0%) and to the larva sample DNA sequenced in this study (93.4%), and were supported by phylogenetic analysis. Thus, T. polyacantha might infect Tibetan foxes (5.6% ± 7.5%, 11.1% ± 10.3%). Our limited findings in the epidemiology of parasitic Taenia species suggest that sylvatic transmission cycles for a more species-rich Taeniid community must be established between wild canids and small mammals than just for the two Echinococcus species. Besides, discrepancies in different primer pairs in detecting the taeniid species were evaluated. The sensitivity of some widely used universal primer pairs was poor in detecting Taenia species from canid copro-DNA samples. It is still challenging to the development of effective taeniid species-specific molecular markers especially for non-zoonotic species.

The benign and malignant (BM) classification of breast masses based on mammography is a key step in the diagnosis of early breast cancer and an effective way to improve the survival rate of patients. Nevertheless, due to the differences in size, shape and texture of breast masses and the visual similarity between masses of the same category, it is difficult to obtain a robust classification model using conventional deep learning methods. To address this problem, we proposed a Multi-Tasking U-shaped Network (MT-UNet), which contains three key ideas: 1) the U-shaped classification architecture constructed can well adapt to the heterogeneity of breast masses; 2) the combination of the proposed truncated normalization method and adaptive histogram equalization method can enhance the contrast of image; 3) training with label smoothing method can alleviate the problem of convergence difficulty caused by insufficient training data. The performance of the proposed scheme is evaluated on the public dataset of DDSM and INbreast. On the DDSM dataset, the Area Under Curve (AUC) and accuracy (ACC) reached 0.9963 and 0.9817, respectively. On the INbreast dataset, the AUC and ACC reached 0.9767 and 0.9391, respectively. Experimental results show that the proposed method can obtain a competitive performance.

This paper introduces a post-training quantization~(PTQ) method achieving highly efficient Convolutional Neural Network~ (CNN) quantization with high performance. Previous PTQ methods usually reduce compression error via performing layer-by-layer parameters calibration. However, with lower representational ability of extremely compressed parameters (e.g., the bit-width goes less than 4), it is hard to eliminate all the layer-wise errors. This work addresses this issue via proposing a unit-wise feature reconstruction algorithm based on an observation of second order Taylor series expansion of the unit-wise error. It indicates that leveraging the interaction between adjacent layers' parameters could compensate layer-wise errors better. In this paper, we define several adjacent layers as a Basic-Unit, and present a unit-wise post-training algorithm which can minimize quantization error. This method achieves near-original accuracy on ImageNet and COCO when quantizing FP32 models to INT4 and INT3., Accepted by BMVC 2021

Solid results from Transformers have made them prevailing architectures in various natural language and vision tasks. As a default component in Transformers, Layer Normalization (LN) normalizes activations within each token to boost the robustness. However, LN requires on-the-fly statistics calculation in inference as well as division and square root operations, leading to inefficiency on hardware. What is more, replacing LN with other hardware-efficient normalization schemes (e.g., Batch Normalization) results in inferior performance, even collapse in training. We find that this dilemma is caused by abnormal behaviors of activation statistics, including large fluctuations over iterations and extreme outliers across layers. To tackle these issues, we propose Unified Normalization (UN), which can speed up the inference by being fused with other linear operations and achieve comparable performance on par with LN. UN strives to boost performance by calibrating the activation and gradient statistics with a tailored fluctuation smoothing strategy. Meanwhile, an adaptive outlier filtration strategy is applied to avoid collapse in training whose effectiveness is theoretically proved and experimentally verified in this paper. We demonstrate that UN can be an efficient drop-in alternative to LN by conducting extensive experiments on language and vision tasks. Besides, we evaluate the efficiency of our method on GPU. Transformers equipped with UN enjoy about 31% inference speedup and nearly 18% memory reduction. Code will be released at https://github.com/hikvision-research/Unified-Normalization., Comment: ACM MM'22

In recent years, significant progress has been made on the research of crowd counting. However, as the challenging scale variations and complex scenes existed in crowds, neither traditional convolution networks nor recent Transformer architectures with fixed-size attention could handle the task well. To address this problem, this paper proposes a scene-adaptive attention network, termed SAANet. First of all, we design a deformable attention in-built Transformer backbone, which learns adaptive feature representations with deformable sampling locations and dynamic attention weights. Then we propose the multi-level feature fusion and count-attentive feature enhancement modules further, to strengthen feature representation under the global image context. The learned representations could attend to the foreground and are adaptive to different scales of crowds. We conduct extensive experiments on four challenging crowd counting benchmarks, demonstrating that our method achieves state-of-the-art performance. Especially, our method currently ranks No.1 on the public leaderboard of the NWPU-Crowd benchmark. We hope our method could be a strong baseline to support future research in crowd counting. The source code will be released to the community.

Text recognition is a popular topic for its broad applications. In this work, we excavate the implicit task, character counting within the traditional text recognition, without additional labor annotation cost. The implicit task plays as an auxiliary branch for complementing the sequential recognition. We design a two-branch reciprocal feature learning framework in order to adequately utilize the features from both the tasks. Through exploiting the complementary effect between explicit and implicit tasks, the feature is reliably enhanced. Extensive experiments on 7 benchmarks show the advantages of the proposed methods in both text recognition and the new-built character counting tasks. In addition, it is convenient yet effective to equip with variable networks and tasks. We offer abundant ablation studies, generalizing experiments with deeper understanding on the tasks. Code is available., Comment: Accepted by ICDAR 2021. Code is available at https://davar-lab.github.io/publication.html or https://github.com/hikopensource/DAVAR-Lab-OCR

Table structure recognition is a challenging task due to the various structures and complicated cell spanning relations. Previous methods handled the problem starting from elements in different granularities (rows/columns, text regions), which somehow fell into the issues like lossy heuristic rules or neglect of empty cell division. Based on table structure characteristics, we find that obtaining the aligned bounding boxes of text region can effectively maintain the entire relevant range of different cells. However, the aligned bounding boxes are hard to be accurately predicted due to the visual ambiguities. In this paper, we aim to obtain more reliable aligned bounding boxes by fully utilizing the visual information from both text regions in proposed local features and cell relations in global features. Specifically, we propose the framework of Local and Global Pyramid Mask Alignment, which adopts the soft pyramid mask learning mechanism in both the local and global feature maps. It allows the predicted boundaries of bounding boxes to break through the limitation of original proposals. A pyramid mask re-scoring module is then integrated to compromise the local and global information and refine the predicted boundaries. Finally, we propose a robust table structure recovery pipeline to obtain the final structure, in which we also effectively solve the problems of empty cells locating and division. Experimental results show that the proposed method achieves competitive and even new state-of-the-art performance on several public benchmarks., Comment: Award of ICDAR2021 Best Industry Paper. Code is available at https://davar-lab.github.io/publication.html or https://github.com/hikopensource/DAVAR-Lab-OCR -------------- Fixed formula typos in Eq. 1

3D vehicle detection based on multi-modal fusion is an important task of many applications such as autonomous driving. Although significant progress has been made, we still observe two aspects that need to be further improvement: First, the specific gain that camera images can bring to 3D detection is seldom explored by previous works. Second, many fusion algorithms run slowly, which is essential for applications with high real-time requirements(autonomous driving). To this end, we propose an end-to-end trainable single-stage multi-modal feature adaptive network in this paper, which uses image information to effectively reduce false positive of 3D detection and has a fast detection speed. A multi-modal adaptive feature fusion module based on channel attention mechanism is proposed to enable the network to adaptively use the feature of each modal. Based on the above mechanism, two fusion technologies are proposed to adapt to different usage scenarios: PointAttentionFusion is suitable for filtering simple false positive and faster; DenseAttentionFusion is suitable for filtering more difficult false positive and has better overall performance. Experimental results on the KITTI dataset demonstrate significant improvement in filtering false positive over the approach using only point cloud data. Furthermore, the proposed method can provide competitive results and has the fastest speed compared to the published state-of-the-art multi-modal methods in the KITTI benchmark., 8 pages, 6 figures

Fast and precise object detection for high-resolution aerial images has been a challenging task over the years. Due to the sharp variations on object scale, rotation, and aspect ratio, most existing methods are inefficient and imprecise. In this paper, we represent the oriented objects by polar method in polar coordinate and propose PolarDet, a fast and accurate one-stage object detector based on that representation. Our detector introduces a sub-pixel center semantic structure to further improve classifying veracity. PolarDet achieves nearly all SOTA performance in aerial object detection tasks with faster inference speed. In detail, our approach obtains the SOTA results on DOTA, UCAS-AOD, HRSC with 76.64\% mAP, 97.01\% mAP, and 90.46\% mAP respectively. Most noticeably, our PolarDet gets the best performance and reaches the fastest speed(32fps) at the UCAS-AOD dataset., Comment: 11 pages, 10 figures, 5 tables

Tibetan foxes (Vulpes ferrilata) have been confirmed as the main wild definitive hosts in echinococcosis transmission in the eastern Tibetan Plateau. However, little information is available about the epidemiology in wildlife from the perspective of the Taeniidae family, which is essential knowledge in understanding the epidemiology and phylogeography of cestode species in the Tibetan plateau. Therefore, in this study, we used copro-PCR techniques, by amplifying nad1 and cox1 gene fragments, to detect the taeniid species from Tibetan fox feces collected in Shiqu County, (Sichuan Province, China), eastern Tibetan Plateau. Phylogenetic relationships between amplified sequences and existed Taenia species genotypes were evaluated. Then, the maximum prevalence (positive PCR results from at least one primer pair) and the conservative prevalence (positive PCR results from at least two primer pairs) were calculated. Thirty-six Tibetan fox feces were analyzed. Echinococcus multilocularis (conservative prevalence ± 95% CI: 22.2% ± 13.6%; maximum prevalence ± 95% CI: 33.3% ± 15.4%) and E. shiquicus (2.8 ± 5.4%; 8.3 ± 9.0%) was detected. Meanwhile, DNA fragments of T. polyacantha were detected with high similarity to NCBI sequences (cox1, 94.0%) and to the larva sample DNA sequenced in this study (93.4%), and were supported by phylogenetic analysis. Thus, T. polyacantha might infect Tibetan foxes (5.6% ± 7.5%, 11.1% ± 10.3%). Our limited findings in the epidemiology of parasitic Taenia species suggest that sylvatic transmission cycles for a more species-rich Taeniid community must be established between wild canids and small mammals than just for the two Echinococcus species. Besides, discrepancies in different primer pairs in detecting the taeniid species were evaluated. The sensitivity of some widely used universal primer pairs was poor in detecting Taenia species from canid copro-DNA samples. It is still challenging to the development of effective taeniid species-specific molecular markers especially for non-zoonotic species., Graphical abstract Image 1, Highlights • Taeniidae species DNA was detected in Tibetan fox feces. • A novel primer was developed exclusively for Taeniidae species.

In this paper we propose a novel decomposition method based on filter group approximation, which can significantly reduce the redundancy of deep convolutional neural networks (CNNs) while maintaining the majority of feature representation. Unlike other low-rank decomposition algorithms which operate on spatial or channel dimension of filters, our proposed method mainly focuses on exploiting the filter group structure for each layer. For several commonly used CNN models, including VGG and ResNet, our method can reduce over 80% floating-point operations (FLOPs) with less accuracy drop than state-of-the-art methods on various image classification datasets. Besides, experiments demonstrate that our method is conducive to alleviating degeneracy of the compressed network, which hurts the convergence and performance of the network.

In this paper we propose a novel decomposition method based on filter group approximation, which can significantly reduce the redundancy of deep convolutional neural networks (CNNs) while maintaining the majority of feature representation. Unlike other low-rank decomposition algorithms which operate on spatial or channel dimension of filters, our proposed method mainly focuses on exploiting the filter group structure for each layer. For several commonly used CNN models, including VGG and ResNet, our method can reduce over 80% floating-point operations (FLOPs) with less accuracy drop than state-of-the-art methods on various image classification datasets. Besides, experiments demonstrate that our method is conducive to alleviating degeneracy of the compressed network, which hurts the convergence and performance of the network., Comment: Accepted by ECCV2018