In this paper, different from previous methods performing knowledge distillation for densely pairwise relations, we propose a novel intra-class feature variation distillation (IFVD) to transfer the intra-class feature variation (IFV) of the cumbersome model (teacher) to the compact model (student).
Extensive experiments on both open-source and in-house datasets consistently demonstrate the effectiveness of the proposed method over some CNN and Transformer-based segmentation methods.
Yet, most existing hard pixel mining strategies for semantic segmentation often rely on pixel's loss value, which tends to decrease during training.
In this paper, considering the sensitivity of different modalities to diverse tumor regions, we propose a Category Aware Group Self-Support Learning framework, called GSS, to make up for the information deficit among the modalities in the individual modal feature extraction phase.
This results in a representation that preserves the inherent characteristic of the curvilinear structure while being robust to contrast changes.
1 code implementation • 18 Nov 2021 • Xiang Bai, Hanchen Wang, Liya Ma, Yongchao Xu, Jiefeng Gan, Ziwei Fan, Fan Yang, Ke Ma, Jiehua Yang, Song Bai, Chang Shu, Xinyu Zou, Renhao Huang, Changzheng Zhang, Xiaowu Liu, Dandan Tu, Chuou Xu, Wenqing Zhang, Xi Wang, Anguo Chen, Yu Zeng, Dehua Yang, Ming-Wei Wang, Nagaraj Holalkere, Neil J. Halin, Ihab R. Kamel, Jia Wu, Xuehua Peng, Xiang Wang, Jianbo Shao, Pattanasak Mongkolwat, Jianjun Zhang, Weiyang Liu, Michael Roberts, Zhongzhao Teng, Lucian Beer, Lorena Escudero Sanchez, Evis Sala, Daniel Rubin, Adrian Weller, Joan Lasenby, Chuangsheng Zheng, Jianming Wang, Zhen Li, Carola-Bibiane Schönlieb, Tian Xia
Artificial intelligence (AI) provides a promising substitution for streamlining COVID-19 diagnoses.
1 code implementation • 19 Jul 2021 • Dawei Du, Longyin Wen, Pengfei Zhu, Heng Fan, QinGhua Hu, Haibin Ling, Mubarak Shah, Junwen Pan, Ali Al-Ali, Amr Mohamed, Bakour Imene, Bin Dong, Binyu Zhang, Bouchali Hadia Nesma, Chenfeng Xu, Chenzhen Duan, Ciro Castiello, Corrado Mencar, Dingkang Liang, Florian Krüger, Gennaro Vessio, Giovanna Castellano, Jieru Wang, Junyu Gao, Khalid Abualsaud, Laihui Ding, Lei Zhao, Marco Cianciotta, Muhammad Saqib, Noor Almaadeed, Omar Elharrouss, Pei Lyu, Qi Wang, Shidong Liu, Shuang Qiu, Siyang Pan, Somaya Al-Maadeed, Sultan Daud Khan, Tamer Khattab, Tao Han, Thomas Golda, Wei Xu, Xiang Bai, Xiaoqing Xu, Xuelong Li, Yanyun Zhao, Ye Tian, Yingnan Lin, Yongchao Xu, Yuehan Yao, Zhenyu Xu, Zhijian Zhao, Zhipeng Luo, Zhiwei Wei, Zhiyuan Zhao
Crowd counting on the drone platform is an interesting topic in computer vision, which brings new challenges such as small object inference, background clutter and wide viewpoint.
Specifically, we perform domain adaptation on the affinity relationship between adjacent pixels termed affinity space of source and target domain.
Cardiac MRI segmentation plays a crucial role in clinical diagnosis for evaluating personalized cardiac performance parameters.
In this paper, we propose a fast image segmentation method based on a novel super boundary-to-pixel direction (super-BPD) and a customized segmentation algorithm with super-BPD.
In this work, inspired by the success of neural architecture search (NAS), which can identify better architectures than human-designed ones, we propose automated STR (AutoSTR) to search data-dependent backbones to boost text recognition performance.
A major issue is that the density map on dense regions usually accumulates density values from a number of nearby Gaussian blobs, yielding different large density values on a small set of pixels.
Yet, the widely adopted horizontal bounding box representation is not appropriate for ubiquitous oriented objects such as objects in aerial images and scene texts.
Ranked #38 on Object Detection In Aerial Images on DOTA (using extra training data)
Recently, end-to-end text spotting that aims to detect and recognize text from cluttered images simultaneously has received particularly growing interest in computer vision.
Dense crowd counting aims to predict thousands of human instances from an image, by calculating integrals of a density map over image pixels.
1 code implementation • 1 Apr 2019 • Hugo J. Kuijf, J. Matthijs Biesbroek, Jeroen de Bresser, Rutger Heinen, Simon Andermatt, Mariana Bento, Matt Berseth, Mikhail Belyaev, M. Jorge Cardoso, Adrià Casamitjana, D. Louis Collins, Mahsa Dadar, Achilleas Georgiou, Mohsen Ghafoorian, Dakai Jin, April Khademi, Jesse Knight, Hongwei Li, Xavier Lladó, Miguel Luna, Qaiser Mahmood, Richard McKinley, Alireza Mehrtash, Sébastien Ourselin, Bo-yong Park, HyunJin Park, Sang Hyun Park, Simon Pezold, Elodie Puybareau, Leticia Rittner, Carole H. Sudre, Sergi Valverde, Verónica Vilaplana, Roland Wiest, Yongchao Xu, Ziyue Xu, Guodong Zeng, Jian-Guo Zhang, Guoyan Zheng, Christopher Chen, Wiesje van der Flier, Frederik Barkhof, Max A. Viergever, Geert Jan Biessels
Segmentation methods had to be containerized and submitted to the challenge organizers.
Experimental results show that the proposed TextField outperforms the state-of-the-art methods by a large margin (28% and 8%) on two curved text datasets: Total-Text and CTW1500, respectively, and also achieves very competitive performance on multi-oriented datasets: ICDAR 2015 and MSRA-TD500.
Ranked #22 on Scene Text Detection on Total-Text
In the present article, we depart from this strategy by training a CNN to predict a two-dimensional vector field, which maps each scene point to a candidate skeleton pixel, in the spirit of flux-based skeletonization algorithms.
Ranked #1 on Object Skeleton Detection on SK-LARGE
Person re-identification (re-ID) is a highly challenging task due to large variations of pose, viewpoint, illumination, and occlusion.
Recently, many methods of person re-identification (Re-ID) rely on part-based feature representation to learn a discriminative pedestrian descriptor.
Then, we combine the word embedding of the recognized words and the deep visual features into a single representation, which is optimized by a convolutional neural network for fine-grained image classification.
Many image simplification and segmentation methods are driven by the optimization of an energy functional, for instance the celebrated Mumford-Shah functional.