no code implementations • ECCV 2020 • Sibei Yang, Guanbin Li, Yizhou Yu
Phrase level visual grounding aims to locate in an image the corresponding visual regions referred to by multiple noun phrases in a given sentence.
no code implementations • 26 Mar 2024 • Ganlong Zhao, Guanbin Li, Weikai Chen, Yizhou Yu
Recent advances in Iterative Vision-and-Language Navigation (IVLN) introduce a more meaningful and practical paradigm of VLN by maintaining the agent's memory across tours of scenes.
1 code implementation • 19 Mar 2024 • Yunxiang Fu, Chaoqi Chen, Yu Qiao, Yizhou Yu
The acquisition of large-scale, high-quality data is a resource-intensive and time-consuming endeavor.
no code implementations • 4 Mar 2024 • Qiushan Guo, Shalini De Mello, Hongxu Yin, Wonmin Byeon, Ka Chun Cheung, Yizhou Yu, Ping Luo, Sifei Liu
Vision language models (VLMs) have experienced rapid advancements through the integration of large language models (LLMs) with image-text pairs, yet they struggle with detailed regional visual understanding due to limited spatial awareness of the vision encoder, and the use of coarse-grained training data that lacks detailed, region-specific captions.
no code implementations • 27 Feb 2024 • Meng Lou, Hanning Ying, Xiaoqing Liu, Hong-Yu Zhou, Yuqing Zhang, Yizhou Yu
This study proposes a novel Siamese Dual-Resolution Transformer (SDR-Former) framework, specifically designed for liver lesion classification in 3D multi-phase CT and MR imaging with varying phase counts.
no code implementations • 7 Feb 2024 • Gangming Zhao, Chaoqi Chen, Wenhao He, Chengwei Pan, Chaowei Fang, Jinpeng Li, Xilin Chen, Yizhou Yu
Moreover, as adjusting to the most recent target domain can interfere with the features learned from previous target domains, we develop a conservative sparse attention mechanism.
1 code implementation • 5 Feb 2024 • Jiarun Liu, Hao Yang, Hong-Yu Zhou, Yan Xi, Lequan Yu, Yizhou Yu, Yong Liang, Guangming Shi, Shaoting Zhang, Hairong Zheng, Shanshan Wang
However, it is challenging for existing methods to model long-range global information, where convolutional neural networks (CNNs) are constrained by their local receptive fields, and vision transformers (ViTs) suffer from high quadratic complexity of their attention mechanism.
1 code implementation • 22 Jan 2024 • Chenyu Lian, Hong-Yu Zhou, Yizhou Yu, Liansheng Wang
Parameter-efficient fine-tuning (PEFT) that was initially developed for exploiting pre-trained large language models has recently emerged as an effective approach to perform transfer learning on computer vision tasks.
no code implementations • 21 Jan 2024 • Jichang Li, Guanbin Li, Yizhou Yu
Once the graph has been refined, Adaptive Betweenness Clustering is introduced to facilitate semantic transfer by using across-domain betweenness clustering and within-domain betweenness clustering, thereby propagating semantic label information from labeled samples across domains to unlabeled target data.
no code implementations • 21 Jan 2024 • Jichang Li, Guanbin Li, Yizhou Yu
However, existing SSDA work fails to make full use of label information from both source and target domains for feature alignment across domains, resulting in label mismatch in the label space during model testing.
Semi-supervised Domain Adaptation Unsupervised Domain Adaptation
no code implementations • 11 Jan 2024 • Xinyuan Wang, Chengwei Pan, Hongming Dai, Gangming Zhao, Jinpeng Li, Xiao Zhang, Yizhou Yu
In this study, we leverage Fourier domain learning as a substitute for multi-scale convolutional kernels in 3D hierarchical segmentation models, which can reduce computational expenses while preserving global receptive fields within the network.
1 code implementation • 19 Dec 2023 • Jichang Li, Guanbin Li, Hui Cheng, Zicheng Liao, Yizhou Yu
However, these prior methods do not learn noise filters by exploiting knowledge across all clients, leading to sub-optimal and inferior noise filtering performance and thus damaging training stability.
1 code implementation • 30 Oct 2023 • Meng Lou, Hong-Yu Zhou, Sibei Yang, Yizhou Yu
Furthermore, when stacking token mixers that consist of convolution and self-attention to form a deep network, the static nature of convolution hinders the fusion of features previously generated by self-attention into convolution kernels.
no code implementations • 14 Oct 2023 • Hao Wang, Qiang Song, Ruofeng Yin, Rui Ma, Yizhou Yu, Yi Chang
In this paper, we propose B-Spine, a novel deep learning pipeline to learn B-spline curve representation of the spine and estimate the Cobb angles for spinal curvature estimation from low-quality X-ray images.
no code implementations • ICCV 2023 • Chaoqi Chen, Luyao Tang, Leitian Tao, Hong-Yu Zhou, Yue Huang, Xiaoguang Han, Yizhou Yu
Albeit the notable performance on in-domain test points, it is non-trivial for deep neural networks to attain satisfactory accuracy when deploying in the open world, where novel domains and object classes often occur.
no code implementations • 22 Sep 2023 • Chenghong Li, Leyang Jin, Yujian Zheng, Yizhou Yu, Xiaoguang Han
Three modules are then carefully designed: RootFinder firstly localizes the fiber root positions which indicates where to grow; OriPredictor predicts an orientation field in the 3D space to guide the growing of fibers; FiberEnder is designed to determine when to stop the growth of each fiber.
2 code implementations • CVPR 2023 • Ganlong Zhao, Guanbin Li, Yipeng Qin, Yizhou Yu
In this paper, we propose a novel dataset condensation method based on distribution matching, which is more efficient and promising.
no code implementations • 3 Jul 2023 • Zhongjin Luo, Dong Du, Heming Zhu, Yizhou Yu, Hongbo Fu, Xiaoguang Han
User studies demonstrate the superiority of our system over existing modeling tools in terms of the ease to use and visual quality of results.
no code implementations • 30 Jun 2023 • Ganlong Zhao, Guanbin Li, Yipeng Qin, Jinjin Zhang, Zhenhua Chai, Xiaolin Wei, Liang Lin, Yizhou Yu
In this paper, we address a complex but practical scenario in semi-supervised learning (SSL) named open-set SSL, where unlabeled data contain both in-distribution (ID) and out-of-distribution (OOD) samples.
1 code implementation • 1 Jun 2023 • Hong-Yu Zhou, Yizhou Yu, Chengdi Wang, Shu Zhang, Yuanxu Gao, Jia Pan, Jun Shao, Guangming Lu, Kang Zhang, Weimin Li
During the diagnostic process, clinicians leverage multimodal information, such as chief complaints, medical images, and laboratory-test results.
1 code implementation • ICCV 2023 • Qiushan Guo, Chuofan Ma, Yi Jiang, Zehuan Yuan, Yizhou Yu, Ping Luo
Learning image classification and image generation using the same set of network parameters is a challenging problem.
1 code implementation • 4 Apr 2023 • Qiushan Guo, Yizhou Yu, Yi Jiang, Jiannan Wu, Zehuan Yuan, Ping Luo
We extend our pretext task to supervised pre-training, which achieves a similar performance to self-supervised learning.
1 code implementation • 30 Jan 2023 • Hong-Yu Zhou, Chenyu Lian, Liansheng Wang, Yizhou Yu
Modern studies in radiograph representation learning rely on either self-supervision to encode invariant semantics or associated radiology reports to incorporate medical expertise, while the complementarity between them is barely noticed.
1 code implementation • 30 Jan 2023 • Hong-Yu Zhou, Yunxiang Fu, Zhicheng Zhang, Cheng Bian, Yizhou Yu
Protein representation learning has primarily benefited from the remarkable development of language models (LMs).
1 code implementation • 12 Jan 2023 • Ruifei Zhang, Sishuo Liu, Yizhou Yu, Guanbin Li
Since the two tasks rely on similar feature information, the unlabeled data effectively enhances the representation of the network to the lesion regions and further improves the segmentation performance.
1 code implementation • 12 Jan 2023 • Ruifei Zhang, Guanbin Li, Zhen Li, Shuguang Cui, Dahong Qian, Yizhou Yu
To tackle these issues, we propose an adaptive context selection based encoder-decoder framework which is composed of Local Context Attention (LCA) module, Global Context Module (GCM) and Adaptive Selection Module (ASM).
no code implementations • 11 Jan 2023 • Hong-Yu Zhou, Chixiang Lu, Liansheng Wang, Yizhou Yu
Self-supervised representation learning has been extremely successful in medical image analysis, as it requires no human annotations to provide transferable representations for downstream tasks.
no code implementations • 6 Jan 2023 • Gangming Zhao, Kongming Liang, Chengwei Pan, Fandong Zhang, Xianpeng Wu, Xinyang Hu, Yizhou Yu
To tackle the challenges caused by the sparsity and anisotropy of vessels, a higher percentage of graph nodes are distributed in areas that potentially contain vessels while a higher percentage of edges follow the orientation of potential nearbyvessels.
no code implementations • 3 Jan 2023 • Haoyu Ma, Xiangru Lin, Yizhou Yu
This paper proposes a novel UDA pipeline for semantic segmentation that unifies image-level and feature-level adaptation.
1 code implementation • 2 Jan 2023 • Hong-Yu Zhou, Chixiang Lu, Chaoqi Chen, Sibei Yang, Yizhou Yu
Recent advances in self-supervised learning (SSL) in computer vision are primarily comparative, whose goal is to preserve invariant and discriminative semantics in latent representations by comparing siamese image views.
1 code implementation • CVPR 2023 • Yixuan Sun, Yiwen Huang, Haijing Guo, Yuzhou Zhao, Runmin Wu, Yizhou Yu, Weifeng Ge, Wenqiang Zhang
Semantic correspondence have built up a new way for object recognition.
no code implementations • 2 Dec 2022 • Yinghong Liao, Wending Zhou, Xu Yan, Shuguang Cui, Yizhou Yu, Zhen Li
Moreover, to improve the 2D classifier in the target domain, we perform domain-invariant geometric adaptation from source to target and unify the 2D semantic and 3D geometric segmentation results in two domains.
1 code implementation • 28 Nov 2022 • Qianyu Guo, Hongtong Gong, Xujun Wei, Yanwei Fu, Weifeng Ge, Yizhou Yu, Wenqiang Zhang
This paper introduces a new few-shot learning pipeline that casts relevance ranking for image retrieval as binary ranking relation classification.
no code implementations • 27 Oct 2022 • Jiansen Guo, Hong-Yu Zhou, Liansheng Wang, Yizhou Yu
These phenomena indicate the potential of UNet-2022 to become the model of choice for medical image segmentation.
no code implementations • 14 Oct 2022 • Chaoqi Chen, Luyao Tang, Feng Liu, Gangming Zhao, Yue Huang, Yizhou Yu
Domain generalization (DG) enables generalizing a learning machine from multiple seen source domains to an unseen target one.
no code implementations • 27 Sep 2022 • Chaoqi Chen, Yushuang Wu, Qiyuan Dai, Hong-Yu Zhou, Mutian Xu, Sibei Yang, Xiaoguang Han, Yizhou Yu
Graph Neural Networks (GNNs) have gained momentum in graph representation learning and boosted the state of the art in a variety of areas, such as data mining (\emph{e. g.,} social network analysis and recommender systems), computer vision (\emph{e. g.,} object detection and point cloud learning), and natural language processing (\emph{e. g.,} relation extraction and sequence learning), to name a few.
no code implementations • 19 Aug 2022 • Gangming Zhao, Quanlong Feng, Chaoqi Chen, Zhen Zhou, Yizhou Yu
On the LIDC-IDRI benchmark dataset for benign-malignant classification of pulmonary nodules in CT images, our method achieves a new state-of-the-art accuracy of 95. 36\% and an AUC of 96. 54\%.
1 code implementation • 5 Aug 2022 • Jichang Li, Guanbin Li, Feng Liu, Yizhou Yu
Specifically, our method is divided into two steps: 1) Neighborhood Collective Noise Verification to separate all training samples into a clean or noisy subset, 2) Neighborhood Collective Label Correction to relabel noisy samples, and then auxiliary techniques are used to assist further model optimization.
no code implementations • 31 Jul 2022 • Zihao Yin, Ping Gong, Chunyu Wang, Yizhou Yu, Yizhou Wang
As an important upstream task for many medical applications, supervised landmark localization still requires non-negligible annotation costs to achieve desirable performance.
1 code implementation • 29 Jul 2022 • Ganlong Zhao, Guanbin Li, Yipeng Qin, Feng Liu, Yizhou Yu
In this paper, we propose a two-stage clean samples identification method to address the aforementioned challenge.
Ranked #3 on Image Classification on Clothing1M (using extra training data)
1 code implementation • 1 Jul 2022 • Chengwei Pan, Gangming Zhao, Junjie Fang, Baolian Qi, Jiaheng Liu, Chaowei Fang, Dingwen Zhang, Jinpeng Li, Yizhou Yu
Although deep learning algorithms have been intensively developed for computer-aided tuberculosis diagnosis (CTD), they mainly depend on carefully annotated datasets, leading to much time and resource consumption.
no code implementations • 6 Jun 2022 • Chaoqi Chen, Jiongcheng Li, Hong-Yu Zhou, Xiaoguang Han, Yue Huang, Xinghao Ding, Yizhou Yu
However, both the global and local alignment approaches fail to capture the topological relations among different foreground objects as the explicit dependencies and interactions between and within domains are neglected.
no code implementations • 21 Apr 2022 • Churan Wang, Jing Li, Xinwei Sun, Fandong Zhang, Yizhou Yu, Yizhou Wang
To resolve this problem, we propose a novel framework, namely Domain Invariant Model with Graph Convolutional Network (DIM-GCN), which only exploits invariant disease-related features from multiple domains.
1 code implementation • 29 Mar 2022 • Yunlong Zhang, Xin Lin, Yihong Zhuang, LiyanSun, Yue Huang, Xinghao Ding, Guisheng Wang, Lin Yang, Yizhou Yu
Comprehensive experiments on the T2 modality of BraTS demonstrate that the proposed method substantially outperforms the state-of-the-art methods.
no code implementations • CVPR 2022 • Chaoqi Chen, Jiongcheng Li, Xiaoguang Han, Xiaoqing Liu, Yizhou Yu
Such holistic semantic structure, referred to as meta-knowledge here, is crucial for learning generalizable representations.
no code implementations • CVPR 2022 • Qiushan Guo, Yao Mu, Jianyu Chen, Tianqi Wang, Yizhou Yu, Ping Luo
Further, we overcome these challenges by introducing a novel approach, Scale-Equivalent Distillation (SED), which is a simple yet effective end-to-end knowledge distillation framework robust to large object size variance and class imbalance.
1 code implementation • CVPR 2022 • Yangji He, Weihan Liang, Dongyang Zhao, Hong-Yu Zhou, Weifeng Ge, Yizhou Yu, Wenqiang Zhang
To improve data efficiency, we propose hierarchically cascaded transformers that exploit intrinsic image structures through spectral tokens pooling and optimize the learnable parameters through latent attribute surrogates.
Ranked #1 on Few-Shot Learning on Mini-ImageNet - 1-Shot Learning
no code implementations • 22 Feb 2022 • Yushuang Wu, Zizheng Yan, Shengcai Cai, Guanbin Li, Yizhou Yu, Xiaoguang Han, Shuguang Cui
Semantic segmentation of point cloud usually relies on dense annotation that is exhausting and costly, so it attracts wide attention to investigate solutions for the weakly supervised scheme with only sparse points annotated.
Representation Learning Weakly supervised Semantic Segmentation +1
1 code implementation • 31 Jan 2022 • Tan Yu, Gangming Zhao, Ping Li, Yizhou Yu
To improve efficiency, recent Vision Transformers adopt local self-attention mechanisms, where self-attention is computed within local windows.
no code implementations • 25 Jan 2022 • Jianwei Xu, Ran Zhao, Yizhou Yu, Qingwei Zhang, Xianzhang Bian, Jun Wang, Zhizheng Ge, Dahong Qian
In order to solve these problems, our method combines the two-dimensional (2-D) CNN-based real-time object detector network with spatiotemporal information.
no code implementations • 7 Jan 2022 • Dingwen Zhang, Guohai Huang, Qiang Zhang, Jungong Han, Junwei Han, Yizhou Yu
Recent advances in machine learning and prevalence of digital medical images have opened up an opportunity to address the challenging brain tumor segmentation (BTS) task by using deep convolutional neural networks.
1 code implementation • 5 Jan 2022 • Shu Zhang, Zihao Li, Hong-Yu Zhou, Jiechao Ma, Yizhou Yu
The difficulties in both data acquisition and annotation substantially restrict the sample sizes of training datasets for 3D medical imaging applications.
Ranked #1 on Medical Object Detection on DeepLesion
1 code implementation • 4 Nov 2021 • Hong-Yu Zhou, Xiaoyu Chen, Yinghao Zhang, Ruibang Luo, Liansheng Wang, Yizhou Yu
Pre-training lays the foundation for recent successes in radiograph analysis supported by deep learning.
1 code implementation • 11 Oct 2021 • Kongming Liang, Kai Han, Xiuli Li, Xiaoqing Cheng, Yiming Li, Yizhou Wang, Yizhou Yu
In this paper, we propose a symmetry enhanced attention network (SEAN) for acute ischemic infarct segmentation.
no code implementations • 8 Oct 2021 • Mingzhou Liu, Xinwei Sun, Fandong Zhang, Yizhou Yu, Yizhou Wang
Finally, to implement this contextual posterior, we introduce a Transformer that takes the object's information as a reference and locates correlated contextual factors.
no code implementations • 29 Sep 2021 • Qiushan Guo, Yizhou Yu, Ping Luo
Furthermore, the limited annotations in semi-supervised learning scale up the challenges: large variance of object sizes and class imbalance (i. e., the extreme ratio between background and object), hindering the performance of prior arts.
2 code implementations • ICCV 2021 • Hong-Yu Zhou, Chixiang Lu, Sibei Yang, Xiaoguang Han, Yizhou Yu
From this perspective, we introduce Preservational Learning to reconstruct diverse image contexts in order to preserve more information in learned representations.
2 code implementations • 7 Sep 2021 • Hong-Yu Zhou, Jiansen Guo, Yinghao Zhang, Lequan Yu, Liansheng Wang, Yizhou Yu
Transformer, the model of choice for natural language processing, has drawn scant attention from the medical imaging community.
Ranked #1 on Medical Image Segmentation on Synapse
no code implementations • 24 Aug 2021 • Gang Yu, Zhongzhi Yu, Yemin Shi, Yingshuo Wang, Xiaoqing Liu, Zheming Li, Yonggen Zhao, Fenglei Sun, Yizhou Yu, Qiang Shu
The first stage structuralizes test results by extracting relevant numerical values from clinical notes, and the disease identification stage provides a diagnosis based on text-form clinical notes and the structured data obtained from the first stage.
1 code implementation • ICCV 2021 • Bingchen Gong, Yinyu Nie, Yiqun Lin, Xiaoguang Han, Yizhou Yu
Main-stream methods predict the missing shapes by decoding a global feature learned from the input point cloud, which often leads to deficient results in preserving topology consistency and surface details.
1 code implementation • 16 Aug 2021 • Xinru Zhang, Chenghao Liu, Ni Ou, Xiangzhu Zeng, Xiaoliang Xiong, Yizhou Yu, Zhiwen Liu, Chuyang Ye
Data augmentation is a widely used strategy that improves the training of CNNs, and the design of the augmentation method for brain lesion segmentation is still an open problem.
no code implementations • 11 Aug 2021 • Hong-Yu Zhou, Chixiang Lu, Sibei Yang, Yizhou Yu
Vision transformers have attracted much attention from computer vision researchers as they are not restricted to the spatial inductive bias of ConvNets.
2 code implementations • ICCV 2021 • Gangming Zhao, Weifeng Ge, Yizhou Yu
State-of-the-art methods for multi-scale feature learning focus on performing feature interactions across space and scales using neural networks with a fixed topology.
1 code implementation • ICCV 2021 • Dongyang Zhao, Ziyang Song, Zhenghao Ji, Gangming Zhao, Weifeng Ge, Yizhou Yu
We follow the coarse-to-fine matching strategy and build a top-down feature and matching enhancement scheme that is coupled with the multi-scale hierarchy of deep convolutional neural networks.
Ranked #11 on Semantic correspondence on SPair-71k
1 code implementation • 14 Jul 2021 • Baolian Qi, Gangming Zhao, Xin Wei, Changde Du, Chengwei Pan, Yizhou Yu, Jinpeng Li
To model the relationship, we propose the Graph Regularized Embedding Network (GREN), which leverages the intra-image and inter-image information to locate diseases on chest X-ray images.
1 code implementation • CVPR 2021 • Sibei Yang, Meng Xia, Guanbin Li, Hong-Yu Zhou, Yizhou Yu
In this paper, we tackle the challenge by jointly performing compositional visual reasoning and accurate segmentation in a single stage via the proposed novel Bottom-Up Shift (BUS) and Bidirectional Attentive Refinement (BIAR) modules.
no code implementations • 13 Jun 2021 • Chenxin Li, Qi Qi, Xinghao Ding, Yue Huang, Dong Liang, Yizhou Yu
In this paper, we propose a novel DG scheme of episodic training with task augmentation on medical imaging classification.
no code implementations • 3 Jun 2021 • Hong-Yu Zhou, Chengdi Wang, Haofeng Li, Gang Wang, Shu Zhang, Weimin Li, Yizhou Yu
Semi-Supervised classification and segmentation methods have been widely investigated in medical image analysis.
no code implementations • 31 May 2021 • Chenxin Li, Wenao Ma, Liyan Sun, Xinghao Ding, Yue Huang, Guisheng Wang, Yizhou Yu
In this paper, to address the above issues, we propose a hierarchical deep network where an attention mechanism localizes the low-contrast capillary regions guided by the whole vessels, and enhance the spatial activation in those areas for the sub-type vessels.
no code implementations • 21 May 2021 • Yuhang Liu, Fandong Zhang, Chaoqi Chen, Siwen Wang, Yizhou Wang, Yizhou Yu
In this paper, we propose an Anatomy-aware Graph convolutional Network (AGN), which is tailored for mammogram mass detection and endows existing detection methods with multi-view reasoning ability.
1 code implementation • 21 Apr 2021 • Jie Lian, Jingyu Liu, Shu Zhang, Kai Gao, Xiaoqing Liu, Dingwen Zhang, Yizhou Yu
Leveraging on constant structure and disease relations extracted from domain knowledge, we propose a structure-aware relation network (SAR-Net) extending Mask R-CNN.
2 code implementations • CVPR 2021 • Jichang Li, Guanbin Li, Yemin Shi, Yizhou Yu
Pseudo labeling expands the number of ``labeled" samples in each class in the target domain, and thus produces a more robust and powerful cluster core for each class to facilitate adversarial learning.
no code implementations • 30 Mar 2021 • Hong-Yu Zhou, Hualuo Liu, Shilei Cao, Dong Wei, Chixiang Lu, Yizhou Yu, Kai Ma, Yefeng Zheng
In this paper, we show that such process can be integrated into the one-shot segmentation task which is a very challenging but meaningful topic.
1 code implementation • CVPR 2021 • Chaoqi Chen, Zebiao Zheng, Yue Huang, Xinghao Ding, Yizhou Yu
Motivated by this, we propose an Implicit Instance-Invariant Network (I3Net), which is tailored for adapting one-stage detectors and implicitly learns instance-invariant features via exploiting the natural characteristics of deep features in different layers.
no code implementations • CVPR 2021 • Haoyu Ma, Xiangru Lin, Zifeng Wu, Yizhou Yu
Unsupervised domain adaptation (UDA) in semantic segmentation is a fundamental yet promising task relieving the need for laborious annotation works.
Ranked #23 on Synthetic-to-Real Translation on SYNTHIA-to-Cityscapes
no code implementations • CVPR 2021 • Xiangru Lin, Guanbin Li, Yizhou Yu
Intuitively, we comprehend the semantics of the instruction to form an overview of where a bathroom is and what a blue towel is in mind; then, we navigate to the target location by consistently matching the bathroom appearance in mind with the current scene.
2 code implementations • CVPR 2021 • Haolin Liu, Anran Lin, Xiaoguang Han, Lei Yang, Yizhou Yu, Shuguang Cui
Grounding referring expressions in RGBD image has been an emerging field.
no code implementations • ICCV 2021 • Chaoqi Chen, Jiongcheng Li, Zebiao Zheng, Yue Huang, Xinghao Ding, Yizhou Yu
Domain Adaptive Object Detection (DAOD) relieves the reliance on large-scale annotated data by transferring the knowledge learned from a labeled source domain to a new unlabeled target domain.
1 code implementation • 16 Dec 2020 • Shu Zhang, Jincheng Xu, Yu-Chun Chen, Jiechao Ma, Zihao Li, Yizhou Wang, Yizhou Yu
We demonstrate that with the novel pre-training method, the proposed MP3D FPN achieves state-of-the-art detection performance on the DeepLesion dataset (3. 48% absolute improvement in the sensitivity of FPs@0. 5), significantly surpassing the baseline method by up to 6. 06% (in MAP@0. 5) which adopts 2D convolution for 3D context modeling.
Ranked #4 on Medical Object Detection on DeepLesion
no code implementations • 14 Dec 2020 • Jiafa He, Chengwei Pan, Can Yang, Ming Zhang, Yang Wang, Xiaowei Zhou, Yizhou Yu
The main idea is to use CNNs to learn local appearances of vessels in image crops while using another point-cloud network to learn the global geometry of vessels in the entire image.
no code implementations • 10 Dec 2020 • Liyan Sun, Chenxin Li, Xinghao Ding, Yue Huang, Guisheng Wang, Yizhou Yu
Motivated by the spatial consistency and regularity in medical images, we developed an efficient global correlation module to capture the correlation between a support and query image and incorporate it into the deep network called global correlation network.
no code implementations • 30 Nov 2020 • Huangxing Lin, Yihong Zhuang, Yue Huang, Xinghao Ding, Yizhou Yu, Xiaoqing Liu, John Paisley
Coupling the noisy data output from ADANI with the corresponding ground-truth, a denoising CNN is then trained in a fully-supervised manner.
1 code implementation • 23 Oct 2020 • Liyan Sun, Jianxiong Wu, Xinghao Ding, Yue Huang, Guisheng Wang, Yizhou Yu
We further proposed a localization branch realized via an aggregation of high-level features in a deep decoder to predict locations of organ and lesion, which enriches student segmentor with precise localization information.
1 code implementation • 19 Oct 2020 • Jie Lian, Jingyu Liu, Yizhou Yu, Mengyuan Ding, Yaoci Lu, Yi Lu, Jie Cai, Deshou Lin, Miao Zhang, Zhe Wang, Kai He, Yijie Yu
The detection of thoracic abnormalities challenge is organized by the Deepwise AI Lab.
no code implementations • 9 Oct 2020 • Yicheng Wu, Chengwei Pan, Shuqi Wang, Ming Zhang, Yong Xia, Yizhou Yu
Analyzing the morphological attributes of blood vessels plays a critical role in the computer-aided diagnosis of many cardiovascular and ophthalmologic diseases.
no code implementations • 9 Oct 2020 • Gangming Zhao, Chaowei Fang, Guanbin Li, Licheng Jiao, Yizhou Yu
Aimed at improving the performance of existing detection methods, we propose a deep end-to-end module to exploit the contralateral context information for enhancing feature representations of disease proposals.
no code implementations • 30 Sep 2020 • Chu-ran Wang, Jing Li, Fandong Zhang, Xinwei Sun, Hao Dong, Yizhou Yu, Yizhou Wang
Mammogram benign or malignant classification with only image-level labels is challenging due to the absence of lesion annotations.
no code implementations • 17 Sep 2020 • Haofeng Li, Yirui Zeng, Guanbin Li, Liang Lin, Yizhou Yu
The field of computer vision has witnessed phenomenal progress in recent years partially due to the development of deep convolutional neural networks.
1 code implementation • 10 Jul 2020 • Shen Wang, Kongming Liang, Yiming Li, Yizhou Yu, Yizhou Wang
Nevertheless, there are still great challenges with brain midline delineation, such as the largely deformed midline caused by the mass effect and the possible morphological failure that the predicted midline is not a connected curve.
1 code implementation • 17 Jun 2020 • Jingyu Liu, Jie Lian, Yizhou Yu
Instance level detection of thoracic diseases or abnormalities are crucial for automatic diagnosis in chest X-ray images.
1 code implementation • CVPR 2020 • Sibei Yang, Guanbin Li, Yizhou Yu
The linguistic structure of a referring expression provides a layout of reasoning over the visual contents, and it is often crucial to align and jointly understand the image and the referring expression.
no code implementations • 11 Mar 2020 • Zhongzhi Yu, Yemin Shi, Tiejun Huang, Yizhou Yu
Thus, KQ can represent the weight tensor in the convolution layer with low-bit indexes and a kernel codebook with limited size, which enables KQ to achieve significant compression ratio.
no code implementations • 27 Feb 2020 • Shen Wang, Kongming Liang, Chengwei Pan, Chuyang Ye, Xiuli Li, Feng Liu, Yizhou Yu, Yizhou Wang
The midline related pathological image features are crucial for evaluating the severity of brain compression caused by stroke or traumatic brain injury (TBI).
1 code implementation • 24 Feb 2020 • Runmin Wu, Kunyao Zhang, Lijun Wang, Yue Wang, Pingping Zhang, Huchuan Lu, Yizhou Yu
Though recent research has achieved remarkable progress in generating realistic images with generative adversarial networks (GANs), the lack of training stability is still a lingering concern of most GANs, especially on high-resolution inputs and complex datasets.
no code implementations • 22 Jan 2020 • Haofeng Li, Guanbin Li, BinBin Yang, Guanqi Chen, Liang Lin, Yizhou Yu
The proposed algorithm for the first time achieves competitive accuracy and high inference efficiency simultaneously with a single CPU thread.
no code implementations • 23 Nov 2019 • Chaowei Fang, Guanbin Li, Chengwei Pan, Yiming Li, Yizhou Yu
Recently 3D volumetric organ segmentation attracts much research interest in medical image analysis due to its significance in computer aided diagnosis.
no code implementations • 23 Nov 2019 • Chaowei Fang, Guanbin Li, Xiaoguang Han, Yizhou Yu
It further recurrently exploits the reconstructed results and intermediate features of a sequence of preceding frames to improve the initial super-resolution of the current frame by modelling the coherence of structural facial features across frames.
no code implementations • ICCV 2019 • Sibei Yang, Guanbin Li, Yizhou Yu
In this paper, we explore the problem of referring expression comprehension from the perspective of language-driven visual reasoning, and propose a dynamic graph attention network to perform multi-step reasoning by modeling both the relationships among the objects in the image and the linguistic structure of the expression.
2 code implementations • ICCV 2019 • Haofeng Li, Guanqi Chen, Guanbin Li, Yizhou Yu
In this paper, we develop a multi-task motion guided video salient object detection network, which learns to accomplish two sub-tasks using two sub-networks, one sub-network for salient object detection in still images and the other for motion saliency detection in optical flow images.
1 code implementation • 10 Sep 2019 • Zihao Li, Shu Zhang, Junge Zhang, Kaiqi Huang, Yizhou Wang, Yizhou Yu
In this paper, we propose to incorporate domain knowledge in clinical practice into the model design of universal lesion detectors.
Ranked #8 on Medical Object Detection on DeepLesion
1 code implementation • CVPR 2019 • Sibei Yang, Guanbin Li, Yizhou Yu
Unfortunately, existing work on grounding referring expressions fails to accurately extract multi-order relationships from the referring expression and associate them with the objects and their related contexts in the image.
no code implementations • 9 May 2019 • Haofeng Li, Guanbin Li, Yizhou Yu
To our knowledge, this paper is the first one that mounts successful adversarial attacks on salient object detection models and verifies that adversarial samples are effective on a wide range of existing methods.
no code implementations • 27 Apr 2019 • Xiang He, Sibei Yang, Guanbin Li?, Haofeng Li, Huiyou Chang, Yizhou Yu
In this paper, we discover that global spatial dependencies and global contextual information in a biomedical image can be exploited to defend against adversarial attacks.
1 code implementation • 2 Apr 2019 • Feida Zhu, Zhetong Liang, Xixi Jia, Lei Zhang, Yizhou Yu
This benchmark includes an image dataset with groundtruth image smoothing results as well as baseline algorithms that can generate competitive edge-preserving smoothing results for a wide range of image contents.
no code implementations • 1 Apr 2019 • Kan Wu, Guanbin Li, Haofeng Li, Jianjun Zhang, Yizhou Yu
As a concrete example, a database of over 1. 2 million visual objects has been built using the proposed method, and has been successfully used in various data-driven image applications.
1 code implementation • CVPR 2019 • Yu Zeng, Yunzhi Zhuge, Huchuan Lu, Lihe Zhang, Mingyang Qian, Yizhou Yu
To this end, we propose a unified framework to train saliency detection models with diverse weak supervision sources.
12 code implementations • 28 Mar 2019 • Huikai Wu, Junge Zhang, Kaiqi Huang, Kongming Liang, Yizhou Yu
Modern approaches for semantic segmentation usually employ dilated convolutions in the backbone to extract high-resolution feature maps, which brings heavy computation complexity and memory footprint.
Ranked #40 on Semantic Segmentation on PASCAL Context
1 code implementation • CVPR 2019 • Weifeng Ge, Xiangru Lin, Yizhou Yu
We build complementary parts models in a weakly supervised manner to retrieve information suppressed by dominant object parts detected by convolutional neural networks.
Ranked #22 on Fine-Grained Image Classification on CUB-200-2011
1 code implementation • NeurIPS 2019 • Zi-Yu Wan, Dong-Dong Chen, Yan Li, Xingguang Yan, Junge Zhang, Yizhou Yu, Jing Liao
Based on the observation that visual features of test instances can be separated into different clusters, we propose a new visual structure constraint on class centers for transductive ZSL, to improve the generality of the projection function (i. e. alleviate the above domain shift problem).
no code implementations • 10 Dec 2018 • Lingbo Liu, Guanbin Li, Yuan Xie, Yizhou Yu, Qing Wang, Liang Lin
In this paper, we propose a novel cascaded backbone-branches fully convolutional neural network~(BB-FCN) for rapidly and accurately localizing facial landmarks in unconstrained and cluttered settings.
no code implementations • 27 Nov 2018 • Feida Zhu, Yizhou Yu
Such photo adjustment tools lack a semantic understanding of image contents and the resulting global color transform limits the range of artistic styles it can represent.
1 code implementation • 18 Sep 2018 • Weifeng Ge, Bingchen Gong, Yizhou Yu
With respect to a downsampled low resolution image, we model a high resolution image as a combination of two components, a deterministic component and a stochastic component.
no code implementations • 24 Jul 2018 • Xiaoguang Han, Kangcheng Hou, Dong Du, Yuda Qiu, Yizhou Yu, Kun Zhou, Shuguang Cui
To construct the mapping between 2D sketches and a vertex-wise scaling field, a novel deep learning architecture is developed.
8 code implementations • 3 Jul 2018 • Chang Gao, Derun Gu, Fangjun Zhang, Yizhou Yu
Image style transfer models based on convolutional neural networks usually suffer from high temporal inconsistency when applied to videos.
Ranked #4 on Semantic Segmentation on FMB Dataset
1 code implementation • 8 May 2018 • Yujing Sun, Yizhou Yu, Wenping Wang
While digital image quality is constantly being improved, taking high-quality photos of digital screens still remains challenging because the photos are often contaminated with moir\'{e} patterns, a result of the interference between the pixel grids of the camera sensor and the device screen.
Ranked #6 on Image Enhancement on TIP 2018
no code implementations • 30 Mar 2018 • Guanbin Li, Yizhou Yu
In this paper, we develop hybrid contrast-oriented deep neural networks to overcome the aforementioned limitations.
no code implementations • CVPR 2018 • Weifeng Ge, Sibei Yang, Yizhou Yu
In this paper, we propose a novel weakly supervised curriculum learning pipeline for multi-label object recognition, detection and semantic segmentation.
Ranked #15 on Weakly Supervised Object Detection on PASCAL VOC 2007
1 code implementation • ECCV 2018 • Yongcheng Jing, Yang Liu, Yezhou Yang, Zunlei Feng, Yizhou Yu, DaCheng Tao, Mingli Song
In this paper, we present a stroke controllable style transfer network that can achieve continuous and spatial stroke size control.
no code implementations • ICCV 2015 • Chaowei Fang, Zicheng Liao, Yizhou Yu
We introduce a new multi-dimensional nonlinear embedding -- Piecewise Flat Embedding (PFE) -- for image segmentation.
no code implementations • 21 Dec 2017 • Haofeng Li, Guanbin Li, Liang Lin, Yizhou Yu
Our proposed GAN-based framework consists of a fully convolutional design for the generator which helps to better preserve spatial structures and a joint loss function with a revised perceptual loss to capture high-level semantics in the context.
no code implementations • ICCV 2017 • Xiaoguang Han, Zhen Li, Haibin Huang, Evangelos Kalogerakis, Yizhou Yu
Our method is based on a new deep learning architecture consisting of two sub-networks: a global structure inference network and a local geometry refinement network.
no code implementations • 28 Aug 2017 • Sheng Wang, Zhen Li, Yizhou Yu, Jinbo Xu
Computational elucidation of membrane protein (MP) structures is challenging partially due to lack of sufficient solved structures for homology modeling.
no code implementations • 7 Jun 2017 • Xiaoguang Han, Chang Gao, Yizhou Yu
This system has a labor-efficient sketching interface, that allows the user to draw freehand imprecise yet expressive 2D lines representing the contours of facial features.
8 code implementations • 11 May 2017 • Yongcheng Jing, Yezhou Yang, Zunlei Feng, Jingwen Ye, Yizhou Yu, Mingli Song
We first propose a taxonomy of current algorithms in the field of NST.
no code implementations • 24 Apr 2017 • Zhen Li, Sheng Wang, Yizhou Yu, Jinbo Xu
Tested on 510 non-redundant MPs, our deep model (learned from only non-MPs) has top L/10 long-range contact prediction accuracy 0. 69, better than our deep model trained by only MPs (0. 63) and much better than a representative DCA method CCMpred (0. 47) and the CASP11 winner MetaPSICOV (0. 55).
no code implementations • CVPR 2017 • Guanbin Li, Yuan Xie, Liang Lin, Yizhou Yu
Image saliency detection has recently witnessed rapid progress due to deep convolutional neural networks.
Ranked #15 on RGB Salient Object Detection on DUTS-TE (max F-measure metric)
1 code implementation • CVPR 2017 • Weifeng Ge, Yizhou Yu
In this paper, we introduce a source-target selective joint fine-tuning scheme for improving the performance of deep learning tasks with insufficient training data.
2 code implementations • 7 Sep 2016 • Guanbin Li, Yizhou Yu
The penultimate layer of our neural network has been confirmed to be a discriminative high-level feature vector for saliency detection, which we call deep contrast feature.
1 code implementation • 25 Apr 2016 • Zhen Li, Yizhou Yu
Inspired by the recent successes of deep neural networks, in this paper, we propose an end-to-end deep network that predicts protein secondary structures from integrated local and global contextual features.
1 code implementation • 18 Apr 2016 • Zhen Li, Yukang Gan, Xiaodan Liang, Yizhou Yu, Hui Cheng, Liang Lin
Another long short-term memorized fusion layer is set up to integrate the contexts along the vertical direction from different channels, and perform bi-directional propagation of the fused vertical contexts along the horizontal direction to obtain true 2D global contexts.
no code implementations • 15 Mar 2016 • Zhicheng Yan, Hao Zhang, Yangqing Jia, Thomas Breuel, Yizhou Yu
State-of-the-art results of semantic segmentation are established by Fully Convolutional neural Networks (FCNs).
no code implementations • CVPR 2016 • Guanbin Li, Yizhou Yu
Our deep network consists of two complementary components, a pixel-level fully convolutional stream and a segment-wise spatial pooling stream.
Ranked #19 on RGB Salient Object Detection on DUTS-TE (max F-measure metric)
no code implementations • ICCV 2015 • Zhicheng Yan, Hao Zhang, Robinson Piramuthu, Vignesh Jagadeesh, Dennis Decoste, Wei Di, Yizhou Yu
In this paper, we introduce hierarchical deep CNNs (HD-CNNs) by embedding deep CNNs into a category hierarchy.
no code implementations • ICCV 2015 • Ruobing Wu, Baoyuan Wang, Wenping Wang, Yizhou Yu
Recent work on scene classification still makes use of generic CNN features in a rudimentary manner.
no code implementations • CVPR 2015 • Guanbin Li, Yizhou Yu
Visual saliency is a fundamental problem in both cognitive and computational sciences, including computer vision.
1 code implementation • 24 Dec 2014 • Zhicheng Yan, Hao Zhang, Baoyuan Wang, Sylvain Paris, Yizhou Yu
Many photographic styles rely on subtle adjustments that depend on the image content and even its semantics.
4 code implementations • 3 Oct 2014 • Zhicheng Yan, Hao Zhang, Robinson Piramuthu, Vignesh Jagadeesh, Dennis Decoste, Wei Di, Yizhou Yu
In this paper, we introduce hierarchical deep CNNs (HD-CNNs) by embedding deep CNNs into a category hierarchy.
Ranked #174 on Image Classification on CIFAR-100
no code implementations • CVPR 2013 • Ruobing Wu, Yizhou Yu, Wenping Wang
In this paper we develop a novel deep learning method that facilitates examplebased visual object category recognition.