986 citations · 1.6k across the 52 of their papers we have counts for
37 papers · 1 filter
Unity in Diversity: Multi-expert Knowledge Confrontation and Collaboration for Generalizable Vehicle Re-identification
Zhenyu Kuang, Hongyang Zhang, Mang Ye +5
Generalizable vehicle re-identification (ReID) seeks to develop models that can adapt to unknown target domains without the need for additional fine-tuning or retraining. Previous…
SRCD: Semantic Reasoning with Compound Domains for Single-Domain Generalized Object Detection
Zhijie Rao, Jingcai Guo, Luyao Tang +3
This paper provides a novel framework for single-domain generalized object detection (i.e., Single-DGOD), where we are interested in learning and maintaining the semantic structure…
Hint-dynamic Knowledge Distillation
Yiyang Liu, Chenxin Li, Xiaotong Tu +2
Knowledge Distillation (KD) transfers the knowledge from a high-capacity teacher model to promote a smaller student model. Existing efforts guide the distillation by matching their…
Uncertainty Inspired Underwater Image Enhancement
Zhenqi Fu, Wu Wang, Yue Huang +2
A main challenge faced in the deep learning-based Underwater Image Enhancement (UIE) is that the ground truth high-quality image is unavailable. Most of the existing methods first…
Knowledge Condensation Distillation
Chenxin Li, Mingbao Lin, Zhiyuan Ding +5
Knowledge Distillation (KD) transfers the knowledge from a high-capacity teacher network to strengthen a smaller student. Existing methods focus on excavating the knowledge hints a…
Relation Matters: Foreground-aware Graph-based Relational Reasoning for Domain Adaptive Object Detection
Chaoqi Chen, Jiongcheng Li, Hong-Yu Zhou +4
Domain Adaptive Object Detection (DAOD) focuses on improving the generalization ability of object detectors via knowledge transfer. Recent advances in DAOD strive to change the emp…
Domain Generalization on Medical Imaging Classification using Episodic Training with Task Augmentation
Chenxin Li, Qi Qi, Xinghao Ding +3
Medical imaging datasets usually exhibit domain shift due to the variations of scanner vendors, imaging protocols, etc. This raises the concern about the generalization capacity of…
I3Net: Implicit Instance-Invariant Network for Adapting One-Stage Object Detectors
Chaoqi Chen, Zebiao Zheng, Yue Huang +2
Recent works on two-stage cross-domain detection have widely explored the local feature patterns to achieve more accurate adaptation results. These methods heavily rely on the regi…
Consistent Posterior Distributions under Vessel-Mixing: A Regularization for Cross-Domain Retinal Artery/Vein Classification
Chenxin Li, Yunlong Zhang, Zhehan Liang +3
Retinal artery/vein (A/V) classification is a critical technique for diagnosing diabetes and cardiovascular diseases. Although deep learning based methods achieve impressive result…
Underwater Image Enhancement via Learning Water Type Desensitized Representations
Zhenqi Fu, Xiaopeng Lin, Wu Wang +2
We present a novel underwater image enhancement method termed SCNet to improve the image quality meanwhile cope with the degradation diversity caused by the water. SCNet is based o…
Twice Mixing: A Rank Learning based Quality Assessment Approach for Underwater Image Enhancement
Zhenqi Fu, Xueyang Fu, Yue Huang +1
To improve the quality of underwater images, various kinds of underwater image enhancement (UIE) operators have been proposed during the past few years. However, the lack of effect…
Few-shot Medical Image Segmentation using a Global Correlation Network with Discriminative Embedding
Liyan Sun, Chenxin Li, Xinghao Ding +3
Despite deep convolutional neural networks achieved impressive progress in medical image computing and analysis, its paradigm of supervised learning demands a large number of annot…
A Teacher-Student Framework for Semi-supervised Medical Image Segmentation From Mixed Supervision
Liyan Sun, Jianxiong Wu, Xinghao Ding +3
Standard segmentation of medical images based on full-supervised convolutional networks demands accurate dense annotations. Such learning framework is built on laborious manual ann…
Generator Versus Segmentor: Pseudo-healthy Synthesis
Zhang Yunlong, Li Chenxin, Lin Xin +6
This paper investigates the problem of pseudo-healthy synthesis that is defined as synthesizing a subject-specific pathology-free image from a pathological one. Recent approaches b…
Hard Class Rectification for Domain Adaptation
Yunlong Zhang, Changxing Jing, Huangxing Lin +4
Domain adaptation (DA) aims to transfer knowledge from a label-rich and related domain (source domain) to a label-scare domain (target domain). Pseudo-labeling has recently been wi…
Harmonizing Transferability and Discriminability for Adapting Object Detectors
Chaoqi Chen, Zebiao Zheng, Xinghao Ding +2
Recent advances in adaptive object detection have achieved compelling results in virtue of adversarial feature adaptation to mitigate the distributional shifts along the detection…
A Real-time Global Inference Network for One-stage Referring Expression Comprehension
Yiyi Zhou, Rongrong Ji, Gen Luo +5
Referring Expression Comprehension (REC) is an emerging research spot in computer vision, which refers to detecting the target region in an image given an text description. Most ex…
Learning Rate Dropout
Huangxing Lin, Weihong Zeng, Xinghao Ding +3
The performance of a deep neural network is highly dependent on its training, and finding better local optimal solutions is the goal of many optimization algorithms. However, exist…
Uncertainty-Guided Domain Alignment for Layer Segmentation in OCT Images
Jiexiang Wang, Cheng Bian, Meng Li +6
Automatic and accurate segmentation for retinal and choroidal layers of Optical Coherence Tomography (OCT) is crucial for detection of various ocular diseases. However, because of…
Look More Than Once: An Accurate Detector for Text of Arbitrary Shapes
Chengquan Zhang, Borong Liang, Zuming Huang +4
Previous scene text detection methods have progressed substantially over the past years. However, limited by the receptive field of CNNs and the simple representations like rectang…
Rain O'er Me: Synthesizing real rain to derain with data distillation
Huangxing Lin, Yanlong Li, Xinghao Ding +3
We present a supervised technique for learning to remove rain from images without using synthetic rain software. The method is based on a two-stage data distillation approach: 1) A…
A^2Net: Adjacent Aggregation Networks for Image Raindrop Removal
Huangxing Lin, Xueyang Fu, Changxing Jing +2
Existing methods for single images raindrop removal either have poor robustness or suffer from parameter burdens. In this paper, we propose a new Adjacent Aggregation Network (A^2N…
A Deep Tree-Structured Fusion Model for Single Image Deraining
Xueyang Fu, Qi Qi, Yue Huang +3
We propose a simple yet effective deep tree-structured fusion model based on feature aggregation for the deraining problem. We argue that by effectively aggregating features, a rel…
Progressive Feature Alignment for Unsupervised Domain Adaptation
Chaoqi Chen, Weiping Xie, Wenbing Huang +5
Unsupervised domain adaptation (UDA) transfers knowledge from a label-rich source domain to a fully-unlabeled target domain. To tackle this task, recent approaches resort to discri…