output
20072025
most citedDeep Subdomain Adaptation Network for Image Classification

1.2k citations

Showing 2022Show all

22 papers · 1 filter

eess.IV202283 cited

LE-UDA: Label-efficient unsupervised domain adaptation for medical image segmentation

Ziyuan Zhao, Fangcheng Zhou, Kaixin Xu +3

While deep learning methods hitherto have achieved considerable success in medical image segmentation, they are still hampered by two limitations: (i) reliance on large-scale well-…

cs.CV2022220 cited

CIR-Net: Cross-modality Interaction and Refinement for RGB-D Salient Object Detection

Runmin Cong, Qinwei Lin, Chen Zhang +4

Focusing on the issue of how to effectively capture and utilize cross-modality information in RGB-D salient object detection (SOD) task, we present a convolutional neural network (…

cs.LG202234 cited

MaxMatch: Semi-Supervised Learning with Worst-Case Consistency

Yangbangyan Jiang, Xiaodan Li, Yuefeng Chen +5

In recent years, great progress has been made to incorporate unlabeled data to overcome the inefficiently supervised problem via semi-supervised learning (SSL). Most state-of-the-a…

cs.CV202213 cited

Self-supervised Image Clustering from Multiple Incomplete Views via Constrastive Complementary Generation

Jiatai Wang, Zhiwei Xu, Xuewen Yang +2

Incomplete Multi-View Clustering aims to enhance clustering performance by using data from multiple modalities. Despite the fact that several approaches for studying this issue hav…

cs.LG202212 cited

A Tale of HodgeRank and Spectral Method: Target Attack Against Rank Aggregation Is the Fixed Point of Adversarial Game

Ke Ma, Qianqian Xu, Jinshan Zeng +3

Rank aggregation with pairwise comparisons has shown promising results in elections, sports competitions, recommendations, and information retrieval. However, little attention has…

eess.IV202223 cited

Cross Modal Compression: Towards Human-comprehensible Semantic Compression

Jiguo Li, Chuanmin Jia, Xinfeng Zhang +2

Traditional image/video compression aims to reduce the transmission/storage cost with signal fidelity as high as possible. However, with the increasing demand for machine analysis…