3.5k citations · 16k across the 85 of their papers we have counts for
85 papers
DFormer: Rethinking RGBD Representation Learning for Semantic Segmentation
Bowen Yin, Xuying Zhang, Zhongyu Li +3
We present DFormer, a novel RGB-D pretraining framework to learn transferable representations for RGB-D segmentation tasks. DFormer has two new key innovations: 1) Unlike previous…
Revisiting Computer-Aided Tuberculosis Diagnosis
Yun Liu, Yu-Huan Wu, Shi-Chen Zhang +3
Tuberculosis (TB) is a major global health threat, causing millions of deaths annually. Although early diagnosis and treatment can greatly improve the chances of survival, it remai…
CrossKD: Cross-Head Knowledge Distillation for Object Detection
Jiabao Wang, Yuming Chen, Zhaohui Zheng +3
Knowledge Distillation (KD) has been validated as an effective model compression technique for learning compact object detectors. Existing state-of-the-art KD methods for object de…
Referring Camouflaged Object Detection
Xuying Zhang, Bowen Yin, Zheng Lin +3
We consider the problem of referring camouflaged object detection (Ref-COD), a new task that aims to segment specified camouflaged objects based on a small set of referring images…
CorrMatch: Label Propagation via Correlation Matching for Semi-Supervised Semantic Segmentation
Boyuan Sun, Yuqi Yang, Le Zhang +2
This paper presents a simple but performant semi-supervised semantic segmentation approach, called CorrMatch. Previous approaches mostly employ complicated training strategies to l…
SAM Struggles in Concealed Scenes -- Empirical Study on Segment Anything
Ge-Peng Ji, Deng-Ping Fan, Peng Xu +3
Segmenting anything is a ground-breaking step toward artificial general intelligence, and the Segment Anything Model (SAM) greatly fosters the foundation models for computer vision…