activity
20182023
most citedSATS: Self-Attention Transfer for Continual Semantic Segmentation

49 citations · 57 across the 9 of their papers we have counts for

collaborators

10 papers

cs.CV2023

Classifier-head Informed Feature Masking and Prototype-based Logit Smoothing for Out-of-Distribution Detection

Zhuohao Sun, Yiqiao Qiu, Zhijun Tan +2

Out-of-distribution (OOD) detection is essential when deploying neural networks in the real world. One main challenge is that neural networks often make overconfident predictions o…

cs.CV2023★ 1 cited

Adapter Learning in Pretrained Feature Extractor for Continual Learning of Diseases

Wentao Zhang, Yujun Huang, Tong Zhang +3

Currently intelligent diagnosis systems lack the ability of continually learning to diagnose new diseases once deployed, under the condition of preserving old disease knowledge. In…

cs.CV2023★ 1 cited

PAMI: partition input and aggregate outputs for model interpretation

Wei Shi, Wentao Zhang, Weishi Zheng +1

There is an increasing demand for interpretation of model predictions especially in high-risk applications. Various visualization approaches have been proposed to estimate the part…

cs.CV2023

Adaptively Integrated Knowledge Distillation and Prediction Uncertainty for Continual Learning

Kanghao Chen, Sijia Liu, Ruixuan Wang +1

Current deep learning models often suffer from catastrophic forgetting of old knowledge when continually learning new knowledge. Existing strategies to alleviate this issue often f…

cs.CV2022★ 2 cited

Learning Discriminative Representation via Metric Learning for Imbalanced Medical Image Classification

Chenghua Zeng, Huijuan Lu, Kanghao Chen +2

Data imbalance between common and rare diseases during model training often causes intelligent diagnosis systems to have biased predictions towards common diseases. The state-of-th…

cs.CV2022★ 1 cited

PCCT: Progressive Class-Center Triplet Loss for Imbalanced Medical Image Classification

Kanghao Chen, Weixian Lei, Rong Zhang +3

Imbalanced training data is a significant challenge for medical image classification. In this study, we propose a novel Progressive Class-Center Triplet (PCCT) framework to allevia…