activity
20162023
most citedTowards Robustness Against Natural Language Word Substitutions

64 citations · 99 across the 9 of their papers we have counts for

collaborators

14 papers

cs.CV2023

STAR Loss: Reducing Semantic Ambiguity in Facial Landmark Detection

Zhenglin Zhou, Huaxia Li, Hong Liu +3

Recently, deep learning-based facial landmark detection has achieved significant improvement. However, the semantic ambiguity problem degrades detection performance. Specifically,…

cs.CV2022

Self-distillation with Online Diffusion on Batch Manifolds Improves Deep Metric Learning

Zelong Zeng, Fan Yang, Hong Liu +1

Recent deep metric learning (DML) methods typically leverage solely class labels to keep positive samples far away from negative ones. However, this type of method normally ignores…

cs.CV20221 cited

Identity-Sensitive Knowledge Propagation for Cloth-Changing Person Re-identification

Jianbing Wu, Hong Liu, Wei Shi +2

Cloth-changing person re-identification (CC-ReID), which aims to match person identities under clothing changes, is a new rising research topic in recent years. However, typical bi…

cs.CV202123 cited

Improving Camouflaged Object Detection with the Uncertainty of Pseudo-edge Labels

Nobukatsu Kajiura, Hong Liu, Shin'ichi Satoh

This paper focuses on camouflaged object detection (COD), which is a task to detect objects hidden in the background. Most of the current COD models aim to highlight the target obj…

cs.CL202164 cited

Towards Robustness Against Natural Language Word Substitutions

Xinshuai Dong, Anh Tuan Luu, Rongrong Ji +1

Robustness against word substitutions has a well-defined and widely acceptable form, i.e., using semantically similar words as substitutions, and thus it is considered as a fundame…

cs.CV20202 cited

Anti-Bandit Neural Architecture Search for Model Defense

Hanlin Chen, Baochang Zhang, Song Xue +4

Deep convolutional neural networks (DCNNs) have dominated as the best performers in machine learning, but can be challenged by adversarial attacks. In this paper, we defend against…