676 citations · 688 across the 6 of their papers we have counts for
6 papers
RePO-VLA: Recovery-Driven Policy Optimization for Vision-Language-Action Models
Weijia Liufu, Xiaoyu Guo, Ruiyi Chen +16
Vision-Language-Action (VLA) models remain brittle in long-horizon, contact-rich manipulation because success-only imitation provides little supervision for execution drift, while…
Enhancing Prototypical Few-Shot Learning by Leveraging the Local-Level Strategy
Junying Huang, Fan Chen, Keze Wang +2
Aiming at recognizing the samples from novel categories with few reference samples, few-shot learning (FSL) is a challenging problem. We found that the existing works often build t…
Instant Response Few-shot Object Detection with Meta Strategy and Explicit Localization Inference
Junying Huang, Fan Chen, Sibo Huang +1
Aiming at recognizing and localizing the object of novel categories by a few reference samples, few-shot object detection (FSOD) is a quite challenging task. Previous works often d…
Transferable, Controllable, and Inconspicuous Adversarial Attacks on Person Re-identification With Deep Mis-Ranking
Hongjun Wang, Guangrun Wang, Ya Li +2
The success of DNNs has driven the extensive applications of person re-identification (ReID) into a new era. However, whether ReID inherits the vulnerability of DNNs remains unexpl…
Cost-effective Object Detection: Active Sample Mining with Switchable Selection Criteria
Keze Wang, Liang Lin, Xiaopeng Yan +3
Though quite challenging, leveraging large-scale unlabeled or partially labeled data in learning systems (e.g., model/classifier training) has attracted increasing attentions due t…
Cost-Effective Active Learning for Deep Image Classification
Keze Wang, Dongyu Zhang, Ya Li +2
Recent successes in learning-based image classification, however, heavily rely on the large number of annotated training samples, which may require considerable human efforts. In t…