6 papers
Step-wise Distribution Alignment Guided Style Prompt Tuning for Source-free Cross-domain Few-shot Learning
Huali Xu, Li Liu, Tianpeng Liu +3
Existing cross-domain few-shot learning (CDFSL) methods, which develop source-domain training strategies to enhance model transferability, face challenges with large-scale pre-trai…
Object-level Correlation for Few-Shot Segmentation
Chunlin Wen, Yu Zhang, Jie Fan +5
Few-shot semantic segmentation (FSS) aims to segment objects of novel categories in the query images given only a few annotated support samples. Existing methods primarily build th…
A Reverse Causal Framework to Mitigate Spurious Correlations for Debiasing Scene Graph Generation
Shuzhou Sun, Li Liu, Tianpeng Liu +4
Existing two-stage Scene Graph Generation (SGG) frameworks typically incorporate a detector to extract relationship features and a classifier to categorize these relationships; the…
A Causal Adjustment Module for Debiasing Scene Graph Generation
Li Liu, Shuzhou Sun, Shuaifeng Zhi +4
While recent debiasing methods for Scene Graph Generation (SGG) have shown impressive performance, these efforts often attribute model bias solely to the long-tail distribution of…
Deep Learning for Cross-Domain Few-Shot Visual Recognition: A Survey
Huali Xu, Shuaifeng Zhi, Shuzhou Sun +2
While deep learning excels in computer vision tasks with abundant labeled data, its performance diminishes significantly in scenarios with limited labeled samples. To address this,…
Uncovering Bias in Foundation Models: Impact, Testing, Harm, and Mitigation
Shuzhou Sun, Li Liu, Yongxiang Liu +4
Bias in Foundation Models (FMs) - trained on vast datasets spanning societal and historical knowledge - poses significant challenges for fairness and equity across fields such as h…