3 papers
cs.CV2026
Learnable Shape Prototypes with Occlusion-Geometry-Guided Injection for Amodal Instance Segmentation
Fufan Zhang, Jingxiang Wang, Xiangjie Ye
Amodal instance segmentation aims to predict the complete object mask including occluded regions that lack pixel-level observations and must be inferred with the aid of shape prior…
cs.LG2026
Cumulative Meta-Learning from Active Learning Queries for Robustness to Spurious Correlations
Kin Whye Chew, Jingxian Wang
Spurious correlations in real-world datasets cause machine learning models to rely on irrelevant patterns, undermining reliability, generalization, and fairness. Active learning of…
cs.CV2026
Deep Attention Reweighting: Post-Hoc Attention-Based Feature Aggregation in CNNs for Disentangling Core and Spurious Features under Spurious Correlations
Kin Whye Chew, Jingxian Wang
Convolutional Neural Networks (CNNs) often exploit spurious correlations in datasets, learning superficially predictive yet causally irrelevant features, leading to poor generaliza…