3 papers
cs.CV2026
PC-Edit: Prompt-Contrastive Region Discovery and Region-Guided Editing
Jian Zhang, Zhijun Zhang
Replacing an object with one that differs in category or shape requires complete source removal, natural target formation unconstrained by the source silhouette, and preservation o…
cs.CV2026
AnchorDiff: Training-Free Concept Grounding for MM-DiTs via Anchor-Based Graph Propagation
Jian Zhang, Zhijun Zhang
Multi-Modal Diffusion Transformers (MM-DiTs) encode rich representations for training-free concept grounding, but existing attention-based methods often produce overlapping activat…
cs.CV2025
Ambiguity-Guided Learnable Distribution Calibration for Semi-Supervised Few-Shot Class-Incremental Learning
Fan Lyu, Linglan Zhao, Chengyan Liu +5
Few-Shot Class-Incremental Learning (FSCIL) focuses on models learning new concepts from limited data while retaining knowledge of previous classes. Recently, many studies have sta…