6 papers
Dual Prototype-Conditioned Diffusion Model for Scalable Multi-Class Unsupervised Anomaly Detection in Large Category Spaces
Yaoxuan Feng, Yuxin Li, Weijiang Lv +5
Multi-class anomaly detection aims to build unified models across diverse product categories. However, as the number of categories grows, its performance often degrades due to incr…
Semantically Guided Dynamic Visual Prototype Refinement for Compositional Zero-Shot Learning
Zhong Peng, Yishi Xu, Gerong Wang +4
Compositional Zero-Shot Learning (CZSL) seeks to recognize unseen state-object pairs by recombining primitives learned from seen compositions. Despite recent progress with vision-l…
Channel Matters: Estimating Channel Influence for Multivariate Time Series
Muyao Wang, Zeke Xie, Bo Chen +2
The influence function serves as an efficient post-hoc interpretability tool that quantifies the impact of training data modifications on model parameters, enabling enhanced model…
Beyond Matryoshka: Revisiting Sparse Coding for Adaptive Representation
Tiansheng Wen, Yifei Wang, Zequn Zeng +7
Many large-scale systems rely on high-quality deep representations (embeddings) to facilitate tasks like retrieval, search, and generative modeling. Matryoshka Representation Learn…
Discovering Fine-Grained Visual-Concept Relations by Disentangled Optimal Transport Concept Bottleneck Models
Yan Xie, Zequn Zeng, Hao Zhang +5
Concept Bottleneck Models (CBMs) try to make the decision-making process transparent by exploring an intermediate concept space between the input image and the output prediction. E…
Explaining Domain Shifts in Language: Concept erasing for Interpretable Image Classification
Zequn Zeng, Yudi Su, Jianqiao Sun +6
Concept-based models can map black-box representations to human-understandable concepts, which makes the decision-making process more transparent and then allows users to understan…