paper-with-me

홈 › Papers

Mitigating Spurious Background Bias in Multimedia Recognition with Disentangled Concept Bottlenecks

2025-10-17 · Gaoxiang Huang, Songning Lai, Yutao Yue arxiv

Concept Bottleneck Models (CBMs) enhance interpretability by predicting human-understandable concepts as intermediate representations. However, existing CBMs often suffer from input-to-concept mapping bias and limited controllability, which restricts their practical utility and undermines the reliability of concept-based strategies. To address these challenges, we propose a Lightweight Disentangled Concept Bottleneck Model (LDCBM) that automatically groups visual features into semantically meaningful components without the need for region annotations. By introducing a filter grouping loss and joint concept supervision, our method improves the alignment between visual patterns and concepts, enabling more transparent and robust decision-making. Notably, experiments on three diverse datasets demonstrate that LDCBM achieves higher concept and class accuracy, outperforming previous CBMs in both interpretability and classification performance. Complexity analysis reveals that the parameter count and FLOPs of LDCBM are less than 5% higher than those of Vanilla CBM. Furthermore, background mask intervention experiments validate the model's strong capability to suppress irrelevant image regions, further corroborating the high precision of the visual-concept mapping under LDCBM's lightweight design paradigm. By grounding concepts in visual evidence, our method overcomes a fundamental limitation of prior models and enhances the reliability of interpretable AI.

📄 PDF Abstract BibTeX arXiv:2510.15770

Code (0)

등록된 구현이 없습니다.

Similar Papers 제목 키워드 기반

SAGE: Spuriousness-Aware Guided Prompt Exploration for Mitigating Multimodal Bias

2025-11-17 · Wenqian Ye, Di Wang, Guangtao Zheng, Bohan Liu 외 arxiv

Large vision-language models, such as CLIP, have shown strong zero-shot classification performance by aligning images and text in a shared embedding space. However, CLIP models often develop multimodal spurious biases, w…

Seeing Beyond the Scene: Analyzing and Mitigating Background Bias in Action Recognition

2025-12-17 · Ellie Zhou, Jihoon Chung, Olga Russakovsky arxiv

Human action recognition models often rely on background cues rather than human movement and pose to make predictions, a behavior known as background bias. We present a systematic analysis of background bias across class…

Action Recognition

AGCD-Net: Attention Guided Context Debiasing Network for Emotion Recognition

2025-07-12 · Varsha Devi, Amine Bohi, Pardeep Kumar arxiv

Context-aware emotion recognition (CAER) enhances affective computing in real-world scenarios, but traditional methods often suffer from context bias-spurious correlation between background context and emotion labels (e.…

Emotion Recognition

Mitigating Spurious Correlations with Causal Logit Perturbation

2025-05-21 · Xiaoling Zhou, Wei Ye, Rui Xie, Shikun Zhang

Deep learning has seen widespread success in various domains such as science, industry, and society. However, it is acknowledged that certain approaches suffer from non-robustness, relying on spurious correlations for pr…

counterfactualLong-tail LearningMeta-Learning

Let Samples Speak: Mitigating Spurious Correlation by Exploiting the Clusterness of Samples

2025-12-28 · Weiwei Li, Junzhuo Liu, Yuanyuan Ren, Yuchen Zheng 외 arxiv

Deep learning models are known to often learn features that spuriously correlate with the class label during training but are irrelevant to the prediction task. Existing methods typically address this issue by annotating…