Mitigating Spurious Background Bias in Multimedia Recognition with Disentangled Concept Bottlenecks
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.
Code (0)
등록된 구현이 없습니다.
Similar Papers 제목 키워드 기반
SAGE: Spuriousness-Aware Guided Prompt Exploration for Mitigating Multimodal Bias
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
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 RecognitionAGCD-Net: Attention Guided Context Debiasing Network for Emotion Recognition
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 RecognitionMitigating Spurious Correlations with Causal Logit Perturbation
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-LearningLet Samples Speak: Mitigating Spurious Correlation by Exploiting the Clusterness of Samples
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…