Debiasing CLIP: Interpreting and Correcting Bias in Attention Heads

• URL: http://arxiv.org/abs/2505.17425v1
• Date: Fri, 23 May 2025 03:13:42 GMT
• Title: Debiasing CLIP: Interpreting and Correcting Bias in Attention Heads
• Authors: Wei Jie Yeo, Rui Mao, Moloud Abdar, Erik Cambria, Ranjan Satapathy,
• Abstract summary: We introduce textsc-Then-Correct (LTC), a contrastive framework that identifies spurious attention heads and mitigates them through targeted ablation.<n>We evaluate LTC on benchmarks with inherent background gender biases, achieving over a $>50%$ gain in worst-group accuracy compared to non-training post-hoc baselines.<n>We visualize the representation of selected heads and find that the presented interpretation corroborates our contrastive mechanism for identifying both spurious and salient attention heads.
• Score: 29.880490526874876
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: Multimodal models like CLIP have gained significant attention due to their remarkable zero-shot performance across various tasks. However, studies have revealed that CLIP can inadvertently learn spurious associations between target variables and confounding factors. To address this, we introduce \textsc{Locate-Then-Correct} (LTC), a contrastive framework that identifies spurious attention heads in Vision Transformers via mechanistic insights and mitigates them through targeted ablation. Furthermore, LTC identifies salient, task-relevant attention heads, enabling the integration of discriminative features through orthogonal projection to improve classification performance. We evaluate LTC on benchmarks with inherent background and gender biases, achieving over a $>50\%$ gain in worst-group accuracy compared to non-training post-hoc baselines. Additionally, we visualize the representation of selected heads and find that the presented interpretation corroborates our contrastive mechanism for identifying both spurious and salient attention heads. Code available at https://github.com/wj210/CLIP_LTC.

Related papers

• Self-Classification Enhancement and Correction for Weakly Supervised Object Detection [113.51483527300496]
  weakly supervised object detection (WSOD) has attracted much attention due to its low labeling cost.<n>In this work, we introduce a novel WSOD framework to ameliorate these two issues.<n>For one thing, we propose a self-classification enhancement module that integrates intra-class binary classification (ICBC) to bridge the gap between the two distinct MCC tasks.<n>For another, we propose a self-classification correction algorithm during inference, which combines the results of both MCC tasks to effectively reduce the mis-classified predictions.
  arXiv  Detail & Related papers  (2025-05-22T06:45:58Z)
• Classifier-guided CLIP Distillation for Unsupervised Multi-label Classification [16.0058187276343]
  Multi-label classification is crucial for comprehensive image understanding.<n>Despite CLIP's proficiency, it suffers from view-dependent predictions and inherent bias, limiting its effectiveness.<n>We propose a novel method that addresses these issues by leveraging multiple views near target objects.
  arXiv  Detail & Related papers  (2025-03-21T06:12:14Z)
• Quantifying Interpretability in CLIP Models with Concept Consistency [5.921976812527759]
  We study conceptual consistency of text descriptions for attention heads in CLIP-like models.<n>We propose Concept Consistency Score (CCS), a novel interpretability metric.<n>We find that high CCS heads capture essential concepts and play a key role in out-of-domain detection, concept-specific reasoning, and video-language understanding.
  arXiv  Detail & Related papers  (2025-03-14T05:47:17Z)
• Self-Calibrated CLIP for Training-Free Open-Vocabulary Segmentation [19.749490092520006]
  Self-Calibrated CLIP (SC-CLIP) is a training-free method that calibrates CLIP to produce finer representations.<n>SC-CLIP boosts the performance of vanilla CLIP ViT-L/14 by 6.8 times.
  arXiv  Detail & Related papers  (2024-11-24T15:14:05Z)
• Rethinking Misalignment in Vision-Language Model Adaptation from a Causal Perspective [13.56923651751788]
  We propose Causality-Guided Semantic Decoupling and Classification to mitigate the interference of task-irrelevant knowledge. We employ the Dempster-Shafer evidence theory to evaluate the uncertainty of each prediction generated by diverse semantics.
  arXiv  Detail & Related papers  (2024-10-01T09:33:45Z)
• ClearCLIP: Decomposing CLIP Representations for Dense Vision-Language Inference [32.852004564832455]
  We re-investigate the architecture of CLIP, and identify residual connections as the primary source of noise that degrades segmentation quality. We propose ClearCLIP, a novel approach that decomposes CLIP's representations to enhance open-vocabulary semantic segmentation.
  arXiv  Detail & Related papers  (2024-07-17T09:52:20Z)
• Enhancing Few-shot CLIP with Semantic-Aware Fine-Tuning [61.902254546858465]
  Methods based on Contrastive Language-Image Pre-training have exhibited promising performance in few-shot adaptation tasks. We propose fine-tuning the parameters of the attention pooling layer during the training process to encourage the model to focus on task-specific semantics.
  arXiv  Detail & Related papers  (2023-11-08T05:18:57Z)
• Gramian Attention Heads are Strong yet Efficient Vision Learners [26.79263390835444]
  We introduce a novel architecture design that enhances expressiveness by incorporating multiple head classifiers (ie, classification heads) Our approach employs attention-based aggregation, utilizing pairwise feature similarity to enhance multiple lightweight heads with minimal resource overhead. Our models eventually surpass state-of-the-art CNNs and ViTs regarding the accuracy-grained trade-off on ImageNet-1K.
  arXiv  Detail & Related papers  (2023-10-25T09:08:58Z)
• Learning Common Rationale to Improve Self-Supervised Representation for Fine-Grained Visual Recognition Problems [61.11799513362704]
  We propose learning an additional screening mechanism to identify discriminative clues commonly seen across instances and classes. We show that a common rationale detector can be learned by simply exploiting the GradCAM induced from the SSL objective.
  arXiv  Detail & Related papers  (2023-03-03T02:07:40Z)
• Non-Contrastive Learning Meets Language-Image Pre-Training [145.6671909437841]
  We study the validity of non-contrastive language-image pre-training (nCLIP) We introduce xCLIP, a multi-tasking framework combining CLIP and nCLIP, and show that nCLIP aids CLIP in enhancing feature semantics.
  arXiv  Detail & Related papers  (2022-10-17T17:57:46Z)
• Using Representation Expressiveness and Learnability to Evaluate Self-Supervised Learning Methods [61.49061000562676]
  We introduce Cluster Learnability (CL) to assess learnability. CL is measured in terms of the performance of a KNN trained to predict labels obtained by clustering the representations with K-means. We find that CL better correlates with in-distribution model performance than other competing recent evaluation schemes.
  arXiv  Detail & Related papers  (2022-06-02T19:05:13Z)
• Dual Contrastive Learning for General Face Forgery Detection [64.41970626226221]
  We propose a novel face forgery detection framework, named Dual Contrastive Learning (DCL), which constructs positive and negative paired data. To explore the essential discrepancies, Intra-Instance Contrastive Learning (Intra-ICL) is introduced to focus on the local content inconsistencies prevalent in the forged faces.
  arXiv  Detail & Related papers  (2021-12-27T05:44:40Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.