Explaining CLIP Zero-shot Predictions Through Concepts

• URL: http://arxiv.org/abs/2603.28211v1
• Date: Mon, 30 Mar 2026 09:31:33 GMT
• Title: Explaining CLIP Zero-shot Predictions Through Concepts
• Abstract summary: We introduce EZPC to explain CLIP's zero-shot predictions through human-understandable concepts.<n>Our method projects CLIP's joint image-text embeddings into a concept space learned from language descriptions.<n>Our approach maintains CLIP's strong zero-shot classification accuracy while providing meaningful concept-level explanations.
• Score: 54.05282304471016
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: Large-scale vision-language models such as CLIP have achieved remarkable success in zero-shot image recognition, yet their predictions remain largely opaque to human understanding. In contrast, Concept Bottleneck Models provide interpretable intermediate representations by reasoning through human-defined concepts, but they rely on concept supervision and lack the ability to generalize to unseen classes. We introduce EZPC that bridges these two paradigms by explaining CLIP's zero-shot predictions through human-understandable concepts. Our method projects CLIP's joint image-text embeddings into a concept space learned from language descriptions, enabling faithful and transparent explanations without additional supervision. The model learns this projection via a combination of alignment and reconstruction objectives, ensuring that concept activations preserve CLIP's semantic structure while remaining interpretable. Extensive experiments on five benchmark datasets, CIFAR-100, CUB-200-2011, Places365, ImageNet-100, and ImageNet-1k, demonstrate that our approach maintains CLIP's strong zero-shot classification accuracy while providing meaningful concept-level explanations. By grounding open-vocabulary predictions in explicit semantic concepts, our method offers a principled step toward interpretable and trustworthy vision-language models. Code is available at https://github.com/oonat/ezpc.

Related papers

• Beyond Heuristic Prompting: A Concept-Guided Bayesian Framework for Zero-Shot Image Recognition [81.2779530670268]
  Vision-Language Models (VLMs) have significantly advanced zero-shot image recognition.<n>This paper enhances prompt by incorporating class-specific concepts.<n>Our method consistently outperforms state-of-the-art approaches.
  arXiv  Detail & Related papers  (2026-03-09T03:11:11Z)
• Insight: Interpretable Semantic Hierarchies in Vision-Language Encoders [52.94006363830628]
  Language-aligned vision foundation models perform strongly across diverse downstream tasks.<n>Recent works decompose these representations into human-interpretable concepts, but provide poor spatial grounding and are limited to image classification tasks.<n>We propose Insight, a language-aligned concept foundation model that provides fine-grained concepts, which are human-interpretable and spatially grounded in the input image.
  arXiv  Detail & Related papers  (2026-01-20T09:57:26Z)
• FaCT: Faithful Concept Traces for Explaining Neural Network Decisions [56.796533084868884]
  Deep networks have shown remarkable performance across a wide range of tasks, yet getting a global concept-level understanding of how they function remains a key challenge.<n>We put emphasis on the faithfulness of concept-based explanations and propose a new model with model-inherent mechanistic concept-explanations.<n>Our concepts are shared across classes and, from any layer, their contribution to the logit and their input-visualization can be faithfully traced.
  arXiv  Detail & Related papers  (2025-10-29T13:35:46Z)
• Enhancing Concept Localization in CLIP-based Concept Bottleneck Models [11.592826680892367]
  We show that Concept Bottleneck Models (CBMs) do not require explicit concept annotations, relying instead on concepts extracted using CLIP in a zero-shot manner.<n>We introduce Concept Hallucination Inhibition via Localized Interpretability (CHILI), a technique that disentangles image embeddings and localizes pixels corresponding to target concepts.
  arXiv  Detail & Related papers  (2025-10-08T15:07:16Z)
• Interpreting and Analysing CLIP's Zero-Shot Image Classification via Mutual Knowledge [20.09852220432504]
  Contrastive Language-Image Pretraining (CLIP) performs zero-shot image classification by mapping images and textual class representation into a shared embedding space.<n>This work provides a new approach for interpreting CLIP models for image classification from the lens of mutual knowledge between the two modalities.
  arXiv  Detail & Related papers  (2024-10-16T20:18:21Z)
• Explain via Any Concept: Concept Bottleneck Model with Open Vocabulary Concepts [8.028021897214238]
  "OpenCBM" is the first CBM with concepts of open vocabularies. Our model significantly outperforms the previous state-of-the-art CBM by 9% in the classification accuracy on the benchmark dataset CUB-200-2011.
  arXiv  Detail & Related papers  (2024-08-05T06:42:00Z)
• CEIR: Concept-based Explainable Image Representation Learning [0.4198865250277024]
  We introduce Concept-based Explainable Image Representation (CEIR) to derive high-quality representations without label dependency. Our method exhibits state-of-the-art unsupervised clustering performance on benchmarks such as CIFAR10, CIFAR100, and STL10. CEIR can seamlessly extract the related concept from open-world images without fine-tuning.
  arXiv  Detail & Related papers  (2023-12-17T15:37:41Z)
• Rewrite Caption Semantics: Bridging Semantic Gaps for Language-Supervised Semantic Segmentation [100.81837601210597]
  We propose Concept Curation (CoCu) to bridge the gap between visual and textual semantics in pre-training data. CoCu achieves superb zero-shot transfer performance and greatly boosts language-supervised segmentation baseline by a large margin.
  arXiv  Detail & Related papers  (2023-09-24T00:05:39Z)
• Concept Gradient: Concept-based Interpretation Without Linear Assumption [77.96338722483226]
  Concept Activation Vector (CAV) relies on learning a linear relation between some latent representation of a given model and concepts. We proposed Concept Gradient (CG), extending concept-based interpretation beyond linear concept functions. We demonstrated CG outperforms CAV in both toy examples and real world datasets.
  arXiv  Detail & Related papers  (2022-08-31T17:06:46Z)
• GlanceNets: Interpretabile, Leak-proof Concept-based Models [23.7625973884849]
  Concept-based models (CBMs) combine high-performance and interpretability by acquiring and reasoning with a vocabulary of high-level concepts. We provide a clear definition of interpretability in terms of alignment between the model's representation and an underlying data generation process. We introduce GlanceNets, a new CBM that exploits techniques from disentangled representation learning and open-set recognition to achieve alignment.
  arXiv  Detail & Related papers  (2022-05-31T08:53:53Z)

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.