Dissecting CLIP: Decomposition with a Schur Complement-based Approach

• URL: http://arxiv.org/abs/2412.18645v2
• Date: Tue, 25 Mar 2025 09:52:53 GMT
• Title: Dissecting CLIP: Decomposition with a Schur Complement-based Approach
• Abstract summary: We extend the application of CLIP embeddings to quantify and interpret the intrinsic diversity of text-to-image models.<n>We demonstrate the use of the Schur complement-based decomposition to nullify the influence of a given prompt in the CLIP embedding of an image.
• Score: 8.056359341994941
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: The use of CLIP embeddings to assess the alignment of samples produced by text-to-image generative models has been extensively explored in the literature. While the widely adopted CLIPScore, derived from the cosine similarity of text and image embeddings, effectively measures the relevance of a generated image, it does not quantify the diversity of images generated by a text-to-image model. In this work, we extend the application of CLIP embeddings to quantify and interpret the intrinsic diversity of text-to-image models, which is responsible for generating diverse images from similar text prompts. To achieve this, we propose a decomposition of the CLIP-based kernel covariance matrix of image data into text-based and non-text-based components. Using the Schur complement of the joint image-text kernel covariance matrix, we perform this decomposition and define the matrix-based entropy of the decomposed component as the \textit{Schur Complement Entropy (SCE)} score, a measure of the intrinsic diversity of a text-to-image model based on data collected with varying text prompts. Additionally, we demonstrate the use of the Schur complement-based decomposition to nullify the influence of a given prompt in the CLIP embedding of an image, enabling focus or defocus of embeddings on specific objects or properties for downstream tasks. We present several numerical results that apply our Schur complement-based approach to evaluate text-to-image models and modify CLIP image embeddings. The codebase is available at https://github.com/aziksh-ospanov/CLIP-DISSECTION

Related papers

• DiCE-CIR: Direct Composition Learning for Efficient Zero-Shot Composed Image Retrieval [52.15696141238419]
  Zero-shot composed image retrieval (ZS-CIR) aims to retrieve a target image from a multimodal query consisting of a reference image and an edit text.<n>We propose DiCE-CIR, a direct composition learning method that predicts composed query representations by directly composing a reference image and an edit text.
  arXiv  Detail & Related papers  (2026-07-06T04:37:30Z)
• Cross-Modal Prototype Alignment and Mixing for Training-Free Few-Shot Classification [52.48204114948899]
  We investigate the impact of directly mixing image and text prototypes for few-shot classification.<n>We show that mixing prototypes acts like a shrinkage estimator.<n>We propose projecting image prototypes onto the principal directions of the semantic text embedding space to obtain a text-aligned semantic image subspace.
  arXiv  Detail & Related papers  (2026-03-25T17:04:43Z)
• TripletCLIP: Improving Compositional Reasoning of CLIP via Synthetic Vision-Language Negatives [65.82577305915643]
  Contrastive Language-Image Pretraining (CLIP) models maximize the mutual information between text and visual modalities to learn representations. We show that generating hard'' negative captions via in-context learning and corresponding negative images with text-to-image generators offers a solution. We demonstrate that our method, named TripletCLIP, enhances the compositional capabilities of CLIP, resulting in an absolute improvement of over 9% on the SugarCrepe benchmark.
  arXiv  Detail & Related papers  (2024-11-04T19:24:59Z)
• Finetuning CLIP to Reason about Pairwise Differences [52.028073305958074]
  We propose an approach to train vision-language models such as CLIP in a contrastive manner to reason about differences in embedding space. We first demonstrate that our approach yields significantly improved capabilities in ranking images by a certain attribute. We also illustrate that the resulting embeddings obey a larger degree of geometric properties in embedding space.
  arXiv  Detail & Related papers  (2024-09-15T13:02:14Z)
• Optimizing CLIP Models for Image Retrieval with Maintained Joint-Embedding Alignment [0.7499722271664144]
  Contrastive Language and Image Pairing (CLIP) is a transformative method in multimedia retrieval. CLIP typically trains two neural networks concurrently to generate joint embeddings for text and image pairs. This paper addresses the challenge of optimizing CLIP models for various image-based similarity search scenarios.
  arXiv  Detail & Related papers  (2024-09-03T14:33:01Z)
• Improving Compositional Attribute Binding in Text-to-Image Generative Models via Enhanced Text Embeddings [46.723653095494896]
  We investigate compositional attribute binding failures in text-to-image generative models. We show that imperfect text conditioning with CLIP text-encoder is one of the primary reasons behind the inability of these models to generate high-fidelity compositional scenes. Our main finding shows that significant compositional improvements can be achieved without harming the model's FID score.
  arXiv  Detail & Related papers  (2024-06-12T03:21:34Z)
• Leveraging Cross-Modal Neighbor Representation for Improved CLIP Classification [54.96876797812238]
  We present a novel CrOss-moDal nEighbor Representation(CODER) based on the distance structure between images and their neighbor texts. The key to construct a high-quality CODER lies in how to create a vast amount of high-quality and diverse texts to match with images. Experiment results across various datasets and models confirm CODER's effectiveness.
  arXiv  Detail & Related papers  (2024-04-27T02:04:36Z)
• Text Augmented Spatial-aware Zero-shot Referring Image Segmentation [60.84423786769453]
  We introduce a Text Augmented Spatial-aware (TAS) zero-shot referring image segmentation framework. TAS incorporates a mask proposal network for instance-level mask extraction, a text-augmented visual-text matching score for mining the image-text correlation, and a spatial for mask post-processing. The proposed method clearly outperforms state-of-the-art zero-shot referring image segmentation methods.
  arXiv  Detail & Related papers  (2023-10-27T10:52:50Z)
• Interpreting CLIP's Image Representation via Text-Based Decomposition [73.54377859089801]
  We investigate the CLIP image encoder by analyzing how individual model components affect the final representation. We decompose the image representation as a sum across individual image patches, model layers, and attention heads. We use this understanding to remove spurious features from CLIP and to create a strong zero-shot image segmenter.
  arXiv  Detail & Related papers  (2023-10-09T17:59:04Z)
• Describing Sets of Images with Textual-PCA [89.46499914148993]
  We seek to semantically describe a set of images, capturing both the attributes of single images and the variations within the set. Our procedure is analogous to Principle Component Analysis, in which the role of projection vectors is replaced with generated phrases.
  arXiv  Detail & Related papers  (2022-10-21T17:10:49Z)
• Hierarchical Text-Conditional Image Generation with CLIP Latents [20.476720970770128]
  We show that explicitly generating image representations improves image diversity with minimal loss in photorealism and caption similarity. Our decoders conditioned on image representations can also produce variations of an image that preserve both its semantics and style.
  arXiv  Detail & Related papers  (2022-04-13T01:10:33Z)
• No Token Left Behind: Explainability-Aided Image Classification and Generation [79.4957965474334]
  We present a novel explainability-based approach, which adds a loss term to ensure that CLIP focuses on all relevant semantic parts of the input. Our method yields an improvement in the recognition rate, without additional training or fine-tuning.
  arXiv  Detail & Related papers  (2022-04-11T07:16:39Z)
• Compositional Sketch Search [91.84489055347585]
  We present an algorithm for searching image collections using free-hand sketches. We exploit drawings as a concise and intuitive representation for specifying entire scene compositions.
  arXiv  Detail & Related papers  (2021-06-15T09:38:09Z)
• Image Captioning with Compositional Neural Module Networks [18.27510863075184]
  We introduce a hierarchical framework for image captioning that explores both compositionality and sequentiality of natural language. Our algorithm learns to compose a detail-rich sentence by selectively attending to different modules corresponding to unique aspects of each object detected in an input image.
  arXiv  Detail & Related papers  (2020-07-10T20:58:04Z)

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.