Compositional Image-Text Matching and Retrieval by Grounding Entities

• URL: http://arxiv.org/abs/2505.02278v1
• Date: Sun, 04 May 2025 22:18:14 GMT
• Title: Compositional Image-Text Matching and Retrieval by Grounding Entities
• Authors: Madhukar Reddy Vongala, Saurabh Srivastava, Jana Košecká,
• Abstract summary: We propose a novel learning-free zero-shot augmentation of CLIP embeddings that has favorable compositional properties.<n>We compute separate embeddings of sub-images of object entities and relations that are localized by the state of the art open vocabulary detectors.<n>The resulting embedding is then utilized for similarity computation with text embedding, resulting in a average 1.5% improvement in image-text matching accuracy.
• Score: 1.962396488631213
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: Vision-language pretraining on large datasets of images-text pairs is one of the main building blocks of current Vision-Language Models. While with additional training, these models excel in various downstream tasks, including visual question answering, image captioning, and visual commonsense reasoning. However, a notable weakness of pretrained models like CLIP, is their inability to perform entity grounding and compositional image and text matching~\cite{Jiang2024ComCLIP, yang2023amc, Rajabi2023GroundedVSR, learninglocalizeCVPR24}. In this work we propose a novel learning-free zero-shot augmentation of CLIP embeddings that has favorable compositional properties. We compute separate embeddings of sub-images of object entities and relations that are localized by the state of the art open vocabulary detectors and dynamically adjust the baseline global image embedding. % The final embedding is obtained by computing a weighted combination of the sub-image embeddings. The resulting embedding is then utilized for similarity computation with text embedding, resulting in a average 1.5\% improvement in image-text matching accuracy on the Visual Genome and SVO Probes datasets~\cite{krishna2017visualgenome, svo}. Notably, the enhanced embeddings demonstrate superior retrieval performance, thus achieving significant gains on the Flickr30K and MS-COCO retrieval benchmarks~\cite{flickr30ke, mscoco}, improving the state-of-the-art Recall@1 by 12\% and 0.4\%, respectively. Our code is available at https://github.com/madhukarreddyvongala/GroundingCLIP.

Related papers

• 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)
• ComAlign: Compositional Alignment in Vision-Language Models [2.3250871476216814]
  We introduce Compositional Alignment (ComAlign) to discover more exact correspondence of text and image components. Our methodology emphasizes that the compositional structure extracted from the text modality must also be retained in the image modality. We train a lightweight network lying on top of existing visual and language encoders using a small dataset.
  arXiv  Detail & Related papers  (2024-09-12T16:46:41Z)
• Advancing Visual Grounding with Scene Knowledge: Benchmark and Method [74.72663425217522]
  Visual grounding (VG) aims to establish fine-grained alignment between vision and language. Most existing VG datasets are constructed using simple description texts. We propose a novel benchmark of underlineScene underlineKnowledge-guided underlineVisual underlineGrounding.
  arXiv  Detail & Related papers  (2023-07-21T13:06:02Z)
• LLaVAR: Enhanced Visual Instruction Tuning for Text-Rich Image Understanding [85.39419609430453]
  This work enhances the current visual instruction tuning pipeline with text-rich images. We first use publicly available OCR tools to collect results on 422K text-rich images from the LAION dataset. We prompt text-only GPT-4 with recognized texts and image captions to generate 16K conversations, each containing question-answer pairs for text-rich images.
  arXiv  Detail & Related papers  (2023-06-29T17:08:16Z)
• STAIR: Learning Sparse Text and Image Representation in Grounded Tokens [84.14528645941128]
  We show that it is possible to build a sparse semantic representation that is as powerful as, or even better than, dense presentations. We extend the CLIP model and build a sparse text and image representation (STAIR), where the image and text are mapped to a sparse token space. It significantly outperforms a CLIP model with +$4.9%$ and +$4.3%$ absolute Recall@1 improvement.
  arXiv  Detail & Related papers  (2023-01-30T17:21:30Z)
• ComCLIP: Training-Free Compositional Image and Text Matching [19.373706257771673]
  Contrastive Language-Image Pretraining has demonstrated great zero-shot performance for matching images and text. We propose a novel textbftextittraining-free compositional CLIP model (ComCLIP) ComCLIP disentangles input images into subjects, objects, and action sub-images and composes CLIP's vision encoder and text encoder to perform evolving matching over compositional text embedding and sub-image embeddings.
  arXiv  Detail & Related papers  (2022-11-25T01:37:48Z)
• ContextCLIP: Contextual Alignment of Image-Text pairs on CLIP visual representations [4.588028371034406]
  We propose ContextCLIP, a contextual and contrastive learning framework for the contextual alignment of image-text pairs. Our framework was observed to improve the image-text alignment by aligning text and image representations contextually in the joint embedding space. ContextCLIP showed good qualitative performance for text-to-image retrieval tasks and enhanced classification accuracy.
  arXiv  Detail & Related papers  (2022-11-14T05:17:51Z)
• CyCLIP: Cyclic Contrastive Language-Image Pretraining [34.588147979731374]
  Recent advances in contrastive representation learning over paired image-text data have led to models such as CLIP that achieve state-of-the-art performance for zero-shot classification and distributional robustness. We demonstrate that the image and text representations learned via a standard contrastive objective are not interchangeable and can lead to inconsistent downstream predictions. We propose CyCLIP, a framework for contrastive representation learning that explicitly optimize for the learned representations to be geometrically consistent in the image and text space.
  arXiv  Detail & Related papers  (2022-05-28T15:31:17Z)
• Scaling Up Visual and Vision-Language Representation Learning With Noisy Text Supervision [57.031588264841]
  We leverage a noisy dataset of over one billion image alt-text pairs, obtained without expensive filtering or post-processing steps. A simple dual-encoder architecture learns to align visual and language representations of the image and text pairs using a contrastive loss. We show that the scale of our corpus can make up for its noise and leads to state-of-the-art representations even with such a simple learning scheme.
  arXiv  Detail & Related papers  (2021-02-11T10:08:12Z)

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.