Dynamic Relation Inference via Verb Embeddings

• URL: http://arxiv.org/abs/2503.13021v1
• Date: Mon, 17 Mar 2025 10:24:27 GMT
• Title: Dynamic Relation Inference via Verb Embeddings
• Authors: Omri Suissa, Muhiim Ali, Ariana Azarbal, Hui Shen, Shekhar Pradhan,
• Abstract summary: We offer insights and practical methods to advance the field of relation inference from images.<n>We propose Dynamic Relation Inference via Verb Embeddings (DRIVE), which augments the COCO dataset, fine-tunes CLIP with hard negatives subject-relation-object triples and corresponding images, and introduces a novel loss function to improve relation detection.
• Score: 2.8436327410529483
• License: http://creativecommons.org/licenses/by-nc-nd/4.0/
• Abstract: CLIP has demonstrated exceptional image-text matching capabilities due to its training on contrastive learning tasks. Past research has suggested that whereas CLIP effectively matches text to images when the matching can be achieved just by matching the text with the objects in the image, CLIP struggles when the matching depends on representing the relationship among the objects in the images (i.e., inferring relations). Previous attempts to address this limitation by training CLIP on relation detection datasets with only linguistic supervision have met with limited success. In this paper, we offer insights and practical methods to advance the field of relation inference from images. This paper approaches the task of creating a model that effectively detects relations among the objects in images by producing text and image embeddings that capture relationships through linguistic supervision. To this end, we propose Dynamic Relation Inference via Verb Embeddings (DRIVE), which augments the COCO dataset, fine-tunes CLIP with hard negatives subject-relation-object triples and corresponding images, and introduces a novel loss function to improve relation detection. Evaluated on multiple CLIP-based models, our method significantly improves zero-shot relation inference accuracy in both frozen and fine-tuned settings, significantly outperforming CLIP and state-of-the-art models while generalizing well on unseen data.

Related papers

• Object-centric Binding in Contrastive Language-Image Pretraining [9.376583779399834]
  We propose a novel approach that diverges from commonly used strategies, which rely on the design of hard-negative augmentations.<n>Our work focuses on integrating inductive biases into pre-trained CLIP-like models to improve their compositional understanding without using any additional hard-negatives.<n>Our resulting model paves the way towards more accurate and sample-efficient image-text matching of complex scenes.
  arXiv  Detail & Related papers  (2025-02-19T21:30:51Z)
• 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)
• Semantic Compositions Enhance Vision-Language Contrastive Learning [46.985865191341944]
  We show that the zero-shot classification and retrieval capabilities of CLIP-like models can be improved significantly through the introduction of semantically composite examples during pretraining. Our method fuses the captions and blends 50% of each image to form a new composite sample. The benefits of CLIP-C are particularly pronounced in settings with relatively limited pretraining data.
  arXiv  Detail & Related papers  (2024-07-01T15:58:20Z)
• Unified Visual Relationship Detection with Vision and Language Models [89.77838890788638]
  This work focuses on training a single visual relationship detector predicting over the union of label spaces from multiple datasets. We propose UniVRD, a novel bottom-up method for Unified Visual Relationship Detection by leveraging vision and language models. Empirical results on both human-object interaction detection and scene-graph generation demonstrate the competitive performance of our model.
  arXiv  Detail & Related papers  (2023-03-16T00:06:28Z)
• FECANet: Boosting Few-Shot Semantic Segmentation with Feature-Enhanced Context-Aware Network [48.912196729711624]
  Few-shot semantic segmentation is the task of learning to locate each pixel of a novel class in a query image with only a few annotated support images. We propose a Feature-Enhanced Context-Aware Network (FECANet) to suppress the matching noise caused by inter-class local similarity. In addition, we propose a novel correlation reconstruction module that encodes extra correspondence relations between foreground and background and multi-scale context semantic features.
  arXiv  Detail & Related papers  (2023-01-19T16:31:13Z)
• 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)
• Robust Cross-Modal Representation Learning with Progressive Self-Distillation [7.676408770854477]
  The learning objective of vision-language approach of CLIP does not effectively account for the noisy many-to-many correspondences found in web-harvested image captioning datasets. We introduce a novel training framework based on cross-modal contrastive learning that uses progressive self-distillation and soft image-text alignments to more efficiently learn robust representations from noisy data.
  arXiv  Detail & Related papers  (2022-04-10T03:28:18Z)
• Deep Relational Metric Learning [84.95793654872399]
  This paper presents a deep relational metric learning framework for image clustering and retrieval. We learn an ensemble of features that characterizes an image from different aspects to model both interclass and intraclass distributions. Experiments on the widely-used CUB-200-2011, Cars196, and Stanford Online Products datasets demonstrate that our framework improves existing deep metric learning methods and achieves very competitive results.
  arXiv  Detail & Related papers  (2021-08-23T09:31:18Z)
• Tensor Composition Net for Visual Relationship Prediction [115.14829858763399]
  We present a novel Composition Network (TCN) to predict visual relationships in images. The key idea of our TCN is to exploit the low rank property of the visual relationship tensor. We show our TCN's image-level visual relationship prediction provides a simple and efficient mechanism for relation-based image retrieval.
  arXiv  Detail & Related papers  (2020-12-10T06:27:20Z)

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.