Visual Perturbation and Adaptive Hard Negative Contrastive Learning for Compositional Reasoning in Vision-Language Models

• URL: http://arxiv.org/abs/2505.15576v1
• Date: Wed, 21 May 2025 14:28:43 GMT
• Title: Visual Perturbation and Adaptive Hard Negative Contrastive Learning for Compositional Reasoning in Vision-Language Models
• Authors: Xin Huang, Ruibin Li, Tong Jia, Wei Zheng, Ya Wang,
• Abstract summary: Vision-Language Models (VLMs) are essential for multimodal tasks, especially compositional reasoning (CR) tasks.<n>Existing methods primarily fine-tune the model by generating text-based hard negative samples.<n>AHNPL translates text-based hard negatives into the visual domain to generate semantically disturbed image-based negatives for training the model.
• Score: 9.682523487279976
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: Vision-Language Models (VLMs) are essential for multimodal tasks, especially compositional reasoning (CR) tasks, which require distinguishing fine-grained semantic differences between visual and textual embeddings. However, existing methods primarily fine-tune the model by generating text-based hard negative samples, neglecting the importance of image-based negative samples, which results in insufficient training of the visual encoder and ultimately impacts the overall performance of the model. Moreover, negative samples are typically treated uniformly, without considering their difficulty levels, and the alignment of positive samples is insufficient, which leads to challenges in aligning difficult sample pairs. To address these issues, we propose Adaptive Hard Negative Perturbation Learning (AHNPL). AHNPL translates text-based hard negatives into the visual domain to generate semantically disturbed image-based negatives for training the model, thereby enhancing its overall performance. AHNPL also introduces a contrastive learning approach using a multimodal hard negative loss to improve the model's discrimination of hard negatives within each modality and a dynamic margin loss that adjusts the contrastive margin according to sample difficulty to enhance the distinction of challenging sample pairs. Experiments on three public datasets demonstrate that our method effectively boosts VLMs' performance on complex CR tasks. The source code is available at https://github.com/nynu-BDAI/AHNPL.

Related papers

• A Visual Leap in CLIP Compositionality Reasoning through Generation of Counterfactual Sets [26.167194142428475]
  Vision-language models (VLMs) often struggle with compositional reasoning due to insufficient high-quality image-text data.<n>We propose a novel block-based diffusion approach that automatically generates counterfactual datasets without manual annotation.<n>Our approach achieves state-of-the-art results across multiple benchmarks while using substantially less training data than existing methods.
  arXiv  Detail & Related papers  (2025-07-07T06:47:10Z)
• Enhancing Fine-Grained Vision-Language Pretraining with Negative Augmented Samples [12.407654428921049]
  Existing Vision-Language Pretraining methods have achieved remarkable improvements across a variety of vision-language tasks.<n>However, their capability for fine-grained understanding, which is critical for many nuanced vision-language applications, remains limited.<n>We introduce Negative Augmented Samples(NAS), a vision-language pretraining model that innovatively incorporates NAS to specifically address the challenge of fine-grained understanding.
  arXiv  Detail & Related papers  (2024-12-13T10:39:31Z)
• Boosting Semi-Supervised Scene Text Recognition via Viewing and Summarizing [71.29488677105127]
  Existing scene text recognition (STR) methods struggle to recognize challenging texts, especially for artistic and severely distorted characters. We propose a contrastive learning-based STR framework by leveraging synthetic and real unlabeled data without any human cost. Our method achieves SOTA performance (94.7% and 70.9% average accuracy on common benchmarks and Union14M-Benchmark.
  arXiv  Detail & Related papers  (2024-11-23T15:24:47Z)
• HNCSE: Advancing Sentence Embeddings via Hybrid Contrastive Learning with Hard Negatives [17.654412302780557]
  HNCSE is a novel contrastive learning framework that extends the leading SimCSE approach. The hallmark of HNCSE is its innovative use of hard negative samples to enhance the learning of both positive and negative samples.
  arXiv  Detail & Related papers  (2024-11-19T01:26:20Z)
• Dissecting Representation Misalignment in Contrastive Learning via Influence Function [15.28417468377201]
  We introduce the Extended Influence Function for Contrastive Loss (ECIF), an influence function crafted for contrastive loss.<n>ECIF considers both positive and negative samples and provides a closed-form approximation of contrastive learning models.<n>Building upon ECIF, we develop a series of algorithms for data evaluation, misalignment detection, and misprediction trace-back tasks.
  arXiv  Detail & Related papers  (2024-11-18T15:45:41Z)
• Debiasing Multimodal Large Language Models [61.6896704217147]
  Large Vision-Language Models (LVLMs) have become indispensable tools in computer vision and natural language processing. Our investigation reveals a noteworthy bias in the generated content, where the output is primarily influenced by the underlying Large Language Models (LLMs) prior to the input image. To rectify these biases and redirect the model's focus toward vision information, we introduce two simple, training-free strategies.
  arXiv  Detail & Related papers  (2024-03-08T12:35:07Z)
• Learning the Unlearned: Mitigating Feature Suppression in Contrastive Learning [45.25602203155762]
  Self-Supervised Contrastive Learning has proven effective in deriving high-quality representations from unlabeled data. A major challenge that hinders both unimodal and multimodal contrastive learning is feature suppression. We propose a novel model-agnostic Multistage Contrastive Learning framework.
  arXiv  Detail & Related papers  (2024-02-19T04:13:33Z)
• Enhancing Multimodal Compositional Reasoning of Visual Language Models with Generative Negative Mining [58.379339799777064]
  Large-scale visual language models (VLMs) exhibit strong representation capacities, making them ubiquitous for enhancing image and text understanding tasks. We propose a framework that not only mines in both directions but also generates challenging negative samples in both modalities. Our code and dataset are released at https://ugorsahin.github.io/enhancing-multimodal-compositional-reasoning-of-vlm.html.
  arXiv  Detail & Related papers  (2023-11-07T13:05:47Z)
• Contrasting Intra-Modal and Ranking Cross-Modal Hard Negatives to Enhance Visio-Linguistic Compositional Understanding [6.798129852396113]
  We introduce a simple and effective method to improve compositional reasoning in Vision-Language Models (VLMs) Our method better leverages available datasets by refining and expanding the standard image-text contrastive learning framework. When integrated with CLIP, our technique yields notable improvement over state-of-the-art baselines.
  arXiv  Detail & Related papers  (2023-06-15T03:26:28Z)
• A Practical Contrastive Learning Framework for Single-Image Super-Resolution [51.422185656787285]
  We investigate contrastive learning-based single image super-resolution from two perspectives. We propose a practical contrastive learning framework for SISR, named PCL-SR. Compared with existing benchmark methods, we re-train them by our proposed PCL-SR framework and achieve superior performance.
  arXiv  Detail & Related papers  (2021-11-27T15:42:12Z)
• Dense Contrastive Visual-Linguistic Pretraining [53.61233531733243]
  Several multimodal representation learning approaches have been proposed that jointly represent image and text. These approaches achieve superior performance by capturing high-level semantic information from large-scale multimodal pretraining. We propose unbiased Dense Contrastive Visual-Linguistic Pretraining to replace the region regression and classification with cross-modality region contrastive learning.
  arXiv  Detail & Related papers  (2021-09-24T07:20:13Z)
• Unleashing the Power of Contrastive Self-Supervised Visual Models via Contrast-Regularized Fine-Tuning [94.35586521144117]
  We investigate whether applying contrastive learning to fine-tuning would bring further benefits. We propose Contrast-regularized tuning (Core-tuning), a novel approach for fine-tuning contrastive self-supervised visual models.
  arXiv  Detail & Related papers  (2021-02-12T16:31:24Z)

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.