Dynamic Multimodal Prototype Learning in Vision-Language Models

• URL: http://arxiv.org/abs/2507.03657v1
• Date: Fri, 04 Jul 2025 15:31:47 GMT
• Title: Dynamic Multimodal Prototype Learning in Vision-Language Models
• Authors: Xingyu Zhu, Shuo Wang, Beier Zhu, Miaoge Li, Yunfan Li, Junfeng Fang, Zhicai Wang, Dongsheng Wang, Hanwang Zhang,
• Abstract summary: We introduce textbfProtoMM, a training-free framework that constructs multimodal prototypes to adapt vision-language models during the test time.<n>By viewing the prototype as a discrete distribution over the textual descriptions and visual particles, ProtoMM has the ability to combine the multimodal features for comprehensive prototype learning.
• Score: 44.84161970425967
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: With the increasing attention to pre-trained vision-language models (VLMs), \eg, CLIP, substantial efforts have been devoted to many downstream tasks, especially in test-time adaptation (TTA). However, previous works focus on learning prototypes only in the textual modality while overlooking the ambiguous semantics in class names. These ambiguities lead to textual prototypes that are insufficient to capture visual concepts, resulting in limited performance. To address this issue, we introduce \textbf{ProtoMM}, a training-free framework that constructs multimodal prototypes to adapt VLMs during the test time. By viewing the prototype as a discrete distribution over the textual descriptions and visual particles, ProtoMM has the ability to combine the multimodal features for comprehensive prototype learning. More importantly, the visual particles are dynamically updated as the testing stream flows. This allows our multimodal prototypes to continually learn from the data, enhancing their generalizability in unseen scenarios. In addition, we quantify the importance of the prototypes and test images by formulating their semantic distance as an optimal transport problem. Extensive experiments on 15 zero-shot benchmarks demonstrate the effectiveness of our method, achieving a 1.03\% average accuracy improvement over state-of-the-art methods on ImageNet and its variant datasets.

Related papers

• Dual Prototype Evolving for Test-Time Generalization of Vision-Language Models [11.545127156146368]
  We introduce Dual Prototype Evolving (DPE), a novel test-time adaptation approach for pre-trained vision-language models (VLMs) We create and evolve two sets of prototypes--textual and visual--to progressively capture more accurate multi-modal representations for target classes during test time. Our proposed DPE consistently outperforms previous state-of-the-art methods while also exhibiting competitive computational efficiency.
  arXiv  Detail & Related papers  (2024-10-16T17:59:49Z)
• NODE-Adapter: Neural Ordinary Differential Equations for Better Vision-Language Reasoning [30.440574052935407]
  existing methods encounter three major challenges in vision-language reasoning. We propose a novel method called NODE-Adapter, which utilizes Neural Ordinary Differential Equations for better vision-language reasoning. Our experimental results, which cover few-shot classification, domain generalization, and visual reasoning on human-object interaction, demonstrate that the proposed method significantly outperforms existing state-of-the-art approaches.
  arXiv  Detail & Related papers  (2024-07-11T17:04:19Z)
• Just Shift It: Test-Time Prototype Shifting for Zero-Shot Generalization with Vision-Language Models [19.683461002518147]
  Test-Time Prototype Shifting (TPS) is a pioneering approach designed to adapt vision-language models to test datasets using unlabeled test inputs.<n>TPS not only facilitates optimization-free prototype reuse for subsequent predictions but also enables seamless integration with current advancements in prompt engineering.<n>A notable aspect of our framework is its significantly reduced memory and computational demands when compared to conventional text-prompt tuning methods.
  arXiv  Detail & Related papers  (2024-03-19T17:54:34Z)
• Expedited Training of Visual Conditioned Language Generation via Redundancy Reduction [61.16125290912494]
  $textEVL_textGen$ is a framework designed for the pre-training of visually conditioned language generation models. We show that our approach accelerates the training of vision-language models by a factor of 5 without a noticeable impact on overall performance.
  arXiv  Detail & Related papers  (2023-10-05T03:40:06Z)
• Unsupervised Prototype Adapter for Vision-Language Models [29.516767588241724]
  We design an unsupervised fine-tuning approach for vision-language models called Unsupervised Prototype Adapter (UP-Adapter) Specifically, for the unannotated target datasets, we leverage the text-image aligning capability of CLIP to automatically select the most confident samples for each class. After fine-tuning, the prototype model prediction is combined with the original CLIP's prediction by a residual connection to perform downstream recognition tasks.
  arXiv  Detail & Related papers  (2023-08-22T15:28:49Z)
• UniDiff: Advancing Vision-Language Models with Generative and Discriminative Learning [86.91893533388628]
  This paper presents UniDiff, a unified multi-modal model that integrates image-text contrastive learning (ITC), text-conditioned image synthesis learning (IS), and reciprocal semantic consistency modeling (RSC) UniDiff demonstrates versatility in both multi-modal understanding and generative tasks.
  arXiv  Detail & Related papers  (2023-06-01T15:39:38Z)
• Rethinking Visual Prompt Learning as Masked Visual Token Modeling [106.71983630652323]
  We propose Visual Prompt learning as masked visual Token Modeling (VPTM) to transform the downstream visual classification into the pre-trained masked visual token prediction. VPTM is the first visual prompt method on the generative pre-trained visual model, which achieves consistency between pre-training and downstream visual classification by task reformulation.
  arXiv  Detail & Related papers  (2023-03-09T02:43:10Z)
• Multimodal Prototype-Enhanced Network for Few-Shot Action Recognition [40.329190454146996]
  MultimOdal PRototype-ENhanced Network (MORN) uses semantic information of label texts as multimodal information to enhance prototypes. We conduct extensive experiments on four popular few-shot action recognition datasets.
  arXiv  Detail & Related papers  (2022-12-09T14:24:39Z)
• Multi-Modal Few-Shot Object Detection with Meta-Learning-Based Cross-Modal Prompting [77.69172089359606]
  We study multi-modal few-shot object detection (FSOD) in this paper, using both few-shot visual examples and class semantic information for detection. Our approach is motivated by the high-level conceptual similarity of (metric-based) meta-learning and prompt-based learning. We comprehensively evaluate the proposed multi-modal FSOD models on multiple few-shot object detection benchmarks, achieving promising results.
  arXiv  Detail & Related papers  (2022-04-16T16:45:06Z)
• Dual Prototypical Contrastive Learning for Few-shot Semantic Segmentation [55.339405417090084]
  We propose a dual prototypical contrastive learning approach tailored to the few-shot semantic segmentation (FSS) task. The main idea is to encourage the prototypes more discriminative by increasing inter-class distance while reducing intra-class distance in prototype feature space. We demonstrate that the proposed dual contrastive learning approach outperforms state-of-the-art FSS methods on PASCAL-5i and COCO-20i datasets.
  arXiv  Detail & Related papers  (2021-11-09T08:14:50Z)
• Behind the Scene: Revealing the Secrets of Pre-trained Vision-and-Language Models [65.19308052012858]
  Recent Transformer-based large-scale pre-trained models have revolutionized vision-and-language (V+L) research. We present VALUE, a set of meticulously designed probing tasks to decipher the inner workings of multimodal pre-training. Key observations: Pre-trained models exhibit a propensity for attending over text rather than images during inference.
  arXiv  Detail & Related papers  (2020-05-15T01:06:54Z)

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.