Learning to Rank Pre-trained Vision-Language Models for Downstream Tasks

• URL: http://arxiv.org/abs/2412.20682v1
• Date: Mon, 30 Dec 2024 03:26:53 GMT
• Title: Learning to Rank Pre-trained Vision-Language Models for Downstream Tasks
• Authors: Yuhe Ding, Bo Jiang, Aihua Zheng, Qin Xu, Jian Liang,
• Abstract summary: Vision language models (VLMs) like CLIP show stellar zero-shot capability on classification benchmarks. selecting the VLM with the highest performance on the unlabeled downstream task is non-trivial. This paper introduces the problem of textbfunsupervised vision-language model selection, where only unsupervised downstream datasets are available.
• Score: 41.488394198111976
• License:
• Abstract: Vision language models (VLMs) like CLIP show stellar zero-shot capability on classification benchmarks. However, selecting the VLM with the highest performance on the unlabeled downstream task is non-trivial. Existing VLM selection methods focus on the class-name-only setting, relying on a supervised large-scale dataset and large language models, which may not be accessible or feasible during deployment. This paper introduces the problem of \textbf{unsupervised vision-language model selection}, where only unsupervised downstream datasets are available, with no additional information provided. To solve this problem, we propose a method termed Visual-tExtual Graph Alignment (VEGA), to select VLMs without any annotations by measuring the alignment of the VLM between the two modalities on the downstream task. VEGA is motivated by the pretraining paradigm of VLMs, which aligns features with the same semantics from the visual and textual modalities, thereby mapping both modalities into a shared representation space. Specifically, we first construct two graphs on the vision and textual features, respectively. VEGA is then defined as the overall similarity between the visual and textual graphs at both node and edge levels. Extensive experiments across three different benchmarks, covering a variety of application scenarios and downstream datasets, demonstrate that VEGA consistently provides reliable and accurate estimates of VLMs' performance on unlabeled downstream tasks.

Related papers

• Can Graph Neural Networks Learn Language with Extremely Weak Text Supervision? [62.12375949429938]
  Building transferable Graph Neural Networks (GNNs) with CLIP pipeline is challenging because of three fundamental issues. We leverage multi-modal prompt learning to effectively adapt pre-trained GNN to downstream tasks and data. Our new paradigm embeds the graphs directly in the same space as the Large Language Models (LLMs) by learning both graph prompts and text prompts simultaneously.
  arXiv  Detail & Related papers  (2024-12-11T08:03:35Z)
• Enhance Graph Alignment for Large Language Models [33.96082485852042]
  Graph-to-token approaches are popular in enabling Large Language Models to process graph information. Existing methods have a misalignment between self-supervised tasks and supervised downstream tasks. We propose Graph Alignment Large Language Models (GALLM) to benefit from aligned task templates.
  arXiv  Detail & Related papers  (2024-10-15T07:50:34Z)
• Bridge the Modality and Capability Gaps in Vision-Language Model Selection [62.26769826687365]
  Vision Language Models (VLMs) excel in zero-shot image classification by pairing images with textual category names. To better reuse the VLM resource, a promising strategy is selecting appropriate Pre-Trained VLMs from the VLM Zoo. We analyze two inherent challenges in assessing the ability of a VLM in this Language-Only VLM selection. We propose VLM Selection With gAp Bridging to mitigate the negative impact of two gaps.
  arXiv  Detail & Related papers  (2024-03-20T17:54:58Z)
• Synthesize, Diagnose, and Optimize: Towards Fine-Grained Vision-Language Understanding [33.33424214458285]
  Vision language models (VLM) have demonstrated remarkable performance across various downstream tasks. However, understanding fine-grained visual-linguistic concepts, such as attributes and inter-object relationships, remains a significant challenge. We introduce a progressive pipeline to synthesize images that vary in a specific attribute while ensuring consistency in all other aspects.
  arXiv  Detail & Related papers  (2023-11-30T03:20:37Z)
• Leveraging VLM-Based Pipelines to Annotate 3D Objects [68.51034848207355]
  We propose an alternative algorithm to marginalize over factors such as the viewpoint that affect the VLM's response. Instead of merging text-only responses, we utilize the VLM's joint image-text likelihoods. We show how a VLM-based pipeline can be leveraged to produce reliable annotations for 764K objects from the 764K dataset.
  arXiv  Detail & Related papers  (2023-11-29T17:54:22Z)
• Visual Data-Type Understanding does not emerge from Scaling Vision-Language Models [31.69213233651326]
  We introduce the novel task of Visual Data-Type Identification. An extensive zero-shot evaluation of 39 vision-language models (VLMs) shows a nuanced performance landscape.
  arXiv  Detail & Related papers  (2023-10-12T17:59:30Z)
• Distribution-Aware Prompt Tuning for Vision-Language Models [20.02599087680773]
  A key to prompt tuning is the feature space alignment between two modalities via learnable vectors with model parameters fixed. Inspired by this observation, we proposed distribution-aware prompt tuning (DAPT) for vision-language models. Our experiments on 11 benchmark datasets demonstrate that our method significantly improves generalizability.
  arXiv  Detail & Related papers  (2023-09-06T23:49:11Z)
• ProbVLM: Probabilistic Adapter for Frozen Vision-Language Models [69.50316788263433]
  We propose ProbVLM, a probabilistic adapter that estimates probability distributions for the embeddings of pre-trained vision-language models. We quantify the calibration of embedding uncertainties in retrieval tasks and show that ProbVLM outperforms other methods. We present a novel technique for visualizing the embedding distributions using a large-scale pre-trained latent diffusion model.
  arXiv  Detail & Related papers  (2023-07-01T18:16:06Z)
• Fine-grained Visual-Text Prompt-Driven Self-Training for Open-Vocabulary Object Detection [87.39089806069707]
  We propose a fine-grained Visual-Text Prompt-driven self-training paradigm for Open-Vocabulary Detection (VTP-OVD) During the adapting stage, we enable VLM to obtain fine-grained alignment by using learnable text prompts to resolve an auxiliary dense pixel-wise prediction task. Experiments show that our method achieves the state-of-the-art performance for open-vocabulary object detection, e.g., 31.5% mAP on unseen classes of COCO.
  arXiv  Detail & Related papers  (2022-11-02T03:38:02Z)

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.