Why are Visually-Grounded Language Models Bad at Image Classification?

• URL: http://arxiv.org/abs/2405.18415v1
• Date: Tue, 28 May 2024 17:57:06 GMT
• Title: Why are Visually-Grounded Language Models Bad at Image Classification?
• Authors: Yuhui Zhang, Alyssa Unell, Xiaohan Wang, Dhruba Ghosh, Yuchang Su, Ludwig Schmidt, Serena Yeung-Levy,
• Abstract summary: We revisit the image classification task using visually-grounded language models (VLMs) such as GPT-4V and LLaVA. We find that existing proprietary and public VLMs significantly underperform CLIP on standard image classification benchmarks like ImageNet. Our analysis reveals that the primary cause is data-related: critical information for image classification is encoded in the VLM's latent space but can only be effectively decoded with enough training data.
• Score: 39.76294811955341
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: Image classification is one of the most fundamental capabilities of machine vision intelligence. In this work, we revisit the image classification task using visually-grounded language models (VLMs) such as GPT-4V and LLaVA. We find that existing proprietary and public VLMs, despite often using CLIP as a vision encoder and having many more parameters, significantly underperform CLIP on standard image classification benchmarks like ImageNet. To understand the reason, we explore several hypotheses concerning the inference algorithms, training objectives, and data processing in VLMs. Our analysis reveals that the primary cause is data-related: critical information for image classification is encoded in the VLM's latent space but can only be effectively decoded with enough training data. Specifically, there is a strong correlation between the frequency of class exposure during VLM training and instruction-tuning and the VLM's performance in those classes; when trained with sufficient data, VLMs can match the accuracy of state-of-the-art classification models. Based on these findings, we enhance a VLM by integrating classification-focused datasets into its training, and demonstrate that the enhanced classification performance of the VLM transfers to its general capabilities, resulting in an improvement of 11.8% on the newly collected ImageWikiQA dataset.

Related papers

• Membership Inference Attacks against Large Vision-Language Models [40.996912464828696]
  Large vision-language models (VLLMs) exhibit promising capabilities for processing multi-modal tasks across various application scenarios. Their emergence also raises significant data security concerns, given the potential inclusion of sensitive information, such as private photos and medical records. Detecting inappropriately used data in VLLMs remains a critical and unresolved issue.
  arXiv  Detail & Related papers  (2024-11-05T08:35:08Z)
• EZ-HOI: VLM Adaptation via Guided Prompt Learning for Zero-Shot HOI Detection [21.091101582856183]
  We introduce a novel prompt learning-based framework for Efficient Zero-Shot HOI detection (EZ-HOI). First, we introduce Large Language Model (LLM) and VLM guidance for learnable prompts, integrating detailed HOI descriptions and visual semantics to adapt VLMs to HOI tasks. We show that our framework achieves state-of-the-art performance across various zero-shot settings with only 10.35% to 33.95% of the trainable parameters compared to existing methods.
  arXiv  Detail & Related papers  (2024-10-31T13:06:29Z)
• Web-Scale Visual Entity Recognition: An LLM-Driven Data Approach [56.55633052479446]
  Web-scale visual entity recognition presents significant challenges due to the lack of clean, large-scale training data. We propose a novel methodology to curate such a dataset, leveraging a multimodal large language model (LLM) for label verification, metadata generation, and rationale explanation. Experiments demonstrate that models trained on this automatically curated data achieve state-of-the-art performance on web-scale visual entity recognition tasks.
  arXiv  Detail & Related papers  (2024-10-31T06:55:24Z)
• How Well Can Vision Language Models See Image Details? [53.036922527685064]
  We introduce a pixel value prediction task to explore "How Well Can Vision Language Models See Image Details?" Our research reveals that incorporating pixel value prediction as one of the VLM pre-training tasks and vision encoder adaptation markedly boosts VLM performance on downstream image-language understanding tasks.
  arXiv  Detail & Related papers  (2024-08-07T17:59:40Z)
• 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)
• Improved Zero-Shot Classification by Adapting VLMs with Text Descriptions [24.596929878045568]
  We develop methods to train vision-language models (VLMs) with "bag-level" image-text supervision. We use descriptions of categories generated by large language models (LLMs) and abundant, fine-grained image classification datasets. Our findings suggest that geographic priors can be just as effective and are complementary to visual appearance.
  arXiv  Detail & Related papers  (2024-01-04T08:39:13Z)
• CLAMP: Contrastive LAnguage Model Prompt-tuning [89.96914454453791]
  We show that large language models can achieve good image classification performance when adapted this way. Our approach beats state-of-the-art mLLMs by 13% and slightly outperforms contrastive learning with a custom text model.
  arXiv  Detail & Related papers  (2023-12-04T05:13:59Z)
• 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)
• Masked Unsupervised Self-training for Zero-shot Image Classification [98.23094305347709]
  Masked Unsupervised Self-Training (MUST) is a new approach which leverages two different and complimentary sources of supervision: pseudo-labels and raw images. MUST improves upon CLIP by a large margin and narrows the performance gap between unsupervised and supervised classification.
  arXiv  Detail & Related papers  (2022-06-07T02:03:06Z)

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.