LLMs Can Compensate for Deficiencies in Visual Representations

• URL: http://arxiv.org/abs/2506.05439v1
• Date: Thu, 05 Jun 2025 12:04:59 GMT
• Title: LLMs Can Compensate for Deficiencies in Visual Representations
• Authors: Sho Takishita, Jay Gala, Abdelrahman Mohamed, Kentaro Inui, Yova Kementchedjhieva,
• Abstract summary: We build on CLIP-based vision encoders, which are known to have various limitations.<n>We perform controlled self-attention ablations on a carefully designed probing task.<n>Our findings show that despite known limitations, CLIP visual representations offer ready-to-read semantic information to the language decoder.
• Score: 34.01176691790258
• License: http://creativecommons.org/licenses/by-sa/4.0/
• Abstract: Many vision-language models (VLMs) that prove very effective at a range of multimodal task, build on CLIP-based vision encoders, which are known to have various limitations. We investigate the hypothesis that the strong language backbone in VLMs compensates for possibly weak visual features by contextualizing or enriching them. Using three CLIP-based VLMs, we perform controlled self-attention ablations on a carefully designed probing task. Our findings show that despite known limitations, CLIP visual representations offer ready-to-read semantic information to the language decoder. However, in scenarios of reduced contextualization in the visual representations, the language decoder can largely compensate for the deficiency and recover performance. This suggests a dynamic division of labor in VLMs and motivates future architectures that offload more visual processing to the language decoder.

Related papers

• CLIP-IN: Enhancing Fine-Grained Visual Understanding in CLIP via Instruction Editing Data and Long Captions [17.05291662808873]
  We present CLIP-IN, a novel framework that bolsters CLIP's fine-grained perception through two core innovations.<n> Firstly, we leverage instruction-editing datasets, originally designed for image manipulation, as a unique source of hard negative image-text pairs.<n> Secondly, CLIP-IN incorporates long captions, utilizing rotary positional encodings to capture rich semantic context often missed by standard CLIP.
  arXiv  Detail & Related papers  (2025-08-04T11:57:10Z)
• Response Wide Shut? Surprising Observations in Basic Vision Language Model Capabilities [54.94982467313341]
  Vision-language Models (VLMs) have emerged as general-purpose tools for addressing a variety of complex computer vision problems.<n>We set out to understand the limitations of SoTA VLMs on fundamental visual tasks by constructing a series of tests that probe which components of design, specifically, may be lacking.
  arXiv  Detail & Related papers  (2025-07-10T15:26:41Z)
• Hidden in plain sight: VLMs overlook their visual representations [48.83628674170634]
  We compare vision language models (VLMs) to their visual encoders to understand their ability to integrate across these modalities.<n>We find that VLMs perform substantially worse than their visual encoders, dropping to near-chance performance.
  arXiv  Detail & Related papers  (2025-06-09T17:59:54Z)
• LLM2CLIP: Powerful Language Model Unlocks Richer Visual Representation [72.02635550088546]
  This work explores how large language models (LLMs) can enhance CLIP's capability, especially for processing longer and more complex image captions.<n>We introduce a caption-to-caption contrastive fine-tuning framework, significantly enhancing the discriminative quality of LLM outputs.<n>Our approach outperforms LoRA-based methods, achieving nearly fourfold faster training with superior performance.
  arXiv  Detail & Related papers  (2024-11-07T18:59:16Z)
• Diffusion Feedback Helps CLIP See Better [40.125318318373715]
  Contrastive Language-Image Pre-training (CLIP) excels at abstracting open-world representations across domains and modalities. CLIP has severe visual shortcomings, such as which can hardly distinguish orientation, quantity, color, structure. We present a post-training approach for CLIP models, which largely overcomes its visual shortcomings via a self-supervised diffusion process.
  arXiv  Detail & Related papers  (2024-07-29T17:00:09Z)
• BRAVE: Broadening the visual encoding of vision-language models [48.41146184575914]
  Vision-language models (VLMs) are composed of a vision encoder, e.g. CLIP, and a language model (LM) that interprets the encoded features to solve downstream tasks. Despite remarkable progress, VLMs are subject to several shortcomings due to the limited capabilities of vision encoders. We introduce BRAVE, which consolidates features from multiple frozen encoders into a more versatile representation that can be directly fed as the input to a frozen LM.
  arXiv  Detail & Related papers  (2024-04-10T17:59:45Z)
• MouSi: Poly-Visual-Expert Vision-Language Models [132.58949014605477]
  This paper proposes the use of ensemble experts technique to synergize the capabilities of individual visual encoders. This technique introduces a fusion network to unify the processing of outputs from different visual experts. In our implementation, this technique significantly reduces the positional occupancy in models like SAM, from a substantial 4096 to a more efficient and manageable 64 or even down to 1.
  arXiv  Detail & Related papers  (2024-01-30T18:09:11Z)
• Eyes Wide Shut? Exploring the Visual Shortcomings of Multimodal LLMs [50.77984109941538]
  Our research reveals that the visual capabilities in recent multimodal LLMs still exhibit systematic shortcomings. We identify ''CLIP-blind pairs'' - images that CLIP perceives as similar despite their clear visual differences. We evaluate various CLIP-based vision-and-language models and found a notable correlation between visual patterns that challenge CLIP models and those problematic for multimodal LLMs.
  arXiv  Detail & Related papers  (2024-01-11T18:58:36Z)
• VCoder: Versatile Vision Encoders for Multimodal Large Language Models [46.95488342139727]
  Multimodal Large Language Models (MLLM) have recently achieved impressive performance on vision-language tasks. However, when prompted to identify or count (perceive) the entities in a given image, existing MLLM systems fail. We propose using Versatile vision enCoders (VCoder) as perception eyes for Multimodal LLMs.
  arXiv  Detail & Related papers  (2023-12-21T18:49:47Z)
• Unified Language-Vision Pretraining in LLM with Dynamic Discrete Visual Tokenization [52.935150075484074]
  We introduce a well-designed visual tokenizer to translate the non-linguistic image into a sequence of discrete tokens like a foreign language. The resulting visual tokens encompass high-level semantics worthy of a word and also support dynamic sequence length varying from the image. This unification empowers LaVIT to serve as an impressive generalist interface to understand and generate multi-modal content simultaneously.
  arXiv  Detail & Related papers  (2023-09-09T03:01:38Z)

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.