Boosting Visual Knowledge-Intensive Training for LVLMs Through Causality-Driven Visual Object Completion

• URL: http://arxiv.org/abs/2508.04453v1
• Date: Wed, 06 Aug 2025 13:54:49 GMT
• Title: Boosting Visual Knowledge-Intensive Training for LVLMs Through Causality-Driven Visual Object Completion
• Authors: Qingguo Hu, Ante Wang, Jia Song, Delai Qiu, Qingsong Liu, Jinsong Su,
• Abstract summary: Large Vision-Language Models (LVLMs) have experienced significant advancements in recent years.<n>However, their performance still falls short in tasks requiring deep visual perception.<n>We introduce a self-improvement framework grounded in a novel visual knowledge-intensive task.
• Score: 25.84673296137996
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: Large Vision-Language Models (LVLMs) have experienced significant advancements in recent years. However, their performance still falls short in tasks requiring deep visual perception, such as identifying subtle differences between images. A potential cause is the scarcity of visual knowledge in popular instruction-tuning corpora, resulting in inadequate visual perception and reasoning capabilities. To address this challenge, we introduce a self-improvement framework grounded in a novel visual knowledge-intensive task, \underline{C}ausality-driven \underline{V}isual object \underline{C}ompletion (CVC). This task requires LVLMs to infer the masked object in an image based on its \textit{causal} relationships with the other visible information. We first obtain rich examples cheaply through our automated instance construction pipeline, without relying on sophisticated LVLMs (\textit{e.g.}, GPT-4V) or human assistance. Then, LVLMs effectively self-improve through trial and error learning using these created instances. Our experiments demonstrate substantial gains across four challenging specialized tasks and four widely-used comprehensive benchmarks. Especially on specialized tasks, our method achieves an average improvement of 5.4\% and 4.0\% compared to the corresponding baselines when utilizing LLaVA-1.5-7B and LLaVA-1.5-13B, respectively. The code is available at https://github.com/XMUDeepLIT/CVC.

Related papers

• ViCrit: A Verifiable Reinforcement Learning Proxy Task for Visual Perception in VLMs [98.27348724529257]
  We introduce ViCrit (Visual Caption Hallucination Critic), an RL proxy task that trains VLMs to localize a subtle, synthetic visual hallucination injected into paragraphs of human-written image captions.<n>Models trained with the ViCrit Task exhibit substantial gains across a variety of vision-language models benchmarks.
  arXiv  Detail & Related papers  (2025-06-11T19:16:54Z)
• Open Eyes, Then Reason: Fine-grained Visual Mathematical Understanding in MLLMs [62.875934732547435]
  Current large language models (MLLMs) often underperform on mathematical problem-solving tasks that require fine-grained visual understanding.<n>In this paper, we evaluate the visual grounding capabilities of state-of-the-art MLLMs and reveal a significant negative correlation between visual grounding accuracy and problem-solving performance.<n>We propose a novel approach, SVE-Math, featuring a geometric-grounded vision encoder and a feature router that dynamically adjusts the contribution of hierarchical visual feature maps.
  arXiv  Detail & Related papers  (2025-01-11T04:08:44Z)
• Rethinking VLMs and LLMs for Image Classification [6.550471260627169]
  Large Language Models (LLMs) are increasingly being merged with Visual Language Models (VLMs) to enable new capabilities. We show that, for object and scene recognition, VLMs that do not leverage LLMs can achieve better performance than VLMs that do. We propose a pragmatic solution: a lightweight fix involving a relatively small LLM that efficiently routes visual tasks to the most suitable model for the task.
  arXiv  Detail & Related papers  (2024-10-03T23:40:21Z)
• Learning to Localize Objects Improves Spatial Reasoning in Visual-LLMs [38.02017186215372]
  Integration of Large Language Models (LLMs) into visual domain tasks, resulting in visual-LLMs (V-LLMs), has enabled exceptional performance in vision-language tasks. However, existing V-LLMs demonstrate weak spatial reasoning and localization awareness. We explore how image-space coordinate based instruction fine-tuning objectives could inject spatial awareness into V-LLMs.
  arXiv  Detail & Related papers  (2024-04-11T03:09:34Z)
• Less is More: High-value Data Selection for Visual Instruction Tuning [127.38740043393527]
  We propose a high-value data selection approach TIVE, to eliminate redundancy within the visual instruction data and reduce the training cost. Our approach using only about 15% data can achieve comparable average performance to the full-data fine-tuned model across eight benchmarks.
  arXiv  Detail & Related papers  (2024-03-14T16:47:25Z)
• Finer: Investigating and Enhancing Fine-Grained Visual Concept Recognition in Large Vision Language Models [57.95366341738857]
  In-depth analyses show that instruction-tuned LVLMs exhibit modality gap, showing discrepancy when given textual and visual inputs that correspond to the same concept.<n>We propose a multiple attribute-centric evaluation benchmark, Finer, to evaluate LVLMs' fine-grained visual comprehension ability and provide significantly improved explainability.
  arXiv  Detail & Related papers  (2024-02-26T05:43:51Z)
• Good Questions Help Zero-Shot Image Reasoning [110.1671684828904]
  Question-Driven Visual Exploration (QVix) is a novel prompting strategy that enhances the exploratory capabilities of large vision-language models (LVLMs) QVix enables a wider exploration of visual scenes, improving the LVLMs' reasoning accuracy and depth in tasks such as visual question answering and visual entailment. Our evaluations on various challenging zero-shot vision-language benchmarks, including ScienceQA and fine-grained visual classification, demonstrate that QVix significantly outperforms existing methods.
  arXiv  Detail & Related papers  (2023-12-04T03:18:51Z)
• VIPHY: Probing "Visible" Physical Commonsense Knowledge [22.00069189468524]
  Vision-language models (VLMs) have shown remarkable performance on visual reasoning tasks. We evaluate their ability to acquire "visible" physical knowledge. Our results indicate a severe gap between model and human performance.
  arXiv  Detail & Related papers  (2022-09-15T02:06:25Z)
• Towards Learning a Generic Agent for Vision-and-Language Navigation via Pre-training [150.35927365127176]
  We present the first pre-training and fine-tuning paradigm for vision-and-language navigation (VLN) tasks. By training on a large amount of image-text-action triplets in a self-supervised learning manner, the pre-trained model provides generic representations of visual environments and language instructions. It learns more effectively in new tasks and generalizes better in a previously unseen environment.
  arXiv  Detail & Related papers  (2020-02-25T03:08:12Z)

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.