Enhancing Cognition and Explainability of Multimodal Foundation Models with Self-Synthesized Data

• URL: http://arxiv.org/abs/2502.14044v1
• Date: Wed, 19 Feb 2025 19:05:45 GMT
• Title: Enhancing Cognition and Explainability of Multimodal Foundation Models with Self-Synthesized Data
• Authors: Yucheng Shi, Quanzheng Li, Jin Sun, Xiang Li, Ninghao Liu,
• Abstract summary: We propose a novel visual rejection sampling framework to improve the cognition and explainability of LMMs using self-synthesized data. Our approach begins by synthesizing interpretable answers that include human-verifiable visual features. After each round of fine-tuning, we apply a reward model-free filtering mechanism to select the highest-quality interpretable answers.
• Score: 35.229595049396245
• License:
• Abstract: Large multimodal models (LMMs) have shown impressive capabilities in a wide range of visual tasks. However, they often struggle with fine-grained visual reasoning, failing to identify domain-specific objectives and provide justifiable explanations for their predictions. To address this, we propose a novel visual rejection sampling framework to improve the cognition and explainability of LMMs using self-synthesized data. Specifically, visual fine-tuning requires images, queries, and target answers. Our approach begins by synthesizing interpretable answers that include human-verifiable visual features. These features are based on expert-defined concepts, carefully selected based on their alignment with the image content. After each round of fine-tuning, we apply a reward model-free filtering mechanism to select the highest-quality interpretable answers for the next round of tuning. This iterative process of data synthesis and fine-tuning progressively improves the model's ability to generate accurate and reasonable explanations. Experimental results demonstrate the effectiveness of our method in improving both the accuracy and explainability of specialized visual classification tasks.

Related papers

• Modeling the Human Visual System: Comparative Insights from Response-Optimized and Task-Optimized Vision Models, Language Models, and different Readout Mechanisms [1.515687944002438]
  We show that response-optimized models with visual inputs offer superior prediction accuracy for early to mid-level visual areas. We identify three distinct regions in the visual cortex that are sensitive to perceptual features of the input that are not captured by linguistic descriptions. We propose a novel scheme that modulates receptive fields and feature maps based on semantic content, resulting in an accuracy boost of 3-23% over existing SOTAs.
  arXiv  Detail & Related papers  (2024-10-17T21:11:13Z)
• Auto Cherry-Picker: Learning from High-quality Generative Data Driven by Language [41.40908753726324]
  Diffusion models can generate realistic and diverse images, potentially facilitating data availability for data-intensive perception tasks. We present textbfAuto textbfCherry-textbfPicker (ACP), a novel framework that generates high-quality cross-modality training samples.
  arXiv  Detail & Related papers  (2024-06-28T17:53:18Z)
• Enhancing Large Vision Language Models with Self-Training on Image Comprehension [131.14381425260706]
  We introduce Self-Training on Image (STIC), which emphasizes a self-training approach specifically for image comprehension. First, the model self-constructs a preference for image descriptions using unlabeled images. To further self-improve reasoning on the extracted visual information, we let the model reuse a small portion of existing instruction-tuning data.
  arXiv  Detail & Related papers  (2024-05-30T05:53:49Z)
• Calibrated Self-Rewarding Vision Language Models [27.686545023186852]
  Large Vision-Language Models (LVLMs) have made substantial progress by integrating pre-trained large language models (LLMs) and vision models through instruction tuning. LVLMs often exhibit the hallucination phenomenon, where generated text responses appear linguistically plausible but contradict the input image. We propose the Calibrated Self-Rewarding (CSR) approach, which enables the model to self-improve by iteratively generating candidate responses, evaluating the reward for each response, and curating preference data for fine-tuning.
  arXiv  Detail & Related papers  (2024-05-23T14:30:33Z)
• Diffexplainer: Towards Cross-modal Global Explanations with Diffusion Models [51.21351775178525]
  DiffExplainer is a novel framework that, leveraging language-vision models, enables multimodal global explainability. It employs diffusion models conditioned on optimized text prompts, synthesizing images that maximize class outputs. The analysis of generated visual descriptions allows for automatic identification of biases and spurious features.
  arXiv  Detail & Related papers  (2024-04-03T10:11:22Z)
• Multi-modal Auto-regressive Modeling via Visual Words [96.25078866446053]
  We propose the concept of visual tokens, which maps the visual features to probability distributions over Large Multi-modal Models' vocabulary. We further explore the distribution of visual features in the semantic space within LMM and the possibility of using text embeddings to represent visual information.
  arXiv  Detail & Related papers  (2024-03-12T14:58:52Z)
• StableLLaVA: Enhanced Visual Instruction Tuning with Synthesized Image-Dialogue Data [129.92449761766025]
  We propose a novel data collection methodology that synchronously synthesizes images and dialogues for visual instruction tuning. This approach harnesses the power of generative models, marrying the abilities of ChatGPT and text-to-image generative models. Our research includes comprehensive experiments conducted on various datasets.
  arXiv  Detail & Related papers  (2023-08-20T12:43:52Z)
• Perception Visualization: Seeing Through the Eyes of a DNN [5.9557391359320375]
  We develop a new form of explanation that is radically different in nature from current explanation methods, such as Grad-CAM. Perception visualization provides a visual representation of what the DNN perceives in the input image by depicting what visual patterns the latent representation corresponds to. Results of our user study demonstrate that humans can better understand and predict the system's decisions when perception visualizations are available.
  arXiv  Detail & Related papers  (2022-04-21T07:18:55Z)
• Generative Counterfactuals for Neural Networks via Attribute-Informed Perturbation [51.29486247405601]
  We design a framework to generate counterfactuals for raw data instances with the proposed Attribute-Informed Perturbation (AIP) By utilizing generative models conditioned with different attributes, counterfactuals with desired labels can be obtained effectively and efficiently. Experimental results on real-world texts and images demonstrate the effectiveness, sample quality as well as efficiency of our designed framework.
  arXiv  Detail & Related papers  (2021-01-18T08:37:13Z)
• Interpretable Detail-Fidelity Attention Network for Single Image Super-Resolution [89.1947690981471]
  We propose a purposeful and interpretable detail-fidelity attention network to progressively process smoothes and details in divide-and-conquer manner. Particularly, we propose a Hessian filtering for interpretable feature representation which is high-profile for detail inference. Experiments demonstrate that the proposed methods achieve superior performances over the state-of-the-art methods.
  arXiv  Detail & Related papers  (2020-09-28T08:31:23Z)

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.