Cognitive Visual-Language Mapper: Advancing Multimodal Comprehension with Enhanced Visual Knowledge Alignment

• URL: http://arxiv.org/abs/2402.13561v2
• Date: Wed, 26 Jun 2024 07:05:21 GMT
• Title: Cognitive Visual-Language Mapper: Advancing Multimodal Comprehension with Enhanced Visual Knowledge Alignment
• Authors: Yunxin Li, Xinyu Chen, Baotian Hu, Haoyuan Shi, Min Zhang,
• Abstract summary: Visual knowledge plays a significant role in analyzing, inferring, and interpreting information from visuals, helping improve the accuracy of answers to knowledge-based visual questions. We present a Cognitive Visual-Language Mapper (CVLM), which contains a pretrained Visual Knowledge Aligner (VKA) and a Fine-grained Knowledge Adapter (FKA) used in the multimodal instruction tuning stage. We conduct extensive experiments on knowledge-based VQA benchmarks and experimental results show that CVLM significantly improves the performance of LMMs on knowledge-based VQA (average gain by 5.0%).
• Score: 31.688373463643373
• License: http://creativecommons.org/licenses/by-nc-nd/4.0/
• Abstract: Evaluating and Rethinking the current landscape of Large Multimodal Models (LMMs), we observe that widely-used visual-language projection approaches (e.g., Q-former or MLP) focus on the alignment of image-text descriptions yet ignore the visual knowledge-dimension alignment, i.e., connecting visuals to their relevant knowledge. Visual knowledge plays a significant role in analyzing, inferring, and interpreting information from visuals, helping improve the accuracy of answers to knowledge-based visual questions. In this paper, we mainly explore improving LMMs with visual-language knowledge alignment, especially aimed at challenging knowledge-based visual question answering (VQA). To this end, we present a Cognitive Visual-Language Mapper (CVLM), which contains a pretrained Visual Knowledge Aligner (VKA) and a Fine-grained Knowledge Adapter (FKA) used in the multimodal instruction tuning stage. Specifically, we design the VKA based on the interaction between a small language model and a visual encoder, training it on collected image-knowledge pairs to achieve visual knowledge acquisition and projection. FKA is employed to distill the fine-grained visual knowledge of an image and inject it into Large Language Models (LLMs). We conduct extensive experiments on knowledge-based VQA benchmarks and experimental results show that CVLM significantly improves the performance of LMMs on knowledge-based VQA (average gain by 5.0%). Ablation studies also verify the effectiveness of VKA and FKA, respectively. The codes are available at https://github.com/HITsz-TMG/Cognitive-Visual-Language-Mapper

Related papers

• Targeted Visual Prompting for Medical Visual Question Answering [3.600327818936722]
  multimodal large language models (MLLMs) have emerged as an alternative to classical model architectures. Simple visual errors cast doubt on the actual visual understanding abilities of these models. This paper introduces targeted visual prompting to equip MLLMs with region-based questioning capabilities.
  arXiv  Detail & Related papers  (2024-08-06T08:58:20Z)
• Rethinking Visual Prompting for Multimodal Large Language Models with External Knowledge [76.45868419402265]
  multimodal large language models (MLLMs) have made significant strides by training on vast high-quality image-text datasets. However, the inherent difficulty in explicitly conveying fine-grained or spatially dense information in text, such as masks, poses a challenge for MLLMs. This paper proposes a new visual prompt approach to integrate fine-grained external knowledge, gleaned from specialized vision models, into MLLMs.
  arXiv  Detail & Related papers  (2024-07-05T17:43:30Z)
• Chain-of-Spot: Interactive Reasoning Improves Large Vision-Language Models [81.71651422951074]
  Chain-of-Spot (CoS) method is a novel approach that enhances feature extraction by focusing on key regions of interest. This technique allows LVLMs to access more detailed visual information without altering the original image resolution. Our empirical findings demonstrate a significant improvement in LVLMs' ability to understand and reason about visual content.
  arXiv  Detail & Related papers  (2024-03-19T17:59:52Z)
• 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)
• A Comprehensive Evaluation of GPT-4V on Knowledge-Intensive Visual Question Answering [53.70661720114377]
  multimodal large models (MLMs) have significantly advanced the field of visual understanding, offering remarkable capabilities in realm of visual question answering (VQA) Yet, the true challenge lies in the domain of knowledge-intensive VQA tasks, which necessitate deep comprehension of the visual information in conjunction with a vast repository of learned knowledge. To uncover such capabilities, we provide an in-depth evaluation from three perspectives: 1) Commonsense Knowledge, which assesses how well models can understand visual cues and connect to general knowledge; 2) Fine-grained World Knowledge, which tests the model's skill in reasoning out specific knowledge from images, showcasing
  arXiv  Detail & Related papers  (2023-11-13T18:22:32Z)
• See, Think, Confirm: Interactive Prompting Between Vision and Language Models for Knowledge-based Visual Reasoning [60.43585179885355]
  We propose a novel framework named Interactive Prompting Visual Reasoner (IPVR) for few-shot knowledge-based visual reasoning. IPVR contains three stages, see, think and confirm. We conduct experiments on a range of knowledge-based visual reasoning datasets.
  arXiv  Detail & Related papers  (2023-01-12T18:59:50Z)
• VLMAE: Vision-Language Masked Autoencoder [21.97700040013084]
  We propose a vision-language masked autoencoder framework (VLMAE) for vision-language pre-training. VLMAE employs visual generative learning, facilitating the model to acquire fine-grained and unbiased features.
  arXiv  Detail & Related papers  (2022-08-19T14:39:18Z)
• Exploring CLIP for Assessing the Look and Feel of Images [87.97623543523858]
  We introduce Contrastive Language-Image Pre-training (CLIP) models for assessing both the quality perception (look) and abstract perception (feel) of images in a zero-shot manner. Our results show that CLIP captures meaningful priors that generalize well to different perceptual assessments.
  arXiv  Detail & Related papers  (2022-07-25T17:58:16Z)
• Reasoning over Vision and Language: Exploring the Benefits of Supplemental Knowledge [59.87823082513752]
  This paper investigates the injection of knowledge from general-purpose knowledge bases (KBs) into vision-and-language transformers. We empirically study the relevance of various KBs to multiple tasks and benchmarks. The technique is model-agnostic and can expand the applicability of any vision-and-language transformer with minimal computational overhead.
  arXiv  Detail & Related papers  (2021-01-15T08:37:55Z)
• KVL-BERT: Knowledge Enhanced Visual-and-Linguistic BERT for Visual Commonsense Reasoning [4.787501955202053]
  In visual commonsense reasoning (VCR) task, a machine must answer correctly and then provide a rationale justifying its answer. We propose a novel Knowledge Enhanced Visual-and-Linguistic BERT (KVL-BERT for short) model. Besides taking visual and linguistic contents as input, external commonsense knowledge extracted from ConceptNet is integrated into the multi-layer Transformer.
  arXiv  Detail & Related papers  (2020-12-13T08:22:33Z)

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.