Improved Baselines for Data-efficient Perceptual Augmentation of LLMs

• URL: http://arxiv.org/abs/2403.13499v1
• Date: Wed, 20 Mar 2024 10:57:17 GMT
• Title: Improved Baselines for Data-efficient Perceptual Augmentation of LLMs
• Authors: Théophane Vallaeys, Mustafa Shukor, Matthieu Cord, Jakob Verbeek,
• Abstract summary: In computer vision, large language models (LLMs) can be used to prime vision-language tasks such as image captioning and visual question answering. We present an experimental evaluation of different interfacing mechanisms, across multiple tasks. We identify a new interfacing mechanism that yields (near) optimal results across different tasks, while obtaining a 4x reduction in training time.
• Score: 66.05826802808177
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: The abilities of large language models (LLMs) have recently progressed to unprecedented levels, paving the way to novel applications in a wide variety of areas. In computer vision, LLMs can be used to prime vision-language tasks such image captioning and visual question answering when coupled with pre-trained vision backbones. While different approaches have been explored to interface LLMs with ``perceptual backbones'' that process, e.g., visual or audio data, they are often explored for different tasks, different datasets, and using different perceptual backbones and language models, hindering direct comparison of the interfacing mechanisms. To remedy this lack of comparability between methods, we present an extensive experimental evaluation of different interfacing mechanisms, across multiple tasks (including image, video, and audio captioning as well as visual question answering), datasets and backbones, paying special attention to low-data settings. We find improved performance using existing mechanisms over state-of-the-art results, and identify a new interfacing mechanism that yields (near) optimal results across different tasks, while obtaining a 4x reduction in training time.

Related papers

• ADEM-VL: Adaptive and Embedded Fusion for Efficient Vision-Language Tuning [38.26304604660713]
  ADEM-VL is an efficient vision-language method that tunes models based on pretrained large language models. Our framework surpasses existing methods by an average accuracy of 0.77% on ScienceQA dataset.
  arXiv  Detail & Related papers  (2024-10-23T11:31:06Z)
• RA-BLIP: Multimodal Adaptive Retrieval-Augmented Bootstrapping Language-Image Pre-training [55.54020926284334]
  Multimodal Large Language Models (MLLMs) have recently received substantial interest, which shows their emerging potential as general-purpose models for various vision-language tasks. Retrieval augmentation techniques have proven to be effective plugins for both LLMs and MLLMs. In this study, we propose multimodal adaptive Retrieval-Augmented Bootstrapping Language-Image Pre-training (RA-BLIP), a novel retrieval-augmented framework for various MLLMs.
  arXiv  Detail & Related papers  (2024-10-18T03:45:19Z)
• Cambrian-1: A Fully Open, Vision-Centric Exploration of Multimodal LLMs [56.391404083287235]
  We introduce Cambrian-1, a family of multimodal LLMs (MLLMs) designed with a vision-centric approach. Our study uses LLMs and visual instruction tuning as an interface to evaluate various visual representations. We provide model weights, code, supporting tools, datasets, and detailed instruction-tuning and evaluation recipes.
  arXiv  Detail & Related papers  (2024-06-24T17:59:42Z)
• Enhancing Visual-Language Modality Alignment in Large Vision Language Models via Self-Improvement [102.22911097049953]
  SIMA is a framework that enhances visual and language modality alignment through self-improvement. It employs an in-context self-critic mechanism to select response pairs for preference tuning. We demonstrate that SIMA achieves superior modality alignment, outperforming previous approaches.
  arXiv  Detail & Related papers  (2024-05-24T23:09:27Z)
• 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)
• Expanding Frozen Vision-Language Models without Retraining: Towards Improved Robot Perception [0.0]
  Vision-language models (VLMs) have shown powerful capabilities in visual question answering and reasoning tasks. In this paper, we demonstrate a method of aligning the embedding spaces of different modalities to the vision embedding space. We show that using multiple modalities as input improves the VLM's scene understanding and enhances its overall performance in various tasks.
  arXiv  Detail & Related papers  (2023-08-31T06:53:55Z)
• mPLUG: Effective and Efficient Vision-Language Learning by Cross-modal Skip-connections [104.14624185375897]
  mPLUG is a new vision-language foundation model for both cross-modal understanding and generation. It achieves state-of-the-art results on a wide range of vision-language downstream tasks, such as image captioning, image-text retrieval, visual grounding and visual question answering.
  arXiv  Detail & Related papers  (2022-05-24T11:52:06Z)
• Evaluation of Audio-Visual Alignments in Visually Grounded Speech Models [2.1320960069210484]
  This work studies multimodal learning in context of visually grounded speech (VGS) models. We introduce systematic metrics for evaluating model performance in aligning visual objects and spoken words. We show that cross-modal attention helps the model to achieve higher semantic cross-modal retrieval performance.
  arXiv  Detail & Related papers  (2021-07-05T12:54:05Z)

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.