TG-LLaVA: Text Guided LLaVA via Learnable Latent Embeddings

• URL: http://arxiv.org/abs/2409.09564v2
• Date: Fri, 20 Sep 2024 14:51:18 GMT
• Title: TG-LLaVA: Text Guided LLaVA via Learnable Latent Embeddings
• Authors: Dawei Yan, Pengcheng Li, Yang Li, Hao Chen, Qingguo Chen, Weihua Luo, Wei Dong, Qingsen Yan, Haokui Zhang, Chunhua Shen,
• Abstract summary: We propose Text Guided LLaVA (TG-LLaVA) to optimize vision-language models (VLMs) We use learnable latent embeddings as a bridge to analyze textual instruction and add the analysis results to the vision encoder as guidance. With the guidance of text, the vision encoder can extract text-related features, similar to how humans focus on the most relevant parts of an image when considering a question.
• Score: 61.9257731511557
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: Currently, inspired by the success of vision-language models (VLMs), an increasing number of researchers are focusing on improving VLMs and have achieved promising results. However, most existing methods concentrate on optimizing the connector and enhancing the language model component, while neglecting improvements to the vision encoder itself. In contrast, we propose Text Guided LLaVA (TG-LLaVA) in this paper, which optimizes VLMs by guiding the vision encoder with text, offering a new and orthogonal optimization direction. Specifically, inspired by the purpose-driven logic inherent in human behavior, we use learnable latent embeddings as a bridge to analyze textual instruction and add the analysis results to the vision encoder as guidance, refining it. Subsequently, another set of latent embeddings extracts additional detailed text-guided information from high-resolution local patches as auxiliary information. Finally, with the guidance of text, the vision encoder can extract text-related features, similar to how humans focus on the most relevant parts of an image when considering a question. This results in generating better answers. Experiments on various datasets validate the effectiveness of the proposed method. Remarkably, without the need for additional training data, our propsoed method can bring more benefits to the baseline (LLaVA-1.5) compared with other concurrent methods. Furthermore, the proposed method consistently brings improvement in different settings.

Related papers

• Fine-Grained Verifiers: Preference Modeling as Next-token Prediction in Vision-Language Alignment [57.0121616203175]
  We propose FiSAO, a novel self-alignment method that utilizes the model's own visual encoder as a fine-grained verifier to improve vision-language alignment. By leveraging token-level feedback from the vision encoder, FiSAO significantly improves vision-language alignment, even surpassing traditional preference tuning methods that require additional data.
  arXiv  Detail & Related papers  (2024-10-18T03:34:32Z)
• Instruction Tuning-free Visual Token Complement for Multimodal LLMs [51.138806401996696]
  multimodal large language models (MLLMs) have promised an elegant bridge between vision and language. We propose a Visual Token Complement framework (VTC) that helps MLLMs regain the missing visual features. Our VTC integrates text-to-image generation as a guide to identifying the text-irrelevant features, and a visual selector is then developed to generate complementary visual tokens.
  arXiv  Detail & Related papers  (2024-08-09T12:13:01Z)
• Exploring the Zero-Shot Capabilities of Vision-Language Models for Improving Gaze Following [10.91834567383105]
  Contextual cues related to a person's pose and interactions with objects can provide valuable information for gaze following. We evaluate Vision-Language Models (VLMs) for extracting a wide array of contextual cues to improve gaze following performance. Using the entire image along with an ellipse drawn around the target person is the most effective strategy for visual prompting.
  arXiv  Detail & Related papers  (2024-06-06T09:41:39Z)
• 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)
• Enhancing Visual Document Understanding with Contrastive Learning in Large Visual-Language Models [56.76307866160105]
  We propose a contrastive learning framework, termed Document Object COntrastive learning (DoCo) DoCo leverages an auxiliary multimodal encoder to obtain the features of document objects and align them to the visual features generated by the vision encoder of Large Visual-Language Models (LVLMs) We demonstrate that the proposed DoCo serves as a plug-and-play pre-training method, which can be employed in the pre-training of various LVLMs without inducing any increase in computational complexity during the inference process.
  arXiv  Detail & Related papers  (2024-02-29T10:17:27Z)
• IPAD: Iterative, Parallel, and Diffusion-based Network for Scene Text Recognition [5.525052547053668]
  Scene text recognition has attracted more and more attention due to its diverse applications. Most state-of-the-art methods adopt an encoder-decoder framework with the attention mechanism, autoregressively generating text from left to right. We propose an alternative solution, using a parallel and iterative decoder that adopts an easy-first decoding strategy.
  arXiv  Detail & Related papers  (2023-12-19T08:03:19Z)
• ZEN 2.0: Continue Training and Adaption for N-gram Enhanced Text Encoders [32.53471313532653]
  We propose to pre-train n-gram-enhanced encoders with a large volume of data and advanced techniques for training. New state-of-the-art performance is observed from a long list of NLP tasks across languages and domains.
  arXiv  Detail & Related papers  (2021-05-04T04:08:58Z)
• TEACHTEXT: CrossModal Generalized Distillation for Text-Video Retrieval [103.85002875155551]
  We propose a novel generalized distillation method, TeachText, for exploiting large-scale language pretraining. We extend our method to video side modalities and show that we can effectively reduce the number of used modalities at test time. Our approach advances the state of the art on several video retrieval benchmarks by a significant margin and adds no computational overhead at test time.
  arXiv  Detail & Related papers  (2021-04-16T17:55:28Z)

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.