Unveiling Encoder-Free Vision-Language Models

• URL: http://arxiv.org/abs/2406.11832v2
• Date: Tue, 29 Oct 2024 06:44:36 GMT
• Title: Unveiling Encoder-Free Vision-Language Models
• Authors: Haiwen Diao, Yufeng Cui, Xiaotong Li, Yueze Wang, Huchuan Lu, Xinlong Wang,
• Abstract summary: Existing vision-language models (VLMs) mostly rely on vision encoders to extract visual features followed by large language models (LLMs) for visual-language tasks. We bridge the gap between encoder-based and encoder-free models, and present a simple yet effective training recipe towards pure VLMs. We launch EVE, an encoder-free vision-language model that can be trained and forwarded efficiently.
• Score: 62.52803514667452
• License:
• Abstract: Existing vision-language models (VLMs) mostly rely on vision encoders to extract visual features followed by large language models (LLMs) for visual-language tasks. However, the vision encoders set a strong inductive bias in abstracting visual representation, e.g., resolution, aspect ratio, and semantic priors, which could impede the flexibility and efficiency of the VLMs. Training pure VLMs that accept the seamless vision and language inputs, i.e., without vision encoders, remains challenging and rarely explored. Empirical observations reveal that direct training without encoders results in slow convergence and large performance gaps. In this work, we bridge the gap between encoder-based and encoder-free models, and present a simple yet effective training recipe towards pure VLMs. Specifically, we unveil the key aspects of training encoder-free VLMs efficiently via thorough experiments: (1) Bridging vision-language representation inside one unified decoder; (2) Enhancing visual recognition capability via extra supervision. With these strategies, we launch EVE, an encoder-free vision-language model that can be trained and forwarded efficiently. Notably, solely utilizing 35M publicly accessible data, EVE can impressively rival the encoder-based VLMs of similar capacities across multiple vision-language benchmarks. It significantly outperforms the counterpart Fuyu-8B with mysterious training procedures and undisclosed training data. We believe that EVE provides a transparent and efficient route for developing a pure decoder-only architecture across modalities. Our code and models are publicly available at: https://github.com/baaivision/EVE.

Related papers

• Learning to Ground VLMs without Forgetting [54.033346088090674]
  We introduce LynX, a framework that equips pretrained Visual Language Models with visual grounding ability without forgetting their existing image and language understanding skills. To train the model effectively, we generate a high-quality synthetic dataset we call SCouT, which mimics human reasoning in visual grounding. We evaluate LynX on several object detection and visual grounding datasets, demonstrating strong performance in object detection, zero-shot localization and grounded reasoning.
  arXiv  Detail & Related papers  (2024-10-14T13:35:47Z)
• Response Wide Shut: Surprising Observations in Basic Vision Language Model Capabilities [30.176918208200604]
  Vision-Language Models (VLMs) have emerged as general purpose tools for addressing a variety of complex computer vision problems. These models have been shown to be highly capable, but also lacking some basic visual understanding skills. This paper sets out to understand the limitations of SoTA VLMs on fundamental visual tasks.
  arXiv  Detail & Related papers  (2024-08-13T08:26:32Z)
• Imperfect Vision Encoders: Efficient and Robust Tuning for Vision-Language Models [26.88977803220915]
  We propose an efficient and robust method for updating vision encoders within vision language models. Our approach selectively and locally updates encoders, leading to substantial performance improvements on data where previous mistakes occurred.
  arXiv  Detail & Related papers  (2024-07-23T14:39:40Z)
• Memory-Space Visual Prompting for Efficient Vision-Language Fine-Tuning [59.13366859237086]
  Current solutions for efficiently constructing large vision-language (VL) models follow a two-step paradigm. We consider visual prompts as additional knowledge that facilitates language models in addressing tasks associated with visual information. We introduce a novel approach, wherein visual prompts are memoryd with the weights of FFN for visual knowledge injection.
  arXiv  Detail & Related papers  (2024-05-09T08:23:20Z)
• EVE: Efficient Vision-Language Pre-training with Masked Prediction and Modality-Aware MoE [66.48689706116808]
  Efficient Vision-languagE is one unified multimodal Transformer pre-trained solely by one unified pre-training task. Eve encodes both vision and language within a shared Transformer network integrated with modality-aware sparse Mixture-of-Experts. Eve achieves state-of-the-art performance on various vision-language downstream tasks, including visual question answering, visual reasoning, and image-text retrieval.
  arXiv  Detail & Related papers  (2023-08-23T07:36:30Z)
• VisionLLM: Large Language Model is also an Open-Ended Decoder for Vision-Centric Tasks [81.32968995346775]
  VisionLLM is a framework for vision-centric tasks that can be flexibly defined and managed using language instructions. Our model can achieve over 60% mAP on COCO, on par with detection-specific models.
  arXiv  Detail & Related papers  (2023-05-18T17:59:42Z)
• Multimodal Adaptive Distillation for Leveraging Unimodal Encoders for Vision-Language Tasks [118.49566068398642]
  Cross-modal encoders for vision-language (VL) tasks are often pretrained with carefully curated vision-language datasets. Unimodal encoders are pretrained with simpler annotations that are less cost-prohibitive, achieving scales of hundreds of millions to billions. We propose Multimodal Adaptive Distillation (MAD), which adaptively distills useful knowledge from pretrained encoders to cross-modal VL encoders.
  arXiv  Detail & Related papers  (2022-04-22T04:41:04Z)
• VLMo: Unified Vision-Language Pre-Training with Mixture-of-Modality-Experts [46.55920956687346]
  We present a unified Vision-Language pretrained Model (VLMo) that jointly learns a dual encoder and a fusion encoder with a modular Transformer network. Because of the modeling flexibility of MoME, pretrained VLMo can be fine-tuned as a fusion encoder for vision-language classification tasks. We propose a stagewise pre-training strategy, which effectively leverages large-scale image-only and text-only data besides image-text pairs.
  arXiv  Detail & Related papers  (2021-11-03T17:20:36Z)

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.