VisualRWKV: Exploring Recurrent Neural Networks for Visual Language Models

• URL: http://arxiv.org/abs/2406.13362v1
• Date: Wed, 19 Jun 2024 09:07:31 GMT
• Title: VisualRWKV: Exploring Recurrent Neural Networks for Visual Language Models
• Authors: Haowen Hou, Peigen Zeng, Fei Ma, Fei Richard Yu,
• Abstract summary: We introduce VisualRWKV, the first application of a linear RNN model to multimodal learning tasks. We propose a data-dependent recurrence and sandwich prompts to enhance our modeling capabilities. VisualRWKV achieves competitive performance compared to Transformer-based models like LLaVA-1.5 on various benchmarks.
• Score: 10.272476734387977
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: Visual Language Models (VLMs) have rapidly progressed with the recent success of large language models. However, there have been few attempts to incorporate efficient linear Recurrent Neural Networks (RNNs) architectures into VLMs. In this study, we introduce VisualRWKV, the first application of a linear RNN model to multimodal learning tasks, leveraging the pre-trained RWKV language model. We propose a data-dependent recurrence and sandwich prompts to enhance our modeling capabilities, along with a 2D image scanning mechanism to enrich the processing of visual sequences. Extensive experiments demonstrate that VisualRWKV achieves competitive performance compared to Transformer-based models like LLaVA-1.5 on various benchmarks. To facilitate further research and analysis, we have made the checkpoints and the associated code publicly accessible at the following GitHub repository: \href{https://github.com/howard-hou/VisualRWKV}{https://github.com/howard-hou/VisualRWKV}.

Related papers

• Renaissance: Investigating the Pretraining of Vision-Language Encoders [0.6445605125467574]
  We seek to answer several questions related to the pretraining of vision-language encoders through meta-analysis. In our first set of experiments, we show that we can save significant compute at no cost to downstream performance, by freezing large parts of vision-language models during pretraining. In our second set of experiments we examine the effect of basing a VL transformer on a vision model versus a text model.
  arXiv  Detail & Related papers  (2024-11-11T01:44:54Z)
• Qwen2-VL: Enhancing Vision-Language Model's Perception of the World at Any Resolution [82.38677987249348]
  We present the Qwen2-VL Series, which redefines the conventional predetermined-resolution approach in visual processing. Qwen2-VL introduces the Naive Dynamic Resolution mechanism, which enables the model to dynamically process images of varying resolutions into different numbers of visual tokens. The model also integrates Multimodal Rotary Position Embedding (M-RoPE), facilitating the effective fusion of positional information across text, images, and videos.
  arXiv  Detail & Related papers  (2024-09-18T17:59:32Z)
• Advancing Vietnamese Visual Question Answering with Transformer and Convolutional Integration [0.40964539027092917]
  This study aims to bridge the gap by conducting experiments on the Vietnamese Visual Question Answering dataset. We have developed a model that enhances image representation capabilities, thereby improving overall performance in the ViVQA system. Our experimental findings demonstrate that our model surpasses competing baselines, achieving promising performance.
  arXiv  Detail & Related papers  (2024-07-30T22:32:50Z)
• RWKV-CLIP: A Robust Vision-Language Representation Learner [31.501759213619646]
  Contrastive Language-Image Pre-training (CLIP) has significantly improved performance in various vision-language tasks. We introduce a diverse description generation framework that can leverage Large Language Models (LLMs) to synthesize and refine content from web-based texts, synthetic captions, and detection tags. We propose RWKV-CLIP, the first RWKV-driven vision-language representation learning model that combines the effective parallel training of transformers with the efficient inference of RNNs.
  arXiv  Detail & Related papers  (2024-06-11T06:10:46Z)
• Visual Delta Generator with Large Multi-modal Models for Semi-supervised Composed Image Retrieval [50.72924579220149]
  Composed Image Retrieval (CIR) is a task that retrieves images similar to a query, based on a provided textual modification. Current techniques rely on supervised learning for CIR models using labeled triplets of the reference image, text, target image. We propose a new semi-supervised CIR approach where we search for a reference and its related target images in auxiliary data.
  arXiv  Detail & Related papers  (2024-04-23T21:00:22Z)
• Multimodal Learned Sparse Retrieval with Probabilistic Expansion Control [66.78146440275093]
  Learned retrieval (LSR) is a family of neural methods that encode queries and documents into sparse lexical vectors. We explore the application of LSR to the multi-modal domain, with a focus on text-image retrieval. Current approaches like LexLIP and STAIR require complex multi-step training on massive datasets. Our proposed approach efficiently transforms dense vectors from a frozen dense model into sparse lexical vectors.
  arXiv  Detail & Related papers  (2024-02-27T14:21:56Z)
• Divert More Attention to Vision-Language Object Tracking [87.31882921111048]
  We argue that the lack of large-scale vision-language annotated videos and ineffective vision-language interaction learning motivate us to design more effective vision-language representation for tracking. Particularly, in this paper, we first propose a general attribute annotation strategy to decorate videos in six popular tracking benchmarks, which contributes a large-scale vision-language tracking database with more than 23,000 videos. We then introduce a novel framework to improve tracking by learning a unified-adaptive VL representation, where the cores are the proposed asymmetric architecture search and modality mixer (ModaMixer)
  arXiv  Detail & Related papers  (2023-07-19T15:22:06Z)
• Enabling Multimodal Generation on CLIP via Vision-Language Knowledge Distillation [79.72299298976525]
  We propose to augment a vision-language pre-training model with a textual pre-trained language model (PLM) via vision-language knowledge distillation (VLKD) Experiments show that the resulting model has strong zero-shot performance on multimodal generation tasks, such as open-ended visual question answering and image captioning. The original textual language understanding and generation ability of the PLM is maintained after VLKD, which makes our model versatile for both multimodal and unimodal tasks.
  arXiv  Detail & Related papers  (2022-03-12T09:33:37Z)
• Few Shot Activity Recognition Using Variational Inference [9.371378627575883]
  We propose a novel variational inference based architectural framework (HF-AR) for few shot activity recognition. Our framework leverages volume-preserving Householder Flow to learn a flexible posterior distribution of the novel classes. This results in better performance as compared to state-of-the-art few shot approaches for human activity recognition.
  arXiv  Detail & Related papers  (2021-08-20T03:57:58Z)
• WenLan: Bridging Vision and Language by Large-Scale Multi-Modal Pre-Training [71.37731379031487]
  We propose a two-tower pre-training model called BriVL within the cross-modal contrastive learning framework. Unlike OpenAI CLIP that adopts a simple contrastive learning method, we devise a more advanced algorithm by adapting the latest method MoCo into the cross-modal scenario. By building a large queue-based dictionary, our BriVL can incorporate more negative samples in limited GPU resources.
  arXiv  Detail & Related papers  (2021-03-11T09:39:49Z)
• A Convolutional Deep Markov Model for Unsupervised Speech Representation Learning [32.59760685342343]
  Probabilistic Latent Variable Models provide an alternative to self-supervised learning approaches for linguistic representation learning from speech. In this work, we propose ConvDMM, a Gaussian state-space model with non-linear emission and transition functions modelled by deep neural networks. When trained on a large scale speech dataset (LibriSpeech), ConvDMM produces features that significantly outperform multiple self-supervised feature extracting methods.
  arXiv  Detail & Related papers  (2020-06-03T21:50:20Z)

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.