SweetTokenizer: Semantic-Aware Spatial-Temporal Tokenizer for Compact Visual Discretization

• URL: http://arxiv.org/abs/2412.10443v2
• Date: Tue, 17 Dec 2024 03:55:34 GMT
• Title: SweetTokenizer: Semantic-Aware Spatial-Temporal Tokenizer for Compact Visual Discretization
• Authors: Zhentao Tan, Ben Xue, Jian Jia, Junhao Wang, Wencai Ye, Shaoyun Shi, Mingjie Sun, Wenjin Wu, Quan Chen, Peng Jiang,
• Abstract summary: SweetTokenizer (SweetTokenizer) is a compact yet effective discretization approach for vision data. Our goal is to boost tokenizers' compression ratio while maintaining reconstruction fidelity in the VQ-VAE paradigm.
• Score: 20.109136454526233
• License:
• Abstract: This paper presents the \textbf{S}emantic-a\textbf{W}ar\textbf{E} spatial-t\textbf{E}mporal \textbf{T}okenizer (SweetTokenizer), a compact yet effective discretization approach for vision data. Our goal is to boost tokenizers' compression ratio while maintaining reconstruction fidelity in the VQ-VAE paradigm. Firstly, to obtain compact latent representations, we decouple images or videos into spatial-temporal dimensions, translating visual information into learnable querying spatial and temporal tokens through a \textbf{C}ross-attention \textbf{Q}uery \textbf{A}uto\textbf{E}ncoder (CQAE). Secondly, to complement visual information during compression, we quantize these tokens via a specialized codebook derived from off-the-shelf LLM embeddings to leverage the rich semantics from language modality. Finally, to enhance training stability and convergence, we also introduce a curriculum learning strategy, which proves critical for effective discrete visual representation learning. SweetTokenizer achieves comparable video reconstruction fidelity with only \textbf{25\%} of the tokens used in previous state-of-the-art video tokenizers, and boost video generation results by \textbf{32.9\%} w.r.t gFVD. When using the same token number, we significantly improves video and image reconstruction results by \textbf{57.1\%} w.r.t rFVD on UCF-101 and \textbf{37.2\%} w.r.t rFID on ImageNet-1K. Additionally, the compressed tokens are imbued with semantic information, enabling few-shot recognition capabilities powered by LLMs in downstream applications.

Related papers

• Incorporating Feature Pyramid Tokenization and Open Vocabulary Semantic Segmentation [8.659766913542938]
  We study a united perceptual and semantic token compression for all granular understanding. We propose Feature Pyramid Tokenization (PAT) to cluster and represent multi-resolution feature by learnable codebooks. Our experiments show that PAT enhances the semantic intuition of VLM feature pyramid.
  arXiv  Detail & Related papers  (2024-12-18T18:43:21Z)
• SparseVLM: Visual Token Sparsification for Efficient Vision-Language Model Inference [45.11612407862277]
  In vision-language models (VLMs), visual tokens usually bear a significant amount of computational overhead despite sparsity of information in them when compared to text tokens. We propose a text-guided training-free token optimization mechanism dubbed SparseVLM that eliminates the need of extra parameters or fine-tuning costs.
  arXiv  Detail & Related papers  (2024-10-06T09:18:04Z)
• VideoLLM-MoD: Efficient Video-Language Streaming with Mixture-of-Depths Vision Computation [66.00245701441547]
  We introduce a novel approach to reduce vision compute by leveraging redundant vision tokens "skipping layers" rather than decreasing the number of vision tokens. Our method, VideoLLM-MoD, is inspired by mixture-of-depths LLMs and addresses the challenge of numerous vision tokens in long-term or streaming video.
  arXiv  Detail & Related papers  (2024-08-29T17:21:58Z)
• VoCo-LLaMA: Towards Vision Compression with Large Language Models [56.20788367278211]
  Vision-Language Models (VLMs) have achieved remarkable success in various multi-modal tasks, but they are often bottlenecked by the limited context window. We propose VoCo-LLaMA, the first approach to compress vision tokens using LLMs. Our method achieves minimal performance loss with a compression ratio of 576$times$, resulting in up to 94.8$%$ fewer FLOPs and 69.6$%$ acceleration in inference time.
  arXiv  Detail & Related papers  (2024-06-18T05:05:12Z)
• OmniTokenizer: A Joint Image-Video Tokenizer for Visual Generation [95.29102596532854]
  Tokenizer serves as a translator to map the intricate visual data into a compact latent space. This paper presents OmniTokenizer, a transformer-based tokenizer for joint image and video tokenization.
  arXiv  Detail & Related papers  (2024-06-13T17:59:26Z)
• Understanding the Effect of using Semantically Meaningful Tokens for Visual Representation Learning [41.81009725976217]
  We provide semantically-meaningful visual tokens to transformer encoders within a vision-language pre-training framework. We demonstrate notable improvements over ViTs in learned representation quality across text-to-image and image-to-text retrieval tasks.
  arXiv  Detail & Related papers  (2024-05-26T01:46:22Z)
• Tokenize Anything via Prompting [65.93061853439512]
  We present a unified, promptable model capable of simultaneously segmenting, recognizing, and captioning anything. We train a generalizable model with massive segmentation masks, eg, SA-1B masks, and semantic priors from a pre-trained CLIP model with 5 billion parameters. We believe this model can be a versatile region-level image tokenizer, capable of encoding general-purpose region context.
  arXiv  Detail & Related papers  (2023-12-14T17:01:02Z)
• CenterCLIP: Token Clustering for Efficient Text-Video Retrieval [67.21528544724546]
  In CLIP, the essential visual tokenization process, which produces discrete visual token sequences, generates many homogeneous tokens due to the redundancy nature of consecutive frames in videos. This significantly increases computation costs and hinders the deployment of video retrieval models in web applications. In this paper, we design a multi-segment token clustering algorithm to find the most representative tokens and drop the non-essential ones.
  arXiv  Detail & Related papers  (2022-05-02T12:02:09Z)
• VIMPAC: Video Pre-Training via Masked Token Prediction and Contrastive Learning [82.09856883441044]
  Video understanding relies on perceiving the global content modeling its internal connections. We propose a block-wise strategy where we mask neighboring video tokens in both spatial and temporal domains. We also add an augmentation-free contrastive learning method to further capture global content.
  arXiv  Detail & Related papers  (2021-06-21T16:48:19Z)

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.