FlexTok: Resampling Images into 1D Token Sequences of Flexible Length

• URL: http://arxiv.org/abs/2502.13967v1
• Date: Wed, 19 Feb 2025 18:59:44 GMT
• Title: FlexTok: Resampling Images into 1D Token Sequences of Flexible Length
• Authors: Roman Bachmann, Jesse Allardice, David Mizrahi, Enrico Fini, Oğuzhan Fatih Kar, Elmira Amirloo, Alaaeldin El-Nouby, Amir Zamir, Afshin Dehghan,
• Abstract summary: We introduce FlexTok, a tokenizer that projects 2D images into variable-length, ordered 1D token sequences.<n>We evaluate our approach in an autoregressive generation setting using a simple GPT-style Transformer.
• Score: 16.76602756308683
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: Image tokenization has enabled major advances in autoregressive image generation by providing compressed, discrete representations that are more efficient to process than raw pixels. While traditional approaches use 2D grid tokenization, recent methods like TiTok have shown that 1D tokenization can achieve high generation quality by eliminating grid redundancies. However, these methods typically use a fixed number of tokens and thus cannot adapt to an image's inherent complexity. We introduce FlexTok, a tokenizer that projects 2D images into variable-length, ordered 1D token sequences. For example, a 256x256 image can be resampled into anywhere from 1 to 256 discrete tokens, hierarchically and semantically compressing its information. By training a rectified flow model as the decoder and using nested dropout, FlexTok produces plausible reconstructions regardless of the chosen token sequence length. We evaluate our approach in an autoregressive generation setting using a simple GPT-style Transformer. On ImageNet, this approach achieves an FID<2 across 8 to 128 tokens, outperforming TiTok and matching state-of-the-art methods with far fewer tokens. We further extend the model to support to text-conditioned image generation and examine how FlexTok relates to traditional 2D tokenization. A key finding is that FlexTok enables next-token prediction to describe images in a coarse-to-fine "visual vocabulary", and that the number of tokens to generate depends on the complexity of the generation task.

Related papers

• Token-Shuffle: Towards High-Resolution Image Generation with Autoregressive Models [92.18057318458528]
  Token-Shuffle is a novel method that reduces the number of image tokens in Transformer. Our strategy requires no additional pretrained text-encoder and enables MLLMs to support extremely high-resolution image synthesis. In GenAI-benchmark, our 2.7B model achieves 0.77 overall score on hard prompts, outperforming AR models LlamaGen by 0.18 and diffusion models LDM by 0.15.
  arXiv  Detail & Related papers  (2025-04-24T17:59:56Z)
• Improving Autoregressive Image Generation through Coarse-to-Fine Token Prediction [4.900334213807624]
  We show how to enjoy the benefits of large codebooks without making autoregressive modeling more difficult. Our framework consists of two stages: (1) an autoregressive model that sequentially predicts coarse labels for each token in the sequence, and (2) an auxiliary model that simultaneously predicts fine-grained labels for all tokens conditioned on their coarse labels.
  arXiv  Detail & Related papers  (2025-03-20T14:41:29Z)
• FlowTok: Flowing Seamlessly Across Text and Image Tokens [20.629139911638646]
  FlowTok is a framework that seamlessly flows across text and images by encoding images into a compact 1D token representation. It reduces the latent space size by 3.3x at an image resolution of 256, eliminating the need for complex conditioning mechanisms or noise scheduling. With its streamlined architecture centered around compact 1D tokens, FlowTok is highly memory-efficient, requires significantly fewer training resources, and achieves much faster sampling speeds-all while delivering performance comparable to state-of-the-art models.
  arXiv  Detail & Related papers  (2025-03-13T18:06:13Z)
• Spectral Image Tokenizer [21.84385276311364]
  Image tokenizers map images to sequences of discrete tokens.<n>We propose to tokenize the image spectrum instead, obtained from a discrete wavelet transform (DWT)<n>We evaluate the tokenizer metrics as multiscale image generation, text-guided image upsampling and editing.
  arXiv  Detail & Related papers  (2024-12-12T18:59:31Z)
• Language-Guided Image Tokenization for Generation [63.0859685332583]
  TexTok is a simple yet effective tokenization framework that leverages language to provide high-level semantics.<n>By conditioning the tokenization process on descriptive text captions, TexTok allows the tokenization process to focus on encoding fine-grained visual details into latent tokens.<n>TexTok with a vanilla DiT generator achieves state-of-the-art FID scores of 1.46 and 1.62 on ImageNet-256 and -512 respectively.
  arXiv  Detail & Related papers  (2024-12-08T03:18:17Z)
• Adaptive Length Image Tokenization via Recurrent Allocation [81.10081670396956]
  Current vision systems assign fixed-length representations to images, regardless of the information content. Inspired by this, we propose an approach to learn variable-length token representations for 2D images.
  arXiv  Detail & Related papers  (2024-11-04T18:58:01Z)
• ElasticTok: Adaptive Tokenization for Image and Video [109.75935878130582]
  We introduce ElasticTok, a method that conditions on prior frames to adaptively encode a frame into a variable number of tokens. During inference, ElasticTok can dynamically allocate tokens when needed. Our evaluations on images and video demonstrate the effectiveness of our approach in efficient token usage.
  arXiv  Detail & Related papers  (2024-10-10T20:54:15Z)
• ImageFolder: Autoregressive Image Generation with Folded Tokens [51.815319504939396]
  Increasing token length is a common approach to improve the image reconstruction quality.<n>There exists a trade-off between reconstruction and generation quality regarding token length.<n>We propose Image, a semantic tokenizer that provides spatially aligned image tokens that can be folded during autoregressive modeling.
  arXiv  Detail & Related papers  (2024-10-02T17:06:39Z)
• An Image is Worth 32 Tokens for Reconstruction and Generation [54.24414696392026]
  Transformer-based 1-Dimensional Tokenizer (TiTok) is an innovative approach that tokenizes images into 1D latent sequences. TiTok achieves competitive performance to state-of-the-art approaches. Our best-performing variant can significantly surpasses DiT-XL/2 (gFID 2.13 vs. 3.04) while still generating high-quality samples 74x faster.
  arXiv  Detail & Related papers  (2024-06-11T17:59:56Z)
• A Layer-Wise Tokens-to-Token Transformer Network for Improved Historical Document Image Enhancement [13.27528507177775]
  We propose textbfT2T-BinFormer which is a novel document binarization encoder-decoder architecture based on a Tokens-to-token vision transformer. Experiments on various DIBCO and H-DIBCO benchmarks demonstrate that the proposed model outperforms the existing CNN and ViT-based state-of-the-art methods.
  arXiv  Detail & Related papers  (2023-12-06T23:01:11Z)

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.