Importance-Based Token Merging for Efficient Image and Video Generation

• URL: http://arxiv.org/abs/2411.16720v2
• Date: Thu, 24 Apr 2025 21:37:00 GMT
• Title: Importance-Based Token Merging for Efficient Image and Video Generation
• Authors: Haoyu Wu, Jingyi Xu, Hieu Le, Dimitris Samaras,
• Abstract summary: We show that preserving high-information tokens during merging significantly improves sample quality.<n>We propose an importance-based token merging method that prioritizes the most critical tokens in computational resource allocation.
• Score: 41.94334394794811
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: Token merging can effectively accelerate various vision systems by processing groups of similar tokens only once and sharing the results across them. However, existing token grouping methods are often ad hoc and random, disregarding the actual content of the samples. We show that preserving high-information tokens during merging - those essential for semantic fidelity and structural details - significantly improves sample quality, producing finer details and more coherent, realistic generations. Despite being simple and intuitive, this approach remains underexplored. To do so, we propose an importance-based token merging method that prioritizes the most critical tokens in computational resource allocation, leveraging readily available importance scores, such as those from classifier-free guidance in diffusion models. Experiments show that our approach significantly outperforms baseline methods across multiple applications, including text-to-image synthesis, multi-view image generation, and video generation with various model architectures such as Stable Diffusion, Zero123++, AnimateDiff, or PixArt-$\alpha$.

Related papers

• UniToken: Harmonizing Multimodal Understanding and Generation through Unified Visual Encoding [84.87802580670579]
  We introduce UniToken, an auto-regressive generation model that encodes visual inputs through a combination of discrete and continuous representations. Our unified visual encoding framework captures both high-level semantics and low-level details, delivering multidimensional information.
  arXiv  Detail & Related papers  (2025-04-06T09:20:49Z)
• Bridging Continuous and Discrete Tokens for Autoregressive Visual Generation [63.89280381800457]
  We propose TokenBridge, which maintains the strong representation capacity of continuous tokens while preserving the modeling simplicity of discrete tokens. We introduce a dimension-wise quantization strategy that independently discretizes each feature dimension, paired with a lightweight autoregressive prediction mechanism. Our approach achieves reconstruction and generation quality on par with continuous methods while using standard categorical prediction.
  arXiv  Detail & Related papers  (2025-03-20T17:59:59Z)
• "Principal Components" Enable A New Language of Images [79.45806370905775]
  We introduce a novel visual tokenization framework that embeds a provable PCA-like structure into the latent token space. Our approach achieves state-of-the-art reconstruction performance and enables better interpretability to align with the human vision system.
  arXiv  Detail & Related papers  (2025-03-11T17:59:41Z)
• Video Token Merging for Long-form Video Understanding [17.59960070514554]
  We propose a learnable video token merging algorithm that dynamically merges tokens based on their saliency. Our approach significantly reduces memory costs by 84% and boosts throughput by approximately 6.89 times compared to baseline algorithms.
  arXiv  Detail & Related papers  (2024-10-31T09:55:32Z)
• Meissonic: Revitalizing Masked Generative Transformers for Efficient High-Resolution Text-to-Image Synthesis [62.06970466554273]
  We present Meissonic, which non-autoregressive masked image modeling (MIM) text-to-image elevates to a level comparable with state-of-the-art diffusion models like SDXL. We leverage high-quality training data, integrate micro-conditions informed by human preference scores, and employ feature compression layers to further enhance image fidelity and resolution. Our model not only matches but often exceeds the performance of existing models like SDXL in generating high-quality, high-resolution images.
  arXiv  Detail & Related papers  (2024-10-10T17:59:17Z)
• Token-level Correlation-guided Compression for Efficient Multimodal Document Understanding [54.532578213126065]
  Most document understanding methods preserve all tokens within sub-images and treat them equally. This neglects their different informativeness and leads to a significant increase in the number of image tokens. We propose Token-level Correlation-guided Compression, a parameter-free and plug-and-play methodology to optimize token processing.
  arXiv  Detail & Related papers  (2024-07-19T16:11:15Z)
• Enhancing Semantic Fidelity in Text-to-Image Synthesis: Attention Regulation in Diffusion Models [23.786473791344395]
  Cross-attention layers in diffusion models tend to disproportionately focus on certain tokens during the generation process. We introduce attention regulation, an on-the-fly optimization approach at inference time to align attention maps with the input text prompt. Experiment results show that our method consistently outperforms other baselines.
  arXiv  Detail & Related papers  (2024-03-11T02:18:27Z)
• Subobject-level Image Tokenization [60.80949852899857]
  Patch-based image tokenization ignores the morphology of the visual world. Inspired by subword tokenization, we introduce subobject-level adaptive token segmentation. We show that subobject tokenization enables faster convergence and better generalization while using fewer visual tokens.
  arXiv  Detail & Related papers  (2024-02-22T06:47:44Z)
• Faster Diffusion: Rethinking the Role of the Encoder for Diffusion Model Inference [95.42299246592756]
  We study the UNet encoder and empirically analyze the encoder features. We find that encoder features change minimally, whereas the decoder features exhibit substantial variations across different time-steps. We validate our approach on other tasks: text-to-video, personalized generation and reference-guided generation.
  arXiv  Detail & Related papers  (2023-12-15T08:46:43Z)
• Token Fusion: Bridging the Gap between Token Pruning and Token Merging [71.84591084401458]
  Vision Transformers (ViTs) have emerged as powerful backbones in computer vision, outperforming many traditional CNNs. computational overhead, largely attributed to the self-attention mechanism, makes deployment on resource-constrained edge devices challenging. We introduce "Token Fusion" (ToFu), a method that amalgamates the benefits of both token pruning and token merging.
  arXiv  Detail & Related papers  (2023-12-02T04:29:19Z)
• Closed-Loop Transcription via Convolutional Sparse Coding [29.75613581643052]
  Autoencoders often use generic deep networks as the encoder or decoder, which are difficult to interpret. In this work, we make the explicit assumption that the image distribution is generated from a multistage convolution sparse coding (CSC) Our method enjoys several side benefits, including more structured and interpretable representations, more stable convergence, and scalability to large datasets.
  arXiv  Detail & Related papers  (2023-02-18T14:40:07Z)
• TokenMixup: Efficient Attention-guided Token-level Data Augmentation for Transformers [8.099977107670917]
  TokenMixup is an efficient attention-guided token-level data augmentation method. A variant of TokenMixup mixes tokens within a single instance, thereby enabling multi-scale feature augmentation. Experiments show that our methods significantly improve the baseline models' performance on CIFAR and ImageNet-1K.
  arXiv  Detail & Related papers  (2022-10-14T06:36:31Z)
• ClusTR: Exploring Efficient Self-attention via Clustering for Vision Transformers [70.76313507550684]
  We propose a content-based sparse attention method, as an alternative to dense self-attention. Specifically, we cluster and then aggregate key and value tokens, as a content-based method of reducing the total token count. The resulting clustered-token sequence retains the semantic diversity of the original signal, but can be processed at a lower computational cost.
  arXiv  Detail & Related papers  (2022-08-28T04:18:27Z)
• Generating Annotated High-Fidelity Images Containing Multiple Coherent Objects [10.783993190686132]
  We propose a multi-object generation framework that can synthesize images with multiple objects without explicitly requiring contextual information. We demonstrate how coherency and fidelity are preserved with our method through experiments on the Multi-MNIST and CLEVR datasets.
  arXiv  Detail & Related papers  (2020-06-22T11:33:55Z)

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.