paper-with-me

홈 › Papers

Importance-Based Token Merging for Efficient Image and Video Generation

2024-11-23 · HaoYu Wu, Jingyi Xu, Hieu Le, Dimitris Samaras

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-$\alpha$.

📄 PDF Abstract BibTeX arXiv:2411.16720

Code (0)

등록된 구현이 없습니다.

Tasks

Image GenerationVideo Generation

Methods 이 논문이 사용한 방법론

Diffusion Diffusion models generate samples by gradually removing noise from a signal, and their training objective can be expressed as a reweighted variational lower-bound…
HOC 설명 없음

Similar Papers 제목 키워드 기반

VidToMe: Video Token Merging for Zero-Shot Video Editing

2023-12-17 · CVPR 2024 1 · Xirui Li, Chao Ma, Xiaokang Yang, Ming-Hsuan Yang

Diffusion models have made significant advances in generating high-quality images, but their application to video generation has remained challenging due to the complexity of temporal motion. Zero-shot video editing offe…

Video EditingVideo Generation

AIM: Adaptive Inference of Multi-Modal LLMs via Token Merging and Pruning

2024-12-04 · Yiwu Zhong, Zhuoming Liu, Yin Li, LiWei Wang

Large language models (LLMs) have enabled the creation of multi-modal LLMs that exhibit strong comprehension of visual data such as images and videos. However, these models usually rely on extensive visual tokens from vi…

Video Understanding

Video Token Merging for Long-form Video Understanding

2024-10-31 · Seon-Ho Lee, Jue Wang, Zhikang Zhang, David Fan 외

As the scale of data and models for video understanding rapidly expand, handling long-form video input in transformer-based models presents a practical challenge. Rather than resorting to input sampling or token dropping…

FormVideo ClassificationVideo Understanding

FrameFusion: Combining Similarity and Importance for Video Token Reduction on Large Visual Language Models

2024-12-30 · Tianyu Fu, Tengxuan Liu, Qinghao Han, Guohao Dai 외

The increasing demand to process long and high-resolution videos significantly burdens Large Vision-Language Models (LVLMs) due to the enormous number of visual tokens. Existing token reduction methods primarily focus on…

Question AnsweringToken ReductionVideo Understanding

Libra-Merging: Importance-redundancy and Pruning-merging Trade-off for Acceleration Plug-in in Large Vision-Language Model

2025-01-01 · CVPR 2025 1 · Longrong Yang, Dong Shen, Chaoxiang Cai, Kaibing Chen 외

Large Vision-Language Models (LVLMs) have achieved significant progress in recent years. However, the expensive inference cost limits the realistic deployment of LVLMs. Some works find that visual tokens are redundan…

Language ModelingLanguage Modelling