Related papers: Lossless Token Merging Even Without Fine-Tuning in…
Recent token reduction methods for Vision Transformers (ViTs) incorporate token merging, which measures the similarities between token embeddings and combines the most similar pairs. However, their merging policies are directly dependent on…
Token merging has emerged as a new paradigm that can accelerate the inference of Vision Transformers (ViTs) without any retraining or fine-tuning. To push the frontier of training-free acceleration in ViTs, we improve token merging by…
The quadratic cost of self-attention in Vision Transformers (ViTs) constitutes a fundamental bottleneck for practical deployment, motivating a vibrant line of research on token reduction. Among existing approaches, token merging (ToMe) has…
Large-scale transformers are central to modern semantic communication, yet their high computational and communication costs hinder deployment on resource-constrained edge devices. This paper introduces a training-free framework for adaptive…
We introduce Token Merging (ToMe), a simple method to increase the throughput of existing ViT models without needing to train. ToMe gradually combines similar tokens in a transformer using a general and light-weight matching algorithm that…
Self-attention and transformers have been widely used in deep learning. Recent efforts have been devoted to incorporating transformer blocks into different neural architectures, including those with convolutions, leading to various visual…
This work presents Adaptive Local-then-Global Merging (ALGM), a token reduction method for semantic segmentation networks that use plain Vision Transformers. ALGM merges tokens in two stages: (1) In the first network layer, it merges…
Vision transformers have been widely explored in various vision tasks. Due to heavy computational cost, much interest has aroused for compressing vision transformer dynamically in the aspect of tokens. Current methods mainly pay attention…
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 visual encoders,…
Decreasing sequence length is a common way to accelerate transformers, but prior token reduction work often targets classification and reports proxy metrics rather than end-to-end latency. For semantic segmentation, token reduction is…
Large-scale transformer models have emerged as a powerful tool for semantic communication systems, enabling edge devices to extract rich representations for robust inference across noisy wireless channels. However, their substantial…
Multimodal Large Language Models (MLLMs) have demonstrated substantial value in unified text-image understanding and reasoning, primarily by converting images into sequences of patch-level tokens that align with their architectural…
While vision transformers have achieved impressive results, effectively and efficiently accelerating these models can further boost performances. In this work, we propose a dense/sparse training framework to obtain a unified model, enabling…
Model merging has emerged as a cost-efficient approximation to multitask learning. Among merging strategies, task arithmetic is notable for its simplicity and effectiveness. In this work, we provide a theoretical motivation for task vectors…
Token compression is essential for reducing the computational and memory requirements of transformer models, enabling their deployment in resource-constrained environments. In this work, we propose an efficient and hardware-compatible token…
Video transformer models require huge amounts of compute resources due to the spatio-temporal scaling of the input. Tackling this, recent methods have proposed to drop or merge tokens for image models, whether randomly or via learned…
Since its inception, Vision Transformer (ViT) has emerged as a prevalent model in the computer vision domain. Nonetheless, the multi-head self-attention (MHSA) mechanism in ViT is computationally expensive due to its calculation of…
Vision transformers have achieved significant improvements on various vision tasks but their quadratic interactions between tokens significantly reduce computational efficiency. Many pruning methods have been proposed to remove redundant…
Vision transformer has emerged as a new paradigm in computer vision, showing excellent performance while accompanied by expensive computational cost. Image token pruning is one of the main approaches for ViT compression, due to the facts…
Diffusion models have emerged as a promising approach for generating high-quality, high-dimensional images. Nevertheless, these models are hindered by their high computational cost and slow inference, partly due to the quadratic…