English
Related papers

Related papers: Elastic ViTs from Pretrained Models without Retrai…

200 papers

We introduce A-ViT, a method that adaptively adjusts the inference cost of vision transformer (ViT) for images of different complexity. A-ViT achieves this by automatically reducing the number of tokens in vision transformers that are…

Computer Vision and Pattern Recognition · Computer Science 2022-10-10 Hongxu Yin , Arash Vahdat , Jose Alvarez , Arun Mallya , Jan Kautz , Pavlo Molchanov

Visual AutoRegressive (VAR) models based on next-scale prediction enable efficient hierarchical generation, yet the inference cost grows quadratically at high resolutions. We observe that the computationally intensive later scales…

Computer Vision and Pattern Recognition · Computer Science 2026-03-03 Keli Liu , Zhendong Wang , Wengang Zhou , Houqiang Li

Recurrent neural networks (RNNs) are central to sequence modeling tasks, yet their high computational complexity poses challenges for scalability and real-time deployment. Traditional pruning techniques, predominantly based on weight…

Neurons and Cognition · Quantitative Biology 2025-02-26 Rakesh Sengupta

Structured pruning is an effective approach for compressing large pre-trained neural networks without significantly affecting their performance. However, most current structured pruning methods do not provide any performance guarantees, and…

Machine Learning · Computer Science 2023-02-14 Marwa El Halabi , Suraj Srinivas , Simon Lacoste-Julien

Neural network pruning with suitable retraining can yield networks with considerably fewer parameters than the original with comparable degrees of accuracy. Typical pruning methods require large, fully trained networks as a starting point…

Machine Learning · Computer Science 2020-10-13 Timothy Foldy-Porto , Yeshwanth Venkatesha , Priyadarshini Panda

Vision Transformer (ViT), a radically different architecture than convolutional neural networks offers multiple advantages including design simplicity, robustness and state-of-the-art performance on many vision tasks. However, in contrast…

Computer Vision and Pattern Recognition · Computer Science 2022-10-14 Hanan Gani , Muzammal Naseer , Mohammad Yaqub

Masked image modeling (MIM) pre-training for large-scale vision transformers (ViTs) has enabled promising downstream performance on top of the learned self-supervised ViT features. In this paper, we question if the \textit{extremely simple}…

Computer Vision and Pattern Recognition · Computer Science 2024-05-28 Jin Gao , Shubo Lin , Shaoru Wang , Yutong Kou , Zeming Li , Liang Li , Congxuan Zhang , Xiaoqin Zhang , Yizheng Wang , Weiming Hu

Compressing neural networks without retraining is vital for deployment at scale. We study calibration-free compression through the lens of projection geometry: structured pruning is an axis-aligned projection, whereas model folding performs…

Machine Learning · Computer Science 2026-02-23 Olga Saukh , Dong Wang , Haris Šikić , Yun Cheng , Lothar Thiele

We present a neat yet effective recursive operation on vision transformers that can improve parameter utilization without involving additional parameters. This is achieved by sharing weights across the depth of transformer networks. The…

Computer Vision and Pattern Recognition · Computer Science 2022-07-27 Zhiqiang Shen , Zechun Liu , Eric Xing

Recently, efficient Vision Transformers have shown great performance with low latency on resource-constrained devices. Conventionally, they use 4x4 patch embeddings and a 4-stage structure at the macro level, while utilizing sophisticated…

Computer Vision and Pattern Recognition · Computer Science 2024-03-29 Seokju Yun , Youngmin Ro

Despite the success of transformers on various computer vision tasks, they suffer from excessive memory and computational cost. Some works present dynamic vision transformers to accelerate inference by pruning redundant tokens. A key to…

Computer Vision and Pattern Recognition · Computer Science 2023-10-27 Fengyuan Shi , Limin Wang

The rapid development of large-scale deep learning models questions the affordability of hardware platforms, which necessitates the pruning to reduce their computational and memory footprints. Sparse neural networks as the product, have…

Computer Vision and Pattern Recognition · Computer Science 2024-09-09 Can Jin , Tianjin Huang , Yihua Zhang , Mykola Pechenizkiy , Sijia Liu , Shiwei Liu , Tianlong Chen

Attention is sparse in vision transformers. We observe the final prediction in vision transformers is only based on a subset of most informative tokens, which is sufficient for accurate image recognition. Based on this observation, we…

Computer Vision and Pattern Recognition · Computer Science 2021-10-27 Yongming Rao , Wenliang Zhao , Benlin Liu , Jiwen Lu , Jie Zhou , Cho-Jui Hsieh

We introduce JetViT, a novel family of hybrid-architecture Vision Transformer (ViT) models that match the accuracy of state-of-the-art full-attention vision foundation models while achieving substantially higher inference efficiency on…

Computer Vision and Pattern Recognition · Computer Science 2026-05-27 Dongyun Zou , Zhuoyang Zhang , Junyu Chen , Wenkun He , Qinhe Peng , Hanrong Ye , Yao Lu , Hongxu Yin , Yu Wang , Song Han , Han Cai

Vision Transformers (ViTs), extensively pre-trained on large-scale datasets, have become essential to foundation models, allowing excellent performance on diverse downstream tasks with minimal adaptation. Consequently, there is growing…

Computer Vision and Pattern Recognition · Computer Science 2025-03-04 Lixu Wang , Bingqi Shang , Yi Li , Payal Mohapatra , Wei Dong , Xiao Wang , Qi Zhu

Vision Transformers (ViTs) deliver state-of-the-art accuracy but their quadratic attention cost and redundant computations severely hinder deployment on latency and resource-constrained platforms. Existing pruning approaches treat either…

Computer Vision and Pattern Recognition · Computer Science 2025-12-24 Mohammad Helal Uddin , Liam Seymour , Sabur Baidya

We present STAT: a simple algorithm to prune transformer models without any fine-tuning. STAT eliminates both attention heads and neurons from the network, while preserving accuracy by calculating a correction to the weights of the next…

Machine Learning · Computer Science 2024-06-04 Megan Flynn , Alexander Wang , Dean Edward Alvarez , Christopher De Sa , Anil Damle

Deep Learning models have become the dominant approach in several areas due to their high performance. Unfortunately, the size and hence computational requirements of operating such models can be considerably high. Therefore, this…

Computer Vision and Pattern Recognition · Computer Science 2019-12-04 Abdullah Salama , Oleksiy Ostapenko , Tassilo Klein , Moin Nabi

Adapting pre-trained neural models to downstream tasks has become the standard practice for obtaining high-quality models. In this work, we propose a novel model adaptation paradigm, adapting by pruning, which prunes neural connections in…

Machine Learning · Computer Science 2021-05-10 Yang Gao , Nicolo Colombo , Wei Wang

This study introduces a novel supervised learning approach for spiking neural networks that does not rely on traditional backpropagation. Instead, it employs spike-timing-dependent plasticity (STDP) within a supervised framework for image…

Computer Vision and Pattern Recognition · Computer Science 2025-02-13 Wei Xie