English
Related papers

Related papers: Co-Me: Confidence-Guided Token Merging for Visual …

200 papers

Vision Transformers (ViTs) have achieved remarkable success in various computer vision tasks. However, ViTs have a huge computational cost due to their inherent reliance on multi-head self-attention (MHSA), prompting efforts to accelerate…

Computer Vision and Pattern Recognition · Computer Science 2024-12-24 Seungdong Yoa , Seungjun Lee , Hyeseung Cho , Bumsoo Kim , Woohyung Lim

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…

Machine Learning · Computer Science 2025-11-17 Omar Erak , Omar Alhussein , Hatem Abou-Zeid , Mehdi Bennis

Diffusion Transformer (DiT) has driven significant progress in image generation tasks. However, DiT inferencing is notoriously compute-intensive and incurs long latency even on datacenter-scale GPUs, primarily due to its iterative nature…

Hardware Architecture · Computer Science 2025-04-14 Daeun Kim , Jinwoo Hwang , Changhun Oh , Jongse Park

Video large language models (LLMs) achieve strong video understanding by leveraging a large number of spatio-temporal tokens, but suffer from quadratic computational scaling with token count. To address this, we propose a training-free…

Computer Vision and Pattern Recognition · Computer Science 2025-07-11 Jeongseok Hyun , Sukjun Hwang , Su Ho Han , Taeoh Kim , Inwoong Lee , Dongyoon Wee , Joon-Young Lee , Seon Joo Kim , Minho Shim

Infrared and visible image fusion aims to integrate comprehensive information from multiple sources to achieve superior performances on various practical tasks, such as detection, over that of a single modality. However, most existing…

Computer Vision and Pattern Recognition · Computer Science 2023-03-24 Yiming Sun , Bing Cao , Pengfei Zhu , Qinghua Hu

Masked Autoencoder (MAE) has demonstrated superior performance on various vision tasks via randomly masking image patches and reconstruction. However, effective data augmentation strategies for MAE still remain open questions, different…

Computer Vision and Pattern Recognition · Computer Science 2024-02-08 Kai Chen , Zhili Liu , Lanqing Hong , Hang Xu , Zhenguo Li , Dit-Yan Yeung

3D change detection from multi-view images is essential for urban monitoring, disaster assessment, and autonomous driving. However, existing methods predominantly operate in the 2D domain, where viewpoint variations are mistaken for…

Computer Vision and Pattern Recognition · Computer Science 2026-05-19 Wei Zhang , Songhua Li , Yihang Wu , Qiang Li , Qi Wang

A method is presented for accelerating inference in transformer language models by exploiting the low effective rank of the token activation manifold at each layer. The method decomposes each activation vector into a subspace component and…

Machine Learning · Computer Science 2026-05-06 Stephen J. Thomas

The cascade of 2D geometric transformations were exploited to model relations between entities in a knowledge graph (KG), leading to an effective KG embedding (KGE) model, CompoundE. Furthermore, the rotation in the 3D space was proposed as…

Artificial Intelligence · Computer Science 2023-04-04 Xiou Ge , Yun-Cheng Wang , Bin Wang , C. -C. Jay Kuo

Large language models like GPT-4 are resource-intensive, but recent advancements suggest that smaller, specialized experts can outperform the monolithic models on specific tasks. The Collaboration-of-Experts (CoE) approach integrates…

Distributed, Parallel, and Cluster Computing · Computer Science 2025-04-11 Jiashun Suo , Xiaojian Liao , Limin Xiao , Li Ruan , Jinquan Wang , Xiao Su , Zhisheng Huo

In this paper, we propose a method using the fusion of CNN and transformer structure to improve image classification performance. In the case of CNN, information about a local area on an image can be extracted well, but there is a limit to…

Computer Vision and Pattern Recognition · Computer Science 2022-08-22 Keong Hun Choi , Jin Woo Kim , Yao Wang , Jong Eun Ha

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 prune tokens based on…

Computer Vision and Pattern Recognition · Computer Science 2025-07-28 Tianyu Fu , Tengxuan Liu , Qinghao Han , Guohao Dai , Shengen Yan , Huazhong Yang , Xuefei Ning , Yu Wang

Coarse-guided visual generation, which synthesizes fine visual samples from degraded or low-fidelity coarse references, is essential for various real-world applications. While training-based approaches are effective, they are inherently…

Computer Vision and Pattern Recognition · Computer Science 2026-03-31 Yanghao Wang , Ziqi Jiang , Zhen Wang , Long Chen

Existing visual change detectors usually adopt CNNs or Transformers for feature representation learning and focus on learning effective representation for the changed regions between images. Although good performance can be obtained by…

Computer Vision and Pattern Recognition · Computer Science 2023-10-18 Bo Jiang , Zitian Wang , Xixi Wang , Ziyan Zhang , Lan Chen , Xiao Wang , Bin Luo

Training deep learning models on limited data while maintaining generalization is one of the fundamental challenges in molecular property prediction. One effective solution is transferring knowledge extracted from abundant datasets to those…

Machine Learning · Computer Science 2024-09-26 Soorin Yim , Dae-Woong Jeong , Sung Moon Ko , Sumin Lee , Hyunseung Kim , Chanhui Lee , Sehui Han

Shifting of objects in an image and merging many images after appropriate shifting is being used in several engineering and scientific applications which require complex perception development. A method has been presented here which could…

Computer Vision and Pattern Recognition · Computer Science 2014-07-31 T. R. Gopalakrishnan Nair , Richa Sharma

Living creatures and machines interact with the world through their morphology and motions. Recent advances in creating bio-inspired morphing robots and machines have led to the study of variable geometry truss (VGT), structures that can…

Artificial Intelligence · Computer Science 2022-11-29 Jianzhe Gu , Lining Yao

Autoregressive (AR) models, long dominant in language generation, are increasingly applied to image synthesis but are often considered less competitive than Diffusion-based models. A primary limitation is the substantial number of image…

Despite recent advances in subquadratic attention mechanisms or state-space models, processing long token sequences still imposes significant computational requirements. Token merging has emerged as a solution to increase computational…

Machine Learning · Computer Science 2025-08-06 Leon Götz , Marcel Kollovieh , Stephan Günnemann , Leo Schwinn

An important feature of kernel mean embeddings (KME) is that the rate of convergence of the empirical KME to the true distribution KME can be bounded independently of the dimension of the space, properties of the distribution and smoothness…

Statistics Theory · Mathematics 2025-04-17 Geoffrey Wolfer , Pierre Alquier