Efficient ViTs

ViT: Vision Transformer

Follow this topic Ask about this topic

Momentum

20 papers in the last four weeks, up 300% on the four weeks before. 0.2% of all new papers.

Jul 13Week of Sep 28

Latest papers 152

All topics

LUMA: Benchmarking Segmentation via a Lightweight Universal Mask Adapter
Jul 1, 2026Tobias Christian Nauen, Anosh Billimoria, Federico Raue +3Efficient ViTs Semantic Segmentation
RPTU University Kaiserslautern-Landau, Kaiserslautern, Germany · German Research Center for Artificial Intelligence (DFKI), Kaiserslautern, Germany
FlexViT: A Flexible FPGA-based Accelerator for Edge Vision Transformers
Jun 30, 2026Hubert Dymarkowski, Xingjian Fu, Rappy Saha +2Hybrid CNN-Transformer Architectures Edge Inference
School of Computing Science, University of Glasgow, Scotland, UK
REDI: Corpus Aware Patch Ranking for DINOv3 Token Reduction
Jun 30, 2026Chanjong Im, Sebastian Diem, Thomas MandlEfficient ViTs Visual Token Pruning
University of Magdeburg · University of Hildesheim
RenderFormer++: Scalable and Physically Grounded Feed-Forward Neural Rendering
Jun 29, 2026Huangsheng Du, Haoran Zhu, Youcheng Cai +2Neural Rendering Efficient ViTs
University of Science and Technology of China, China
TuringViT: Making SOTA Vision Transformers Accessible to All
Jun 23, 2026Qiman Wu, Hanlin Chen, Lyujie Chen +19Vision Foundation Models Vision Transformer
Foundation Model Team, Xpeng Inc.
FrequencyFormer: A Co-Designed Sensor-to-Processor Pipeline for Frequency-Domain Vision Transformer Inference
Jun 17, 2026Chengwei Zhou, Ovishake Sen, Xuming Chen +5Edge Inference Efficient ViTs
Case Western Reserve University, USA · University of Florida, USA · New Jersey Institute of Technology, USA
Dyna-DINO: Efficient ViT Distillation Via Adaptive Representation Anchoring
Jun 17, 2026Jiaqi Zhang, Ashton Lee, Anthony Wong +3Efficient ViTs Curriculum Learning
Brown University · Rice University
RegimeVGGT: Layer-Wise Spatially Preserving Redundancy Removal for Visual Geometry Grounded Transformer
Jun 16, 2026Jinhao You, Shuo Lyu, Zhuohang Lyu +53D ViTs Multi-View 3D Reconstruction
University of Pennsylvania · University of California, Irvine · Nanyang Technological University +1
RT-Counter: Real-Time Text-Guided Open-Vocabulary Object Counting
Jun 16, 2026Hao-Yuan Ma, Li Zhang, Zhiwei Zhu +1Object Counting Efficient ViTs
School of Computer Science and Technology, Soochow University Suzhou, China
EdgeZSAD: Practical Zero-Shot Anomaly Detection on Edge Devices
Jun 15, 2026Taewan Cho, Andrew Jaeyong ChoiEdge Inference Industrial Anomaly Detection
1Gachon University · 2Plaid Labs Inc.
ViT-FREE: Efficient Face Recognition via Early Exiting and Synthetic Adaptation
Jun 10, 2026Tahar Chettaoui, Guray Ozgur, Eduarda Caldeira +2Inference-Time Optimization Efficient ViTs
Fraunhofer Institute for Computer Graphics Research IGD, Germany · Department of Computer Science, TU Darmstadt, Germany
Spatial Priors via Space Filling Curves for Small and Limited Data Vision Transformers
Jun 8, 2026Leyla Naz Candogan, Arshia Afzal, Pol Puigdemont +1Vision Transformer Efficient ViTs
LIONS, École Polytechnique Fédérale de Lausanne (EPFL), Lausanne, Switzerland.
Beyond Self-Attention: Sub-Quadratic Vision Transformers for Fast Image Captioning
Jun 7, 2026Chiradeep Ghosh, Dakshina Ranjan KiskuImage Captioning Vision Transformer
Department of Computer Science and Engineering · National Institute of Technology Durgapur · Durgapur, India
NGram-MoSE: Efficient Remote Sensing Super-Resolution via N-Gram Context and Mixture-of-Experts
Jun 7, 2026Yun-Hsuan Huang, Trong-An Bui, Chih-Hung ChuangOOD Generalization Remote Sensing Image Super-Resolution
Institute of Aerospace and Systems Engineering, National Taipei University of Technology, Taipei City, Taiwan.
RAPID: Layer-Wise Redundancy-Aware Pruning and Importance-Driven Token Merging for Efficient ViT
Jun 6, 2026Kyumin Choi, Ikbeom JangVision Transformer Efficient ViTs
Hankuk University of Foreign Studies Seoul, South Korea
ATT-CR: Adaptive Triangular Transformer for Cloud Removal
Jun 4, 2026Yang Wu, Ye Deng, Pengna Li +4Remote Sensing Transformer Attention
Xi’an Jiaotong University, Xi’an, Shaanxi 710049, China · School of Computing and Artificial Intelligence, Southwestern University of Finance and Economics, Chengdu, Sichuan 611130, China · Ningbo University of Technology, Ningbo, Zhejiang 315211, China
UtVAA: Ultra-tiny Vision Transformer with Affix Attention for Mobile Image Classification
Jun 2, 2026Romiyal George, Sathiyamohan Nishankar, Selvarajah Thuseethan +1Vision Transformer Edge Inference
University of Peradeniya, Sri Lanka · Charles Darwin University, Australia
Efficient Transformer-Based Localized Patch Sampling for Choroid Plexus Segmentation in Multiple Sclerosis
Jun 2, 2026Po-Jui Lu, Alessandro Cagol, Mario Ocampo-Pineda +12Efficient ViTs Magnetic Resonance Imaging
Translational Imaging in Neurology (ThINk) Basel, Department of Biomedical Engineering, Faculty of Medicine, University Hospital Basel and University of Basel, Basel, Switzerland · Department of Neurology, University Hospital Basel, Basel, Switzerland · Research Center for Clinical Neuroimmunology and Neuroscience Basel (RC2NB), University Hospital Basel and University of Basel, Basel, Switzerland +4
PSViT: A Methodology for Structurally Pruning Spiking Vision Transformers
Jun 2, 2026Rachmad Vidya Wicaksana Putra, Achyuta Muthuvelan, Alberto Marchisio +1Efficient ViTs Spiking Neural Networks
eBRAIN Lab, Division of Engineering, New York University (NYU) Abu Dhabi, United Arab Emirates (UAE)
LALE: Lightweight-Transformer Architecture for Land-Cover Estimation
Jun 1, 2026Ümit Mert Çağlar, Alptekin TemizelRemote Sensing Image Segmentation Hybrid CNN-Transformer Architectures
Graduate School of Informatics, METU, Ankara, Turkey
hZACH-ViT: Curved Latent Geometry for Compact Vision Transformers in Low-Data Medical Imaging
May 30, 2026Athanasios AngelakisGeometric Representation Learning Efficient ViTs
BioML Lab, Research Institute CODE, UniBw, Munich, Germany · Department of Epidemiology and Data Science, Amsterdam UMC, Amsterdam, Netherlands
Scaling Parallel Sequence Models to Foundation-Scale Vision Encoders
May 30, 2026Yitong Jiang, Hongjun Wang, Collin McCarthy +15GPU Kernel Optimization Vision Foundation Models
NVIDIA · The Chinese University of Hong Kong · The University of Hong Kong +1
FSM-Net: An Efficient Frequency-Spatial Network for Real-World Deblurring
May 29, 2026Vinh-Thuan LyImage Deblurring Frequency-Domain Image Processing
University of Science, VNU-HCM, Ho Chi Minh City, Vietnam · Vietnam National University, Ho Chi Minh City, Vietnam
SwInception -- Local Attention Meets Convolutions
May 28, 2026David Hagerman, Roman Naeem, Jakob Lindqvist +3Hybrid CNN-Transformer Architectures Efficient ViTs
Chalmers University of technology, 412 96 Gothenburg, Sweden · Zenseact, Lindholmspiren 2, 417 56 Gothenburg, Sweden
Accelerating HEVC Intra Partitioning via a CNN-Hierarchical Attention Transformer Hybrid
May 27, 2026Krishna Kumar Sharma, Somdyuti PaulEfficient Neural Network Inference Hybrid CNN-Transformer Architectures
Department of Artificial Intelligence, Indian Institute of Technology Kharagpur, Kharagpur, West Bengal 721302, India
Recursive Vision Transformer with Dynamic Depth and Width Adjustment for Resource-Efficient Image Semantic Communication
May 27, 2026Zhilong Zhang, Xinhui Zhang, Gongyu Jin +3Dynamic Neural Networks Semantic Communication
Beijing Laboratory of Advanced Information Network, and the Beijing Key Laboratory of Network System Architecture and Convergence, Beijing University of Posts and Telecommunications, Beijing 100876, China
Dual-branch Distilled Transformer for Efficient Asymmetric UAV Tracking
May 27, 2026Hongtao Yang, Bineng Zhong, Qihua Liang +4Visual Object Tracking Efficient ViTs
Key Lab of Education Blockchain and Intelligent Technology, Ministry of Education, Guangxi Normal University, Guilin, 541004, China · Guangxi Key Lab of Multi-Source Information Mining and Security, Guangxi Normal University, Guilin, 541004, China · Nanjing University of Science and Technology +1
JetViT: Efficient High-Resolution Vision Transformer with Post-Training Attention Search
May 26, 2026Dongyun Zou, Zhuoyang Zhang, Junyu Chen +8Efficient Transformer Inference Vision Foundation Models
MIT · NVIDIA · University of Pennsylvania +1
AdaMerge: Salience-Aware Adaptive Token Merging for Training-Free Acceleration of Vision Transformers
May 26, 2026Semi Lee, Hyejin Go, Hyesong ChoiToken Merging Self-Attention
Electronic Engineering · Soongsil University · Seoul, South Korea
Event-to-Video Reconstruction using Spatio-Temporal and Frequency-Enhanced Deep Neural Networks
May 25, 2026Ramna Maqsood, Paulo Nunes, Luís Ducla Soares +1Event-Based Vision Vision Transformer
Instituto de Telecomunicações, Instituto Universitário de Lisboa (ISCTE-IUL) Lisbon, Portugal · Instituto de Telecomunicac¸˜oes, Instituto Universit´ario de Lisboa (ISCTE-IUL) Lisbon, Portugal

Jul 1, 2026, cs.CVJ/K move · Enter open · S save

LUMA: Benchmarking Segmentation via a Lightweight Universal Mask Adapter

Tobias Christian Nauen, Anosh Billimoria, Federico Raue, Stanislav Frolov+2

RPTU University Kaiserslautern-Landau, Kaiserslautern, Germany · German Research Center for Artificial Intelligence (DFKI), Kaiserslautern, Germany

Efficient ViTs Semantic Segmentation

Open paper AskPDF arXiv

Comparing transformer backbones for image segmentation is confounded: each is paired with a different decoder, recipe, and pretraining, so reported differences rarely reflect the backbone itself. We introduce the Lightweight Universal Mask Adapter (LUMA), a lightweight, backbone-agnostic mask-transformer head that treats any backbone as a black-box feature extractor, letting a set of queries read from its features through cheap cross-attention. LUMA matches the accuracy of EoMT, the state-of-the-art efficient ViT-segmenter, at lower cost, while attaching unchanged to isotropic, hierarchical, convolutional, and mixture-of-experts backbones alike. Holding this head fixed, we benchmark 20 backbones, 11 pretraining schemes and a range of resolutions on ADE20K and Cityscapes under one modern recipe. We find that ``efficient'' token mixers fail to deliver efficiency even at the high resolutions that motivate them, with plain ViT holding the throughput Pareto-front at every resolution. Additionally, the pretraining objective, not the architecture, the lever the field has tuned hardest, governs segmentation quality.

Momentum

Related topics

Latest papers 152