English
Related papers

Related papers: Improving the Behaviour of Vision Transformers wit…

200 papers

Large transformer-based models have made significant progress in generalizable novel view synthesis (NVS) from sparse input views, generating novel viewpoints without the need for test-time optimization. However, these models are…

While the Self-Attention mechanism in the Transformer model has proven to be effective in many domains, we observe that it is less effective in more diverse settings (e.g. multimodality) due to the varying granularity of each token and the…

Computer Vision and Pattern Recognition · Computer Science 2024-06-06 Wayner Barrios , SouYoung Jin

Large language models have demonstrated predictable scaling behaviors with respect to model parameters and training data. This study investigates whether a similar scaling relationship exist for vision-language models with respect to the…

Artificial Intelligence · Computer Science 2025-12-30 Tenghui Li , Guoxu Zhou , Xuyang Zhao , Qibin Zhao

Fine-tuning a pre-trained deep neural network has become a successful paradigm in various machine learning tasks. However, such a paradigm becomes particularly challenging with tabular data when there are discrepancies between the feature…

Machine Learning · Computer Science 2023-10-24 Qi-Le Zhou , Han-Jia Ye , Le-Ye Wang , De-Chuan Zhan

In this paper, we present a new approach for model acceleration by exploiting spatial sparsity in visual data. We observe that the final prediction in vision Transformers is only based on a subset of the most informative tokens, which is…

Computer Vision and Pattern Recognition · Computer Science 2023-06-05 Yongming Rao , Zuyan Liu , Wenliang Zhao , Jie Zhou , Jiwen Lu

Transformers are widely applied to solve natural language understanding and computer vision tasks. While scaling up these architectures leads to improved performance, it often comes at the expense of much higher computational costs. In…

Computer Vision and Pattern Recognition · Computer Science 2022-02-25 Cedric Renggli , André Susano Pinto , Neil Houlsby , Basil Mustafa , Joan Puigcerver , Carlos Riquelme

Many modern applications of the artificial neural networks ensue large number of layers making traditional digital implementations increasingly complex. Optical neural networks offer parallel processing at high bandwidth, but have the…

Neural and Evolutionary Computing · Computer Science 2022-08-24 Egor Manuylovich , Diego Argüello Ron , Morteza Kamalian-Kopae , Sergei Turitsyn

Conventional Vision-Language Models(VLMs) typically utilize a fixed number of vision tokens, regardless of task complexity. This one-size-fits-all strategy introduces notable inefficiencies: using excessive tokens leads to unnecessary…

Computer Vision and Pattern Recognition · Computer Science 2025-04-07 Junshan Hu , Jialiang Mao , Zhikang Liu , Zhongpu Xia , Peng Jia , Xianpeng Lang

Vision Transformers (ViTs) can learn strong image-level representations while their patch representations become less effective for dense prediction during prolonged training. We revisit this dense degradation phenomenon and argue that it…

Computer Vision and Pattern Recognition · Computer Science 2026-05-25 Linxiang Su

Despite the recent success in many applications, the high computational requirements of vision transformers limit their use in resource-constrained settings. While many existing methods improve the quadratic complexity of attention, in most…

Computer Vision and Pattern Recognition · Computer Science 2023-02-28 Dmitrii Marin , Jen-Hao Rick Chang , Anurag Ranjan , Anish Prabhu , Mohammad Rastegari , Oncel Tuzel

Large Vision-Language Models (LVLMs) achieve strong performance on single-image tasks, but their performance declines when multiple images are provided as input. One major reason is the cross-image information leakage, where the model…

Computer Vision and Pattern Recognition · Computer Science 2026-02-26 Minyoung Lee , Yeji Park , Dongjun Hwang , Yejin Kim , Seong Joon Oh , Junsuk Choe

Query-based Vision Transformer segmentation models typically reconstruct dense spatial feature maps to predict masks, inheriting design patterns from convolutional architectures. We show that this explicit image-space reconstruction is not…

Computer Vision and Pattern Recognition · Computer Science 2026-05-19 Calvin Galagain , Martyna Poreba , François Goulette

Token compression expedites the training and inference of Vision Transformers (ViTs) by reducing the number of the redundant tokens, e.g., pruning inattentive tokens or merging similar tokens. However, when applied to downstream tasks,…

Computer Vision and Pattern Recognition · Computer Science 2024-08-14 Shibo Jie , Yehui Tang , Jianyuan Guo , Zhi-Hong Deng , Kai Han , Yunhe Wang

Deep convolutional neural networks achieve remarkable visual recognition performance, at the cost of high computational complexity. In this paper, we have a new design of efficient convolutional layers based on three schemes. The 3D…

Computer Vision and Pattern Recognition · Computer Science 2017-01-25 Min Wang , Baoyuan Liu , Hassan Foroosh

Advances in adversarial defenses have led to a significant improvement in the robustness of Deep Neural Networks. However, the robust accuracy of present state-ofthe-art defenses is far from the requirements in critical applications such as…

Machine Learning · Computer Science 2023-06-13 Sravanti Addepalli , Samyak Jain , Gaurang Sriramanan , R. Venkatesh Babu

The pretrain-finetune paradigm usually improves downstream performance over training a model from scratch on the same task, becoming commonplace across many areas of machine learning. While pretraining is empirically observed to be…

Computer Vision and Pattern Recognition · Computer Science 2023-07-13 Gabriele Merlin , Vedant Nanda , Ruchit Rawal , Mariya Toneva

Transformers have revolutionized deep learning across various domains but understanding the precise token dynamics remains a theoretical challenge. Existing theories of deep Transformers with layer normalization typically predict that…

Machine Learning · Statistics 2026-01-30 Lev Fedorov , Michaël E. Sander , Romuald Elie , Pierre Marion , Mathieu Laurière

The resurgence of convolutional neural networks (CNNs) in visual recognition tasks, exemplified by ConvNeXt, has demonstrated their capability to rival transformer-based architectures through advanced training methodologies and ViT-inspired…

Computer Vision and Pattern Recognition · Computer Science 2025-07-16 Quan Bi Pay , Vishnu Monn Baskaran , Junn Yong Loo , KokSheik Wong , Simon See

Low precision weights, activations, and gradients have been proposed as a way to improve the computational efficiency and memory footprint of deep neural networks. Recently, low precision networks have even shown to be more robust to…

Machine Learning · Computer Science 2018-07-04 Griffin Lacey , Graham W. Taylor , Shawki Areibi

In the past decade, we have witnessed rapid progress in the machine vision backbone. By introducing the inductive bias from the image processing, convolution neural network (CNN) has achieved excellent performance in numerous computer…

Computer Vision and Pattern Recognition · Computer Science 2021-06-29 Tan Yu , Xu Li , Yunfeng Cai , Mingming Sun , Ping Li