English
Related papers

Related papers: MetaFormer Baselines for Vision

200 papers

Transformers have achieved great success in effectively processing sequential data such as text. Their architecture consisting of several attention and feedforward blocks can model relations between elements of a sequence in parallel…

Machine Learning · Computer Science 2025-02-20 Jaemu Heo , Eldor Fozilov , Hyunmin Song , Taehwan Kim

Several recent Transformer architectures expose later layers to representations computed in the earliest layers, motivated by the observation that low-level features can become harder to recover as the residual stream is repeatedly…

Machine Learning · Computer Science 2026-05-07 Skye Gunasekaran , Téa Wright , Rui-Jie Zhu , Jason Eshraghian

Transformer-based architectures have advanced medical image analysis by effectively modeling long-range dependencies, yet they often struggle in 3D settings due to substantial memory overhead and insufficient capture of fine-grained local…

Although convolutional neural networks (CNNs) have achieved remarkable progress in weakly supervised semantic segmentation (WSSS), the effective receptive field of CNN is insufficient to capture global context information, leading to…

Computer Vision and Pattern Recognition · Computer Science 2022-03-17 Chunmeng Liu , Enze Xie , Wenjia Wang , Wenhai Wang , Guangyao Li , Ping Luo

Image resizing operation is a fundamental preprocessing module in modern computer vision. Throughout the deep learning revolution, researchers have overlooked the potential of alternative resizing methods beyond the commonly used resizers…

Computer Vision and Pattern Recognition · Computer Science 2023-04-07 Zhengzhong Tu , Peyman Milanfar , Hossein Talebi

In this paper, we propose a vision model that adopts token mixing, sequence-pooling, and convolutional tokenizers to achieve state-of-the-art performance and efficient inference in fixed context-length tasks. In the CIFAR100 benchmark, our…

Computer Vision and Pattern Recognition · Computer Science 2025-08-27 Simpenzwe Honore Leandre , Natenaile Asmamaw Shiferaw , Dillip Rout

Transformers have recently gained increasing attention in computer vision. However, existing studies mostly use Transformers for feature representation learning, e.g. for image classification and dense predictions, and the generalizability…

Computer Vision and Pattern Recognition · Computer Science 2021-12-08 Shengcai Liao , Ling Shao

Convolutional neural network (CNN) based methods have achieved great successes in medical image segmentation, but their capability to learn global representations is still limited due to using small effective receptive fields of convolution…

Computer Vision and Pattern Recognition · Computer Science 2022-11-17 Pengfei Gu , Yejia Zhang , Chaoli Wang , Danny Z. Chen

There has been exploding interest in embracing Transformer-based architectures for medical image segmentation. However, the lack of large-scale annotated medical datasets make achieving performances equivalent to those in natural images…

Image and Video Processing · Electrical Eng. & Systems 2024-06-04 Saikat Roy , Gregor Koehler , Constantin Ulrich , Michael Baumgartner , Jens Petersen , Fabian Isensee , Paul F. Jaeger , Klaus Maier-Hein

Multimodal learning aims to build models that can process and relate information from multiple modalities. Despite years of development in this field, it still remains challenging to design a unified network for processing various…

Computer Vision and Pattern Recognition · Computer Science 2023-07-21 Yiyuan Zhang , Kaixiong Gong , Kaipeng Zhang , Hongsheng Li , Yu Qiao , Wanli Ouyang , Xiangyu Yue

Transformers have become the dominant model in natural language processing, owing to their ability to pretrain on massive amounts of data, then transfer to smaller, more specific tasks via fine-tuning. The Vision Transformer was the first…

Computer Vision and Pattern Recognition · Computer Science 2020-12-21 Josh Beal , Eric Kim , Eric Tzeng , Dong Huk Park , Andrew Zhai , Dmitry Kislyuk

Recently, there has been a surge of interest and attention in Transformer-based structures, such as Vision Transformer (ViT) and Vision Multilayer Perceptron (VMLP). Compared with the previous convolution-based structures, the…

Computer Vision and Pattern Recognition · Computer Science 2023-09-26 Hao Cheng , Jinhao Duan , Hui Li , Lyutianyang Zhang , Jiahang Cao , Ping Wang , Jize Zhang , Kaidi Xu , Renjing Xu

Non-overlapping patch-wise convolution is the default image tokenizer for all state-of-the-art vision Transformer (ViT) models. Even though many ViT variants have been proposed to improve its efficiency and accuracy, little research on…

Computer Vision and Pattern Recognition · Computer Science 2024-05-30 Zhenhai Zhu , Radu Soricut

Humans can often count unfamiliar objects by observing visual repetition and composition, rather than relying only on object categories. However, many exemplar-free counting models struggle in such situations and may overcount when objects…

Computer Vision and Pattern Recognition · Computer Science 2026-03-10 Md Tanvir Hossain , Akif Islam , Mohd Ruhul Ameen

We propose Styleformer, which is a style-based generator for GAN architecture, but a convolution-free transformer-based generator. In our paper, we explain how a transformer can generate high-quality images, overcoming the disadvantage that…

Computer Vision and Pattern Recognition · Computer Science 2022-04-06 Jeeseung Park , Younggeun Kim

Feature pyramids have been widely adopted in convolutional neural networks and transformers for tasks in medical image segmentation. However, existing models generally focus on the Encoder-side Transformer for feature extraction. We further…

Computer Vision and Pattern Recognition · Computer Science 2025-04-08 Hongyi Cai , Mohammad Mahdinur Rahman , Wenzhen Dong , Jingyu Wu

Recently, Transformers have emerged as the go-to architecture for both vision and language modeling tasks, but their computational efficiency is limited by the length of the input sequence. To address this, several efficient variants of…

Computer Vision and Pattern Recognition · Computer Science 2023-05-18 Hao Zheng , Jinbao Wang , Xiantong Zhen , Hong Chen , Jingkuan Song , Feng Zheng

Due to adverse atmospheric and imaging conditions, natural images suffer from various degradation phenomena. Consequently, image restoration has emerged as a key solution and garnered substantial attention. Although recent Transformer…

Image and Video Processing · Electrical Eng. & Systems 2025-05-12 Xingyu Jiang , Ning Gao , Xiuhui Zhang , Hongkun Dou , Shaowen Fu , Xiaoqing Zhong , Hongjue Li , Yue Deng

Remote sensing imagery from systems such as Sentinel provides full coverage of the Earth's surface at around 10-meter resolution. The remote sensing community has transitioned to extensive use of deep learning models due to their high…

Computer Vision and Pattern Recognition · Computer Science 2025-03-12 Mingshi Li , Dusan Grujicic , Ben Somers , Stien Heremans , Steven De Saeger , Matthew B. Blaschko

The dot product self-attention (DPSA) is a fundamental component of transformers. However, scaling them to long sequences, like documents or high-resolution images, becomes prohibitively expensive due to quadratic time and memory…

Computer Vision and Pattern Recognition · Computer Science 2024-01-09 Pourya Shamsolmoali , Masoumeh Zareapoor , Eric Granger , Michael Felsberg