English
Related papers

Related papers: ConvNet vs Transformer, Supervised vs CLIP: Beyond…

200 papers

The remarkable performance of the Transformer architecture in natural language processing has recently also triggered broad interest in Computer Vision. Among other merits, Transformers are witnessed as capable of learning long-range…

Computer Vision and Pattern Recognition · Computer Science 2023-11-07 Reza Azad , Amirhossein Kazerouni , Moein Heidari , Ehsan Khodapanah Aghdam , Amirali Molaei , Yiwei Jia , Abin Jose , Rijo Roy , Dorit Merhof

Vision Transformers (ViTs) is emerging as an alternative to convolutional neural networks (CNNs) for visual recognition. They achieve competitive results with CNNs but the lack of the typical convolutional inductive bias makes them more…

Computer Vision and Pattern Recognition · Computer Science 2022-01-27 Yun-Hao Cao , Hao Yu , Jianxin Wu

Pre-training general-purpose visual features with convolutional neural networks without relying on annotations is a challenging and important task. Most recent efforts in unsupervised feature learning have focused on either small or highly…

Computer Vision and Pattern Recognition · Computer Science 2019-08-14 Mathilde Caron , Piotr Bojanowski , Julien Mairal , Armand Joulin

Capsule Network (CapsNet) is among the promising classifiers and a possible successor of the classifiers built based on Convolutional Neural Network (CNN). CapsNet is more accurate than CNNs in detecting images with overlapping categories…

Computer Vision and Pattern Recognition · Computer Science 2025-12-02 Pouya Shiri , Amirali Baniasadi

Large multi-modal models (LMMs) hold the potential to usher in a new era of automated visual assistance for people who are blind or low vision (BLV). Yet, these models have not been systematically evaluated on data captured by BLV users. We…

Computer Vision and Pattern Recognition · Computer Science 2024-03-26 Daniela Massiceti , Camilla Longden , Agnieszka Słowik , Samuel Wills , Martin Grayson , Cecily Morrison

Computer vision has achieved remarkable success by (a) representing images as uniformly-arranged pixel arrays and (b) convolving highly-localized features. However, convolutions treat all image pixels equally regardless of importance;…

Computer Vision and Pattern Recognition · Computer Science 2020-11-23 Bichen Wu , Chenfeng Xu , Xiaoliang Dai , Alvin Wan , Peizhao Zhang , Zhicheng Yan , Masayoshi Tomizuka , Joseph Gonzalez , Kurt Keutzer , Peter Vajda

Vision foundation models pretrained on web-scale data have recently shown strong transfer capabilities on many downstream tasks, but their effectiveness for industrial visual inspection remains unclear. Industrial data differ substantially…

Computer Vision and Pattern Recognition · Computer Science 2026-05-25 Mehdi Gharbage , Céline Teulière , Pierre Bouges , Thierry Chateau

The rapid evolution of digital image manipulation techniques poses significant challenges for content verification, with models such as stable diffusion and mid-journey producing highly realistic, yet synthetic, images that can deceive…

Computer Vision and Pattern Recognition · Computer Science 2024-12-10 Alejandro Marco Montejano , Angela Sanchez Perez , Javier Barrachina , David Ortiz-Perez , Manuel Benavent-Lledo , Jose Garcia-Rodriguez

Deep learning with a convolutional neural network (CNN) has been proved to be very effective in feature extraction and representation of images. For image classification problems, this work aim at finding which classifier is more…

Machine Learning · Computer Science 2015-06-09 Lei Zhang , David Zhang

How do humans learn to acquire a powerful, flexible and robust representation of objects? While much of this process remains unknown, it is clear that humans do not require millions of object labels. Excitingly, recent algorithmic…

Computer Vision and Pattern Recognition · Computer Science 2020-10-19 Robert Geirhos , Kantharaju Narayanappa , Benjamin Mitzkus , Matthias Bethge , Felix A. Wichmann , Wieland Brendel

Neural networks have become the standard technique for medical diagnostics, especially in cancer detection and classification. This work evaluates the performance of Vision Transformers architectures, including Swin Transformer and MaxViT,…

Computer Vision and Pattern Recognition · Computer Science 2025-06-17 Óscar A. Martín , Javier Sánchez

For computer vision, Vision Transformers (ViTs) have become one of the go-to deep net architectures. Despite being inspired by Convolutional Neural Networks (CNNs), ViTs' output remains sensitive to small spatial shifts in the input, i.e.,…

Computer Vision and Pattern Recognition · Computer Science 2023-11-30 Renan A. Rojas-Gomez , Teck-Yian Lim , Minh N. Do , Raymond A. Yeh

Convolutional neural networks (CNN) are the dominant deep neural network (DNN) architecture for computer vision. Recently, Transformer and multi-layer perceptron (MLP)-based models, such as Vision Transformer and MLP-Mixer, started to lead…

Computer Vision and Pattern Recognition · Computer Science 2021-11-29 Yucheng Zhao , Guangting Wang , Chuanxin Tang , Chong Luo , Wenjun Zeng , Zheng-Jun Zha

Edge detection has made significant progress with the help of deep Convolutional Networks (ConvNet). These ConvNet based edge detectors have approached human level performance on standard benchmarks. We provide a systematical study of these…

Computer Vision and Pattern Recognition · Computer Science 2018-12-05 Yupei Wang , Xin Zhao , Yin Li , Kaiqi Huang

Convolutional neural networks (CNNs) are widely used in many image recognition tasks due to their extraordinary performance. However, training a good CNN model can still be a challenging task. In a training process, a CNN model typically…

Machine Learning · Computer Science 2017-10-17 Haipeng Zeng , Hammad Haleem , Xavier Plantaz , Nan Cao , Huamin Qu

While adversarial training has been extensively studied for ResNet architectures and low resolution datasets like CIFAR, much less is known for ImageNet. Given the recent debate about whether transformers are more robust than convnets, we…

Computer Vision and Pattern Recognition · Computer Science 2023-10-31 Naman D Singh , Francesco Croce , Matthias Hein

The tremendous success of ImageNet-trained deep features on a wide range of transfer tasks begs the question: what are the properties of the ImageNet dataset that are critical for learning good, general-purpose features? This work provides…

Computer Vision and Pattern Recognition · Computer Science 2016-12-13 Minyoung Huh , Pulkit Agrawal , Alexei A. Efros

The vision transformer (ViT) has advanced to the cutting edge in the visual recognition task. Transformers are more robust than CNN, according to the latest research. ViT's self-attention mechanism, according to the claim, makes it more…

Computer Vision and Pattern Recognition · Computer Science 2023-10-10 Salman Rahman , Wonkwon Lee

Can a lightweight Vision Transformer (ViT) match or exceed the performance of Convolutional Neural Networks (CNNs) like ResNet on small datasets with small image resolutions? This report demonstrates that a pure ViT can indeed achieve…

Computer Vision and Pattern Recognition · Computer Science 2024-02-07 Jen Hong Tan

Large vision language models, such as CLIP, demonstrate impressive robustness to spurious features than single-modal models trained on ImageNet. However, existing test datasets are typically curated based on ImageNet-trained models, which…

Computer Vision and Pattern Recognition · Computer Science 2024-11-05 Qizhou Wang , Yong Lin , Yongqiang Chen , Ludwig Schmidt , Bo Han , Tong Zhang