English
Related papers

Related papers: Do Better ImageNet Models Transfer Better?

200 papers

Previous work has proposed many new loss functions and regularizers that improve test accuracy on image classification tasks. However, it is not clear whether these loss functions learn better representations for downstream tasks. This…

Computer Vision and Pattern Recognition · Computer Science 2021-11-05 Simon Kornblith , Ting Chen , Honglak Lee , Mohammad Norouzi

Transfer learning from supervised ImageNet models has been frequently used in medical image analysis. Yet, no large-scale evaluation has been conducted to benchmark the efficacy of newly-developed pre-training techniques for medical image…

Computer Vision and Pattern Recognition · Computer Science 2021-08-16 Mohammad Reza Hosseinzadeh Taher , Fatemeh Haghighi , Ruibin Feng , Michael B. Gotway , Jianming Liang

In recent developments in the field of Computer Vision, a rise is seen in the use of transformer-based architectures. They are surpassing the state-of-the-art set by CNN architectures in accuracy but on the other hand, they are…

Computer Vision and Pattern Recognition · Computer Science 2021-10-12 Durvesh Malpure , Onkar Litake , Rajesh Ingle

Transfer learning from huge natural image datasets, fine-tuning of deep neural networks and the use of the corresponding pre-trained networks have become de facto the core of art analysis applications. Nevertheless, the effects of transfer…

Computer Vision and Pattern Recognition · Computer Science 2020-11-25 Nicolas Gonthier , Yann Gousseau , Saïd Ladjal

State-of-the-art visual perception models for a wide range of tasks rely on supervised pretraining. ImageNet classification is the de facto pretraining task for these models. Yet, ImageNet is now nearly ten years old and is by modern…

Computer Vision and Pattern Recognition · Computer Science 2018-05-03 Dhruv Mahajan , Ross Girshick , Vignesh Ramanathan , Kaiming He , Manohar Paluri , Yixuan Li , Ashwin Bharambe , Laurens van der Maaten

In this work we examine the performance enhancement in classification of medical imaging data when image features are combined with associated non-image data. We compare the performance of eight state-of-the-art deep neural networks in…

Image and Video Processing · Electrical Eng. & Systems 2021-11-30 Spencer A. Thomas

Almost all the state-of-the-art neural networks for computer vision tasks are trained by (1) pre-training on a large-scale dataset and (2) finetuning on the target dataset. This strategy helps reduce dependence on the target dataset and…

Computer Vision and Pattern Recognition · Computer Science 2021-11-22 Shuvam Chakraborty , Burak Uzkent , Kumar Ayush , Kumar Tanmay , Evan Sheehan , Stefano Ermon

It is an open secret that ImageNet is treated as the panacea of pretraining. Particularly in medical machine learning, models not trained from scratch are often finetuned based on ImageNet-pretrained models. We posit that pretraining on…

Computer Vision and Pattern Recognition · Computer Science 2025-02-17 Frederic Jonske , Moon Kim , Enrico Nasca , Janis Evers , Johannes Haubold , René Hosch , Felix Nensa , Michael Kamp , Constantin Seibold , Jan Egger , Jens Kleesiek

In recent years, deep perceptual loss has been widely and successfully used to train machine learning models for many computer vision tasks, including image synthesis, segmentation, and autoencoding. Deep perceptual loss is a type of loss…

Computer Vision and Pattern Recognition · Computer Science 2024-07-04 Gustav Grund Pihlgren , Konstantina Nikolaidou , Prakash Chandra Chhipa , Nosheen Abid , Rajkumar Saini , Fredrik Sandin , Marcus Liwicki

Pre-training a deep neural network on the ImageNet dataset is a common practice for training deep learning models, and generally yields improved performance and faster training times. The technique of pre-training on one task and then…

Machine Learning · Computer Science 2020-01-03 Nishai Kooverjee , Steven James , Terence van Zyl

Vision transformers have attracted much attention from computer vision researchers as they are not restricted to the spatial inductive bias of ConvNets. However, although Transformer-based backbones have achieved much progress on ImageNet…

Computer Vision and Pattern Recognition · Computer Science 2021-08-18 Hong-Yu Zhou , Chixiang Lu , Sibei Yang , Yizhou Yu

Recent progress in image recognition has stimulated the deployment of vision systems at an unprecedented scale. As a result, visual data are now often consumed not only by humans but also by machines. Existing image processing methods only…

Computer Vision and Pattern Recognition · Computer Science 2022-09-13 Zhuang Liu , Hung-Ju Wang , Tinghui Zhou , Zhiqiang Shen , Bingyi Kang , Evan Shelhamer , Trevor Darrell

Convolutional Neural Networks (CNNs) are commonly thought to recognise objects by learning increasingly complex representations of object shapes. Some recent studies suggest a more important role of image textures. We here put these…

Computer Vision and Pattern Recognition · Computer Science 2022-11-11 Robert Geirhos , Patricia Rubisch , Claudio Michaelis , Matthias Bethge , Felix A. Wichmann , Wieland Brendel

Material classification in natural settings is a challenge due to complex interplay of geometry, reflectance properties, and illumination. Previous work on material classification relies strongly on hand-engineered features of visual…

Computer Vision and Pattern Recognition · Computer Science 2016-09-21 Patrick Wieschollek , Hendrik P. A. Lensch

This paper presents a comparative study of a custom convolutional neural network (CNN) architecture against widely used pretrained and transfer learning CNN models across five real-world image datasets. The datasets span binary…

Computer Vision and Pattern Recognition · Computer Science 2026-01-06 Mahmudul Hasan , Mabsur Fatin Bin Hossain

Modern computer vision offers a great variety of models to practitioners, and selecting a model from multiple options for specific applications can be challenging. Conventionally, competing model architectures and training protocols are…

Computer Vision and Pattern Recognition · Computer Science 2024-07-24 Kirill Vishniakov , Zhiqiang Shen , Zhuang Liu

Training deep neural networks using simulations typically requires very large numbers of simulated events. This can be a large computational burden and a limitation in the performance of the deep learning algorithm when insufficient numbers…

High Energy Physics - Experiment · Physics 2023-03-21 Andrew Chappell , Leigh H. Whitehead

Deep neural networks such as convolutional neural networks (CNNs) and transformers have achieved many successes in image classification in recent years. It has been consistently demonstrated that best practice for image classification is…

Computer Vision and Pattern Recognition · Computer Science 2025-12-09 Jo Plested , Musa Phiri , Tom Gedeon

Pre-training has been a popular learning paradigm in deep learning era, especially in annotation-insufficient scenario. Better ImageNet pre-trained models have been demonstrated, from the perspective of architecture, by previous research to…

Computer Vision and Pattern Recognition · Computer Science 2023-08-21 Andong Deng , Xingjian Li , Di Hu , Tianyang Wang , Haoyi Xiong , Chengzhong Xu

Deep neural networks demonstrate to have a high performance on image classification tasks while being more difficult to train. Due to the complexity and vanishing gradient problem, it normally takes a lot of time and more computational…

Computer Vision and Pattern Recognition · Computer Science 2018-05-02 Mohammad Sadegh Ebrahimi , Hossein Karkeh Abadi