English
Related papers

Related papers: Revisiting ResNets: Improved Training and Scaling …

200 papers

Vision transformers (ViTs) have been an alternative design paradigm to convolutional neural networks (CNNs). However, the training of ViTs is much harder than CNNs, as it is sensitive to the training parameters, such as learning rate,…

Computer Vision and Pattern Recognition · Computer Science 2022-01-13 Pichao Wang , Xue Wang , Hao Luo , Jingkai Zhou , Zhipeng Zhou , Fan Wang , Hao Li , Rong Jin

In this paper, we describe a phenomenon, which we named "super-convergence", where neural networks can be trained an order of magnitude faster than with standard training methods. The existence of super-convergence is relevant to…

Machine Learning · Computer Science 2018-05-18 Leslie N. Smith , Nicholay Topin

Convolutional networks are at the center of best-in-class computer vision applications for a wide assortment of undertakings. Since 2014, a profound amount of work began to make better convolutional architectures, yielding generous…

Computer Vision and Pattern Recognition · Computer Science 2021-10-07 Dishant Parikh

Structured pruning is a popular method for compressing a neural network: given a large trained network, one alternates between removing channel connections and fine-tuning; reducing the overall width of the network. However, the efficacy of…

Machine Learning · Statistics 2019-06-10 Elliot J. Crowley , Jack Turner , Amos Storkey , Michael O'Boyle

Much of the recent progress made in image classification research can be credited to training procedure refinements, such as changes in data augmentations and optimization methods. In the literature, however, most refinements are either…

Computer Vision and Pattern Recognition · Computer Science 2018-12-07 Tong He , Zhi Zhang , Hang Zhang , Zhongyue Zhang , Junyuan Xie , Mu Li

The limited and dynamically varied resources on edge devices motivate us to deploy an optimized deep neural network that can adapt its sub-networks to fit in different resource constraints. However, existing works often build sub-networks…

Computer Vision and Pattern Recognition · Computer Science 2022-07-05 Zhongnan Qu , Syed Shakib Sarwar , Xin Dong , Yuecheng Li , Ekin Sumbul , Barbara De Salvo

As Artificial Intelligence (AI) models are increasingly integrated into critical systems, the need for a robust framework to establish the trustworthiness of AI is increasingly paramount. While collaborative efforts have established…

Machine Learning · Computer Science 2026-03-02 Haniyeh Ehsani Oskouie , Sajjad Ghiasvand , Lionel Levine , Majid Sarrafzadeh

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

Forecasting complex system dynamics, particularly for long-term predictions, is persistently hindered by error accumulation and computational burdens. This study presents RefreshNet, a multiscale framework developed to overcome these…

Machine Learning · Computer Science 2024-01-25 Junaid Farooq , Danish Rafiq , Pantelis R. Vlachas , Mohammad Abid Bazaz

Gradient-based algorithms for training ResNets typically require a forward pass of the input data, followed by back-propagating the objective gradient to update parameters, which are time-consuming for deep ResNets. To break the…

Machine Learning · Computer Science 2021-02-19 Qi Sun , Hexin Dong , Zewei Chen , Weizhen Dian , Jiacheng Sun , Yitong Sun , Zhenguo Li , Bin Dong

All-in-one image restoration tackles different types of degradations with a unified model instead of having task-specific, non-generic models for each degradation. The requirement to tackle multiple degradations using the same model can…

Computer Vision and Pattern Recognition · Computer Science 2024-10-15 Akshay Dudhane , Omkar Thawakar , Syed Waqas Zamir , Salman Khan , Fahad Shahbaz Khan , Ming-Hsuan Yang

Convolutional Neural Networks (CNNs) has revolutionized computer vision, but training very deep networks has been challenging due to the vanishing gradient problem. This paper explores Residual Networks (ResNet), introduced by He et al.…

Computer Vision and Pattern Recognition · Computer Science 2025-10-29 Xingyu Liu , Kun Ming Goh

One of the ways to train deep neural networks effectively is to use residual connections. Residual connections can be classified as being either identity connections or bridge-connections with a reshaping convolution. Empirical observations…

Machine Learning · Computer Science 2019-02-19 Varshaneya V , Balasubramanian S , Darshan Gera

One of the main challenges since the advancement of convolutional neural networks is how to connect the extracted feature map to the final classification layer. VGG models used two sets of fully connected layers for the classification part…

Computer Vision and Pattern Recognition · Computer Science 2024-03-12 Mohammad Rahimzadeh , AmirAli Askari , Soroush Parvin , Elnaz Safi , Mohammad Reza Mohammadi

Research in self-supervised learning (SSL) with natural images has progressed rapidly in recent years and is now increasingly being applied to and benchmarked with datasets containing remotely sensed imagery. A common benchmark case is to…

Computer Vision and Pattern Recognition · Computer Science 2023-05-24 Isaac Corley , Caleb Robinson , Rahul Dodhia , Juan M. Lavista Ferres , Peyman Najafirad

We present a new dataset condensation framework termed Squeeze, Recover and Relabel (SRe$^2$L) that decouples the bilevel optimization of model and synthetic data during training, to handle varying scales of datasets, model architectures…

Computer Vision and Pattern Recognition · Computer Science 2024-02-13 Zeyuan Yin , Eric Xing , Zhiqiang Shen

Convolutional neural networks (CNNs) depend on deep network architectures to extract accurate information for image super-resolution. However, obtained information of these CNNs cannot completely express predicted high-quality images for…

Image and Video Processing · Electrical Eng. & Systems 2024-03-25 Chunwei Tian , Xuanyu Zhang , Qi Zhang , Mingming Yang , Zhaojie Ju

Large models support great zero-shot and few-shot capabilities. However, updating these models on new tasks can break performance on previous seen tasks and their zero/few-shot unseen tasks. Our work explores how to update zero/few-shot…

Machine Learning · Computer Science 2023-01-30 Siddhartha Datta , Nigel Shadbolt

Convolutional neural networks have achieved a great success in the recent years. Although, the way to maximize the performance of the convolutional neural networks still in the beginning. Furthermore, the optimization of the size and the…

Computer Vision and Pattern Recognition · Computer Science 2017-06-21 Hussam Qassim , David Feinzimer , Abhishek Verma

State-of-the-art convolutional neural networks (CNNs) used in vision applications have large models with numerous weights. Training these models is very compute- and memory-resource intensive. Much research has been done on pruning or…

Machine Learning · Computer Science 2019-12-10 Sangkug Lym , Esha Choukse , Siavash Zangeneh , Wei Wen , Sujay Sanghavi , Mattan Erez
‹ Prev 1 8 9 10 Next ›