English
Related papers

Related papers: Network Augmentation for Tiny Deep Learning

200 papers

In this paper, we explore and compare multiple solutions to the problem of data augmentation in image classification. Previous work has demonstrated the effectiveness of data augmentation through simple techniques, such as cropping,…

Computer Vision and Pattern Recognition · Computer Science 2017-12-14 Luis Perez , Jason Wang

Deep neural networks have emerged as very successful tools for image restoration and reconstruction tasks. These networks are often trained end-to-end to directly reconstruct an image from a noisy or corrupted measurement of that image. To…

Image and Video Processing · Electrical Eng. & Systems 2021-06-30 Zalan Fabian , Reinhard Heckel , Mahdi Soltanolkotabi

In this paper we present a technique to train neural network models on small amounts of data. Current methods for training neural networks on small amounts of rich data typically rely on strategies such as fine-tuning a pre-trained neural…

Machine Learning · Computer Science 2016-11-08 Ark Anderson , Kyle Shaffer , Artem Yankov , Court D. Corley , Nathan O. Hodas

Data augmentation has long been a cornerstone for reducing overfitting in vision models, with methods like AutoAugment automating the design of task-specific augmentations. Recent advances in generative models, such as conditional diffusion…

Computer Vision and Pattern Recognition · Computer Science 2026-02-04 Judah Goldfeder , Shreyes Kaliyur , Vaibhav Sourirajan , Patrick Minwan Puma , Philippe Martin Wyder , Yuhang Hu , Jiong Lin , Hod Lipson

Data-augmentation is key to the training of neural networks for image classification. This paper first shows that existing augmentations induce a significant discrepancy between the typical size of the objects seen by the classifier at…

Computer Vision and Pattern Recognition · Computer Science 2022-01-21 Hugo Touvron , Andrea Vedaldi , Matthijs Douze , Hervé Jégou

AutoAugment has been a powerful algorithm that improves the accuracy of many vision tasks, yet it is sensitive to the operator space as well as hyper-parameters, and an improper setting may degenerate network optimization. This paper delves…

Computer Vision and Pattern Recognition · Computer Science 2020-03-26 Longhui Wei , An Xiao , Lingxi Xie , Xin Chen , Xiaopeng Zhang , Qi Tian

Data augmentation is a dominant method for reducing model overfitting and improving generalization. Most existing data augmentation methods tend to find a compromise in augmenting the data, \textit{i.e.}, increasing the amplitude of…

Computer Vision and Pattern Recognition · Computer Science 2023-10-17 Zehao Wang , Yiwen Guo , Qizhang Li , Guanglei Yang , Wangmeng Zuo

Handwritten text and scene text suffer from various shapes and distorted patterns. Thus training a robust recognition model requires a large amount of data to cover diversity as much as possible. In contrast to data collection and…

Computer Vision and Pattern Recognition · Computer Science 2020-03-17 Canjie Luo , Yuanzhi Zhu , Lianwen Jin , Yongpan Wang

One of the growing trends in machine learning is the use of data generation techniques, since the performance of machine learning models is dependent on the quantity of the training dataset. However, in many real-world applications,…

Artificial Intelligence · Computer Science 2025-04-25 Yasaman Haghbin , Hadi Moradi , Reshad Hosseini

In contrast to conventional artificial neural networks, which are structurally static, we present two approaches for evolving small networks into larger ones during training. The first method employs an auxiliary weight that directly…

Machine Learning · Computer Science 2025-07-29 Anil Radhakrishnan , John F. Lindner , Scott T. Miller , Sudeshna Sinha , William L. Ditto

Image classification has been a popular task due to its feasibility in real-world applications. Training neural networks by feeding them RGB images has demonstrated success over it. Nevertheless, improving the classification accuracy and…

Computer Vision and Pattern Recognition · Computer Science 2024-01-17 Tianhao Bu , Michalis Lazarou , Tania Stathaki

Traditional CNN models are trained and tested on relatively low resolution images (<300 px), and cannot be directly operated on large-scale images due to compute and memory constraints. We propose Patch Gradient Descent (PatchGD), an…

Computer Vision and Pattern Recognition · Computer Science 2023-02-01 Deepak K. Gupta , Gowreesh Mago , Arnav Chavan , Dilip K. Prasad

Tiny deep learning has attracted increasing attention driven by the substantial demand for deploying deep learning on numerous intelligent Internet-of-Things devices. However, it is still challenging to unleash tiny deep learning's full…

Machine Learning · Computer Science 2023-06-26 Zhongzhi Yu , Yonggan Fu , Jiayi Yuan , Haoran You , Yingyan Lin

Deep neural networks are learning models with a very high capacity and therefore prone to over-fitting. Many regularization techniques such as Dropout, DropConnect, and weight decay all attempt to solve the problem of over-fitting by…

Machine Learning · Computer Science 2016-12-06 Armen Aghajanyan

In this paper, we present augmentation inside the network, a method that simulates data augmentation techniques for computer vision problems on intermediate features of a convolutional neural network. We perform these transformations,…

Computer Vision and Pattern Recognition · Computer Science 2023-06-27 Maciej Sypetkowski , Jakub Jasiulewicz , Zbigniew Wojna

Convolutional Neural Networks (CNNs) serve as the workhorse of deep learning, finding applications in various fields that rely on images. Given sufficient data, they exhibit the capacity to learn a wide range of concepts across diverse…

Computer Vision and Pattern Recognition · Computer Science 2025-02-27 Saorj Kumar , Prince Asiamah , Oluwatoyin Jolaoso , Ugochukwu Esiowu

RNN-Transducer (RNN-T) is a widely adopted architecture in speech recognition, integrating acoustic and language modeling in an end-to-end framework. However, the RNN-T predictor tends to over-rely on consecutive word dependencies in…

Sound · Computer Science 2025-02-21 Khanh Le , Tuan Vu Ho , Dung Tran , Duc Thanh Chau

Data augmentation is one of the most important tools in training modern deep neural networks. Recently, great advances have been made in searching for optimal augmentation policies in the image classification domain. However, two key points…

Computer Vision and Pattern Recognition · Computer Science 2020-08-25 Zhiqiang Tang , Yunhe Gao , Leonid Karlinsky , Prasanna Sattigeri , Rogerio Feris , Dimitris Metaxas

State-of-the-art automatic augmentation methods (e.g., AutoAugment and RandAugment) for visual recognition tasks diversify training data using a large set of augmentation operations. The range of magnitudes of many augmentation operations…

Computer Vision and Pattern Recognition · Computer Science 2022-12-21 Sachin Mehta , Saeid Naderiparizi , Fartash Faghri , Maxwell Horton , Lailin Chen , Ali Farhadi , Oncel Tuzel , Mohammad Rastegari

We introduce DiffAug, a simple and efficient diffusion-based augmentation technique to train image classifiers for the crucial yet challenging goal of improved classifier robustness. Applying DiffAug to a given example consists of one…

Computer Vision and Pattern Recognition · Computer Science 2024-05-30 Chandramouli Sastry , Sri Harsha Dumpala , Sageev Oore