English
Related papers

Related papers: Optimal Layer Selection for Latent Data Augmentati…

200 papers

Data Augmentation (DA) -- generating extra training samples beyond original training set -- has been widely-used in today's unbiased VQA models to mitigate the language biases. Current mainstream DA strategies are synthetic-based methods,…

Computer Vision and Pattern Recognition · Computer Science 2022-09-16 Long Chen , Yuhang Zheng , Jun Xiao

Test Time Adaptation (TTA) addresses the problem of distribution shift by adapting a pretrained model to a new domain during inference. When faced with challenging shifts, most methods collapse and perform worse than the original pretrained…

Machine Learning · Computer Science 2025-02-25 Sabyasachi Sahoo , Mostafa ElAraby , Jonas Ngnawe , Yann Pequignot , Frederic Precioso , Christian Gagne

Deep learning models have a large number of freeparameters that need to be calculated by effective trainingof the models on a great deal of training data to improvetheir generalization performance. However, data obtaining andlabeling is…

Computer Vision and Pattern Recognition · Computer Science 2019-07-01 Benlin Hu , Cheng Lei , Dong Wang , Shu Zhang , Zhenyu Chen

Non-parametric, additive models are able to capture complex data dependencies in a flexible, yet interpretable way. However, choosing the format of the additive components often requires non-trivial data exploration. Here, as an…

Machine Learning · Computer Science 2022-02-23 Oskar Allerbo , Rebecka Jörnsten

As an essential branch of recommender systems, sequential recommendation (SR) has received much attention due to its well-consistency with real-world situations. However, the widespread data sparsity issue limits the SR model's performance.…

Information Retrieval · Computer Science 2024-09-23 Yizhou Dang , Enneng Yang , Yuting Liu , Guibing Guo , Linying Jiang , Jianzhe Zhao , Xingwei Wang

Quantization-aware training (QAT) and Knowledge Distillation (KD) are combined to achieve competitive performance in creating low-bit deep learning models. Existing KD and QAT works focus on improving the accuracy of quantized models from…

Machine Learning · Computer Science 2025-09-05 Justin Kur , Kaiqi Zhao

Convolutional Neural Network (CNN)-based accurate prediction typically requires large-scale annotated training data. In Medical Imaging, however, both obtaining medical data and annotating them by expert physicians are challenging; to…

Computer Vision and Pattern Recognition · Computer Science 2019-05-30 Changhee Han , Kohei Murao , Shin'ichi Satoh , Hideki Nakayama

Data augmentation is an effective technique for improving the accuracy of modern image classifiers. However, current data augmentation implementations are manually designed. In this paper, we describe a simple procedure called AutoAugment…

Computer Vision and Pattern Recognition · Computer Science 2019-04-15 Ekin D. Cubuk , Barret Zoph , Dandelion Mane , Vijay Vasudevan , Quoc V. Le

Deep learning has recently been applied to automatically classify the modulation categories of received radio signals without manual experience. However, training deep learning models requires massive volume of data. An insufficient…

Signal Processing · Electrical Eng. & Systems 2019-12-11 Liang Huang , Weijian Pan , You Zhang , LiPing Qian , Nan Gao , Yuan Wu

The performance of learning models heavily relies on the availability and adequacy of training data. To address the dataset adequacy issue, researchers have extensively explored data augmentation (DA) as a promising approach. DA generates…

Computation and Language · Computer Science 2023-08-22 Dania Refai , Saleh Abo-Soud , Mohammad Abdel-Rahman

Dementia is a growing problem as our society ages, and detection methods are often invasive and expensive. Recent deep-learning techniques can offer a faster diagnosis and have shown promising results. However, they require large amounts of…

Computation and Language · Computer Science 2022-07-19 Anna Hlédiková , Dominika Woszczyk , Alican Akman , Soteris Demetriou , Björn Schuller

Objective: The use of deep learning for electroencephalography (EEG) classification tasks has been rapidly growing in the last years, yet its application has been limited by the relatively small size of EEG datasets. Data augmentation,…

Machine Learning · Computer Science 2022-11-16 Cédric Rommel , Joseph Paillard , Thomas Moreau , Alexandre Gramfort

Aggregating information from features across different layers is an essential operation for dense prediction models. Despite its limited expressiveness, feature concatenation dominates the choice of aggregation operations. In this paper, we…

Computer Vision and Pattern Recognition · Computer Science 2023-01-20 Yung-Hsu Yang , Thomas E. Huang , Min Sun , Samuel Rota Bulò , Peter Kontschieder , Fisher Yu

Large pre-trained models are usually fine-tuned on downstream task data, and tested on unseen data. When the train and test data come from different domains, the model is likely to struggle, as it is not adapted to the test domain. We…

Computation and Language · Computer Science 2022-06-02 Omer Antverg , Eyal Ben-David , Yonatan Belinkov

Camera localization is a fundamental and crucial problem for many robotic applications. In recent years, using deep-learning for camera-based localization has become a popular research direction. However, they lack robustness to large…

Computer Vision and Pattern Recognition · Computer Science 2021-12-07 Jialu Wang , Muhamad Risqi U. Saputra , Chris Xiaoxuan Lu , Niki Trigon , Andrew Markham

The composition of pretraining data is a key determinant of foundation models' performance, but there is no standard guideline for allocating a limited computational budget across different data sources. Most current approaches either rely…

Machine Learning · Computer Science 2024-10-16 Yiding Jiang , Allan Zhou , Zhili Feng , Sadhika Malladi , J. Zico Kolter

Robustness is a significant constraint in machine learning models. The performance of the algorithms must not deteriorate when training and testing with slightly different data. Deep neural network models achieve awe-inspiring results in a…

Computer Vision and Pattern Recognition · Computer Science 2021-02-25 Flavio Santos , Cleber Zanchettin , Leonardo Matos , Paulo Novais

Data augmentation is commonly applied to improve performance of deep learning by enforcing the knowledge that certain transformations on the input preserve the output. Currently, the data augmentation parameters are chosen by human effort…

In this paper, we introduce a novel data augmentation technique that combines the advantages of style augmentation and random erasing by selectively replacing image subregions with style-transferred patches. Our approach first applies a…

Computer Vision and Pattern Recognition · Computer Science 2025-09-29 Qikai Yang , Cheng Ji , Huaiying Luo , Panfeng Li , Zhicheng Ding

Synthetically augmenting training datasets with diffusion models has become an effective strategy for improving the generalization of image classifiers. However, existing approaches typically increase dataset size by 10-30x and struggle to…

Computer Vision and Pattern Recognition · Computer Science 2026-03-05 Dang Nguyen , Jiping Li , Jinghao Zheng , Baharan Mirzasoleiman