English
Related papers

Related papers: Better Aggregation in Test-Time Augmentation

200 papers

Data augmentation, the artificial creation of training data for machine learning by transformations, is a widely studied research field across machine learning disciplines. While it is useful for increasing a model's generalization…

Computation and Language · Computer Science 2022-09-09 Markus Bayer , Marc-André Kaufhold , Christian Reuter

We propose Test-Time Augmentation (TTA) as an effective technique for addressing combinatorial optimization problems, including the Traveling Salesperson Problem. In general, deep learning models possessing the property of invariance, where…

Machine Learning · Computer Science 2024-05-09 Ryo Ishiyama , Takahiro Shirakawa , Seiichi Uchida , Shinnosuke Matsuo

Synthetic augmentation is increasingly used to mitigate data scarcity in financial machine learning, yet its statistical role remains poorly understood. We formalize synthetic augmentation as a modification of the effective training…

Artificial Intelligence · Computer Science 2026-04-17 Mel Sohm , Charles Dezons , Sami Sellami , Oscar Ninou , Axel Pincon

Breast cancer is a serious disease that inflicts millions of people each year, and the number of cases is increasing. Early detection is the best way to reduce the impact of the disease. Researchers have developed many techniques to detect…

Artificial Intelligence · Computer Science 2023-11-23 Mosab S. M. Farea , zhe chen

Large-batch SGD is important for scaling training of deep neural networks. However, without fine-tuning hyperparameter schedules, the generalization of the model may be hampered. We propose to use batch augmentation: replicating instances…

Machine Learning · Computer Science 2019-01-29 Elad Hoffer , Tal Ben-Nun , Itay Hubara , Niv Giladi , Torsten Hoefler , Daniel Soudry

In this paper we investigate the question of how much combined measurements can increase the accuracy of additive quantities. Therefore, we consider a set of measurements from a selection of all possible combinations of the $n$ labeled…

Data Analysis, Statistics and Probability · Physics 2022-05-18 B. Mirbach , M. Boguslawski

Test-Time Adaptation (TTA) methods improve the robustness of deep neural networks to domain shift on a variety of tasks such as image classification or segmentation. This work explores adapting segmentation models to a single unlabelled…

Computer Vision and Pattern Recognition · Computer Science 2024-07-04 Klara Janouskova , Tamir Shor , Chaim Baskin , Jiri Matas

Scarcity of training data is one of the prominent problems for deep networks which require large amounts data. Data augmentation is a widely used method to increase the number of training samples and their variations. In this paper, we…

Computer Vision and Pattern Recognition · Computer Science 2020-12-10 Hilmi Kumdakcı , Cihan Öngün , Alptekin Temizel

Conventional image classifiers are trained by randomly sampling mini-batches of images. To achieve state-of-the-art performance, practitioners use sophisticated data augmentation schemes to expand the amount of training data available for…

Machine Learning · Computer Science 2021-06-23 Renkun Ni , Micah Goldblum , Amr Sharaf , Kezhi Kong , Tom Goldstein

Convolutional Neural Networks (ConvNets) are trained offline using the few available data and may therefore suffer from substantial accuracy loss when ported on the field, where unseen input patterns received under unpredictable external…

Computer Vision and Pattern Recognition · Computer Science 2021-05-14 Luca Mocerino , Roberto G. Rizzo , Valentino Peluso , Andrea Calimera , Enrico Macii

Pretrained VLMs exhibit strong zero-shot classification capabilities, but their predictions degrade significantly under common image corruptions. To improve robustness, many test-time adaptation (TTA) methods adopt positive data…

Machine Learning · Computer Science 2025-11-14 Ruxi Deng , Wenxuan Bao , Tianxin Wei , Jingrui He

Self-supervised contrastive learning has become a key technique in deep learning, particularly in time series analysis, due to its ability to learn meaningful representations without explicit supervision. Augmentation is a critical…

Machine Learning · Computer Science 2024-07-15 Ziyu Liu , Azadeh Alavi , Minyi Li , Xiang Zhang

Natural language processing models often face challenges due to limited labeled data, especially in domain specific areas, e.g., clinical trials. To overcome this, text augmentation techniques are commonly used to increases sample size by…

Computation and Language · Computer Science 2025-04-08 Charco Hui , Yalu Wen

Small datasets are common in health research. However, the generalization performance of machine learning models is suboptimal when the training datasets are small. To address this, data augmentation is one solution. Augmentation increases…

The weighted average is by far the most popular approach to combining multiple forecasts of some future outcome. This paper shows that both for probability or real-valued forecasts, a non-trivial weighted average of different forecasts is…

Methodology · Statistics 2015-09-28 Ville Satopää , Lyle Ungar

A general challenge in statistics is prediction in the presence of multiple candidate models or learning algorithms. Model aggregation tries to combine all predictive distributions from individual models, which is more stable and flexible…

Methodology · Statistics 2021-09-28 Yuling Yao

Deep neural networks have become popular in many supervised learning tasks, but they may suffer from overfitting when the training dataset is limited. To mitigate this, many researchers use data augmentation, which is a widely used and…

Machine Learning · Computer Science 2022-05-27 Jianhan Wu , Shijing Si , Jianzong Wang , Jing Xiao

Few-shot learning (FSL) commonly requires a model to identify images (queries) that belong to classes unseen during training, based on a few labelled samples of the new classes (support set) as reference. So far, plenty of algorithms…

Computer Vision and Pattern Recognition · Computer Science 2024-12-20 Yunwei Bai , Ying Kiat Tan , Shiming Chen , Yao Shu , Tsuhan Chen

The problem of combining individual forecasters to produce a forecaster with improved performance is considered. The connections between probability elicitation and classification are used to pose the combining forecaster problem as that of…

Methodology · Statistics 2017-07-11 Hamed Masnadi-Shirazi

Counterfactual data augmentation has recently emerged as a method to mitigate confounding biases in the training data. These biases, such as spurious correlations, arise due to various observed and unobserved confounding variables in the…

Machine Learning · Computer Science 2023-11-22 Abbavaram Gowtham Reddy , Saketh Bachu , Saloni Dash , Charchit Sharma , Amit Sharma , Vineeth N Balasubramanian