Learning Loss for Test-Time Augmentation
Data augmentation has been actively studied for robust neural networks. Most of the recent data augmentation methods focus on augmenting datasets during the training phase. At the testing phase, simple transformations are still widely used for test-time augmentation. This paper proposes a novel instance-level test-time augmentation that efficiently selects suitable transformations for a test input. Our proposed method involves an auxiliary module to predict the loss of each possible transformation given the input. Then, the transformations having lower predicted losses are applied to the input. The network obtains the results by averaging the prediction results of augmented inputs. Experimental results on several image classification benchmarks show that the proposed instance-aware test-time augmentation improves the model's robustness against various corruptions.
Code (0)
등록된 구현이 없습니다.
Tasks
Data Augmentationimage-classificationImage ClassificationSimilar Papers 제목 키워드 기반
Cyclic Test Time Augmentation with Entropy Weight Method
In the recent studies of data augmentation of neural networks, the application of test time augmentation has been studied to extract optimal transformation policies to enhance performance with minimum cost. The policy se…
Data AugmentationGeneralized Wasserstein Dice Loss, Test-time Augmentation, and Transformers for the BraTS 2021 challenge
Brain tumor segmentation from multiple Magnetic Resonance Imaging (MRI) modalities is a challenging task in medical image computation. The main challenges lie in the generalizability to a variety of scanners and imaging …
Brain Tumor SegmentationTumor SegmentationAugLoss: A Robust Augmentation-based Fine Tuning Methodology
Deep Learning (DL) models achieve great successes in many domains. However, DL models increasingly face safety and robustness concerns, including noisy labeling in the training stage and feature distribution shifts in th…
Data AugmentationSEVA: Leveraging Single-Step Ensemble of Vicinal Augmentations for Test-Time Adaptation
Test-Time adaptation (TTA) aims to enhance model robustness against distribution shifts through rapid model adaptation during inference. While existing TTA methods often rely on entropy-based unsupervised training and ac…
Test-time AdaptationFeature Augmentation based Test-Time Adaptation
Test-time adaptation (TTA) allows a model to be adapted to an unseen domain without accessing the source data. Due to the nature of practical environments, TTA has a limited amount of data for adaptation. Recent TTA meth…
Test-time Adaptation