Can One-Shot Test-Time Data Augmentation Help with Generalization?
cs.CV, cs.AI, cs.LG
Submitted: 2026-01-27
Updated: 2026-09-05
License: http://creativecommons.org/licenses/by/4.0/
The gist: Data augmentation is crucial for model generalization, but existing methods are mostly centered on the training stage.
Terminology
Abstract
Data augmentation is crucial for model generalization, but existing methods are mostly centered on the training stage. Test-time augmentation, while underexplored, can be practically effective for generalization while avoiding extra model parameters or fine-tuning. Given the increasing training cost and the literature gap, we study whether it is possible to perform effective test-time augmentation using image generation from just the single original image. We first analyze the importance of test-time augmentation, and then design and study a simple yet natural operator named 1S-DAug, which comprises geometric perturbations with controlled noise injection and image-conditioned denoising. We obtain positive results on well-established image-classification benchmarks across four datasets and multiple models, achieving up to 20% relative accuracy improvement without model training or parameter access. Code will be released.
Sources
- A Closer Look at Few-shot Classification
- InstructBLIP: Towards General-purpose Vision-Language Models with Instruction Tuning
- Mitigating Object Hallucinations in Large Vision-Language Models through Visual Contrastive Decoding
- BLIP-2: Bootstrapping Language-Image Pre-training with Frozen Image Encoders and Large Language Models
- Evaluating Object Hallucination in Large Vision-Language Models
- Data Augmentation for Meta-Learning
- Improved Denoising Diffusion Probabilistic Models
- On First-Order Meta-Learning Algorithms
- Visual Instruction Tuning
- A Survey on Hallucination in Large Vision-Language Models
- Adding Conditional Control to Text-to-Image Diffusion Models
- IP-Adapter: Text Compatible Image Prompt Adapter for Text-to-Image Diffusion Models
Related papers
- Loss Knows Best: Detecting Annotation Errors in Videos via Loss Trajectories
- AnchorWeave: World-Consistent Video Generation with Retrieved Local Spatial Memories
- Benchmarking the Robustness of Foundation Models for Mammography under Domain Shift
- MambaX-Net: Dual-Input Mamba-Enhanced Cross-Attention Network for Longitudinal MRI Segmentation
- TeleOCR: Navigating Document Parsing Across Digital and Camera-Captured Documents
- A Survey on Efficient Vision-Language-Action Models