AI Paper Atlas

Research map / Detection and segmentation / CNN features

Sample-Aware RandAugment: Search-Free Automatic Data Augmentation for Effective Image Recognition

Anqi Xiao, Weichen Yu, Hongyuan Yu

IJCV 2025 · Detection and segmentation › CNN features · approach: Efficient DETR query design · 5 citations (OpenAlex)

Read the paperCheck your idea against 137,217 papers

AI-extracted. The measured effects below were read by AI from the paper's full text (no summary yet). Numbers and claims can be wrong or missing context, so check the paper before you cite or build on it.

Measured effects reported in the paper

What was changedWhereMeasuredEffect
add scaling factor gamma to MIS (ablation)SRA · CIFAR-100 (WRN-28-10)top-1 accuracy (%): 84.49 -> 84.64Improved
add random augmentation in Step 1 exploration (ablation)SRA · CIFAR-100 (WRN-28-10)top-1 accuracy (%): 84.45 -> 84.64Improved
add distribution exploration (Step 1) alongside refinement (ablation)SRA · CIFAR-100 (WRN-28-10)top-1 accuracy (%): 84.09 -> 84.64Improved
add sample-aware refinement (Step 2 & 3) alongside exploration (ablation)SRA · CIFAR-100 (WRN-28-10)top-1 accuracy (%): 83.93 -> 84.64Improved
split exploration and refinement into separate sub-batches (asymmetric) (ablation)SRA · CIFAR-100 (WRN-28-10)top-1 accuracy (%): 84.54 -> 84.64Improved
use cosine similarity instead of Euclidean distance for MIS (ablation)SRA · CIFAR-100 (WRN-28-10)top-1 accuracy (%): 84.37 -> 84.64Improved
use cosine similarity instead of Jaccard similarity for MIS (ablation)SRA · CIFAR-100 (WRN-28-10)top-1 accuracy (%): 84.03 -> 84.64Improved
augmentation depth D=2 instead of D=4 (ablation)SRA · CIFAR-100 (WRN-28-10)top-1 accuracy (%): 84.02 -> 84.64Improved
normalization scale epsilon 2 instead of 0 (ablation)SRA · CIFAR-100 (WRN-28-10)top-1 accuracy (%): 84.44 -> 84.64Improved
add TranslateY operator to the candidate set (ablation)SRA · CIFAR-100 (WRN-28-10)top-1 accuracy (%): 84.11 -> 84.64Improved
use SRA instead of RA (2, 9)ResNet-50 · ImageNet-LT (overall)top-1 accuracy (%): 45.18 -> 46.76Improved
use SRA instead of RA (2, 9)ResNet-50 · Food101top-1 accuracy (%): 85.97 -> 87.04Improved

Closest papers by meaning

Writing a paper in this area? scime draft is a free LaTeX editor with AI included, real-time co-authors and a check of your references and venue rules before you submit. It also imports OpenAI Prism projects.

Open scime draft

Get the next scime Dispatch and a monthly field update

Free. We send a confirmation link first; every email has a one-click unsubscribe. Privacy