AI Paper Atlas

Research map / Label-efficient and robust learning / Zero-/few-shot and meta-learning

Image Block Augmentation for One-Shot Learning

Zitian Chen, Yanwei Fu, Kaiyu Chen, Yu-Gang Jiang

AAAI 2019 · Label-efficient and robust learning › Zero-/few-shot and meta-learning · approach: Fine-grained and cross-domain few-shot baselines · 112 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
full Self-Jig vs SVM baselineSVM one-shot classifier · miniImageNet 5-way 1-shotaccuracy: 52.73 -> 58.80Improved
full Self-Jig vs SVM baselineSVM classifier, ResNet-10 · ImageNet1k novel n=1top-1: 15.9 -> 23.8Improved
add self-training gallery selection (ablation)Rob+Jigsaw (SVM) · miniImageNet 5-way 1-shotaccuracy: 55.54 -> 58.80Improved
add jigsaw augmentation (ablation)Rob+Self-T (SVM) · miniImageNet 5-way 1-shotaccuracy: 51.22 -> 58.80Improved
add robust feature extractor finetuning (ablation)Self-T+Jigsaw (SVM) · miniImageNet 5-way 1-shotaccuracy: 49.89 -> 58.80Improved
use only self-training (ablation)SVM · miniImageNet 5-way 1-shotaccuracy: 52.73 -> 49.81Hurt
use only robust extractor (ablation)SVM · miniImageNet 5-way 1-shotaccuracy: 52.73 -> 52.55No clear effect
use base-class images as gallery instead of unlabeled novel (ablation)Self-Jig (SVM) · ImageNet1k novel n=1top-1: 23.8/51.9 -> 17.7/39.1Hurt
increase synthesized images from 0 to 10 (ablation)Self-Jig · miniImageNet 5-way 1-shotaccuracy: 52.55% -> 58.2%Improved
vary number of replaced blocks (ablation)Self-Jig · miniImageNet 5-way 1-shotaccuracyNo clear effect
more shots per classSelf-Jig gain over baseline · ImageNet1ktop-1Hurt

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