AI Paper Atlas

Research map / Label-efficient and robust learning / Recognition and long-tail

Fine-Grained Visual Categorization using Meta-Learning Optimization with Sample Selection of Auxiliary Data

Yabin Zhang, Hui Tang, Kui Jia

ECCV 2018 · Label-efficient and robust learning › Recognition and long-tail · approach: Correspondence and causal representation learning · 115 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
replace fine-tuning with joint training on auxiliary dataResNet-34 · CUB-200-2011 (aux: ImageNet Subset)accuracy: 73.5 -> 74.5Improved
replace joint training with regularized meta-learning objective (MetaFGNet) (ablation)ResNet-34 · CUB-200-2011 (aux: ImageNet Subset)accuracy: 74.5 -> 75.0Improved
add sample selection of auxiliary data (ablation)MetaFGNet · CUB-200-2011 (aux: ImageNet Subset)accuracy: 75.0 -> 75.3Improved
add sample selection of auxiliary data (ablation)Joint training · CUB-200-2011 (aux: ImageNet Subset)accuracy: 74.5 -> 75.0Improved
replace joint training with regularized meta-learning objective (MetaFGNet) (ablation)ResNet-34 · CUB-200-2011 (aux: ImageNet)accuracy: 78.8 -> 79.5Improved
add sample selection of auxiliary data (ablation)MetaFGNet · CUB-200-2011 (aux: ImageNet)accuracy: 79.5 -> 80.3Improved
add sample selection of auxiliary data (ablation)Joint training · CUB-200-2011 (aux: ImageNet)accuracy: 78.8 -> 79.4Improved
use full ImageNet instead of ImageNet Subset as auxiliary data (fine-tuning)ResNet-34 · CUB-200-2011accuracy: 73.5 -> 76.8Improved
use L-Bird Subset as auxiliary data for MetaFGNet instead of ImageNetMetaFGNet · CUB-200-2011accuracy: 79.5 -> 87.2Improved
add MetaFGNet meta-learning on top of fine-tuning on L-Bird SubsetResNet-34 · CUB-200-2011 (aux: L-Bird Subset)accuracy: 86.2 -> 87.2Improved
add sample selection of auxiliary data (ablation)MetaFGNet · CUB-200-2011 (aux: L-Bird Subset)accuracy: 87.2 -> 87.6Improved
add MetaFGNet with sample selection after removing dog classes from ImageNetResNet-34 · Stanford Dogs (ImageNet without 120 dog classes as aux)accuracy: 69.3 -> 73.2Improved

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