AI Paper Atlas

Research map / Label-efficient and robust learning / Domain adaptation and generalization

Large Scale Fine-Grained Categorization and Domain-Specific Transfer Learning

Yin Cui, Yang Song, Chen Sun, Andrew Howard, Serge Belongie

CVPR 2018 · Label-efficient and robust learning › Domain adaptation and generalization · approach: Cross-domain few-shot with transformers · 525 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
Increase Inception-v3 input resolution from 299 to 560 (ablation)Inception-v3 on iNat · iNat minivaltop-1 error rate (%): 29.93 -> 25.37Improved
Add fine-tuning on a more balanced subset (ablation)Inception-v4 560 on iNat · iNat minival, head categoriestop-1 error rate (%): 19.28 -> 17.33Improved
Add fine-tuning on a more balanced subset (ablation)Inception-v4 560 on iNat · iNat minival, tail categoriestop-1 error rate (%): 29.89 -> 24.15Improved
Add fine-tuning on a more balanced subset (ablation)Inception-v3 560 on iNat · iNat minivaltop-1 error rate (%): 25.4 (+ 4.5) -> 22.7 (+ 2.7)Improved
Replace Inception-v3 with Inception-v4 (ablation)iNat model with balanced-subset fine-tuning · iNat minivaltop-1 error rate (%): 22.7 (+ 2.7) -> 20.8 (+ 1.9)Improved
Add 12-crop inference (ablation)Inception-v4 560 FT · iNat minivaltop-1 error rate (%): 20.8 (+ 1.9) -> 19.2 (+ 1.6)Improved
Ensemble Inception-v4 and Inception-ResNet-v2 models (ablation)iNat models with 12-crop inference · iNat minivaltop-1 error rate (%): 19.2 (+ 1.6) -> 18.1 (+ 1.1)Improved
Pre-train on the domain-similarity-selected Subset B instead of ImageNetInception-v3 transfer learning · CUB200top-1 accuracy: 82.84 -> 88.76Improved
Pre-train on the domain-similarity-selected Subset B instead of ImageNetInception-v3 transfer learning · Stanford Dogstop-1 accuracy: 84.19 -> 85.23Improved
Pre-train on the domain-similarity-selected source subsetInception-v3 transfer learning · Food101top-1 accuracy: 88.65 -> 88.37No clear effect
Train on combined ImageNet + iNat rather than only one source domain (ablation)ResNet-50 pre-training · ImageNet valtop-1 error rate: 24.33 -> 25.23Hurt
Train on combined ImageNet + iNat rather than only one source domain (ablation)Inception-v3 pre-training · iNaturalist minivaltop-1 error rate: 31.18 -> 30.29Improved

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