Domain Adaptive Transfer Learning with Specialist Models

16 Nov 2018Jiquan NgiamDaiyi PengVijay VasudevanSimon KornblithQuoc V. LeRuoming Pang

Transfer learning is a widely used method to build high performing computer vision models. In this paper, we study the efficacy of transfer learning by examining how the choice of data impacts performance... (read more)

PDF Abstract

Results from the Paper


TASK DATASET MODEL METRIC NAME METRIC VALUE GLOBAL RANK USES EXTRA
TRAINING DATA
RESULT LEADERBOARD
Fine-Grained Image Classification Stanford Cars DAT Accuracy 96.2% # 1

Methods used in the Paper


METHOD TYPE
🤖 No Methods Found Help the community by adding them if they're not listed; e.g. Deep Residual Learning for Image Recognition uses ResNet