Timezone: »

TransBoost: Improving the Best ImageNet Performance using Deep Transduction
Omer Belhasin · Guy Bar-Shalom · Ran El-Yaniv

Thu Dec 01 02:00 PM -- 04:00 PM (PST) @ Hall J #912

This paper deals with deep transductive learning, and proposes TransBoost as a procedure for fine-tuning any deep neural model to improve its performance on any (unlabeled) test set provided at training time. TransBoost is inspired by a large margin principle and is efficient and simple to use. Our method significantly improves the ImageNet classification performance on a wide range of architectures, such as ResNets, MobileNetV3-L, EfficientNetB0, ViT-S, and ConvNext-T, leading to state-of-the-art transductive performance.Additionally we show that TransBoost is effective on a wide variety of image classification datasets. The implementation of TransBoost is provided at: https://github.com/omerb01/TransBoost .

Author Information

Omer Belhasin (Computer Science Departmen, Technion-Israel Institute of Technology)
Omer Belhasin

PhD student researcher at Technion & Verily/Google researcher in Deep Learning

Guy Bar-Shalom (Technion, Technion)
Ran El-Yaniv (Technion & Deci.AI)

More from the Same Authors