TransBoost: Improving the Best ImageNet Performance using Deep Transduction
This addresses the challenge of boosting model accuracy for image classification tasks when test data is available during training, offering a practical solution for researchers and practitioners.
The paper tackles the problem of improving deep neural network performance on unlabeled test sets via transductive learning, proposing TransBoost, which significantly enhances ImageNet classification across various architectures and achieves state-of-the-art results.
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 .