论文标题
TransBoost：使用深层转导提高最佳成像网性能
TransBoost: Improving the Best ImageNet Performance using Deep Transduction
论文作者
论文摘要
本文讨论了深层的跨传输学习，并提出了TransBoost作为微调任何深神经模型的程序，以提高其在培训时提供的任何（未标记的）测试集上的性能。 TransBoost的灵感来自较大的边缘原理，并且易于使用且易于使用。我们的方法大大改善了在各种体系结构上的分类性能，例如Resnet，MobilenetV3-L，EdgitionNetB0，Vit-S和Convnext-T，从而导致最新的转导性能。此外，我们表明TransBoost在各种图像分类数据集上有效。提供TransBoost的实现，网址为：https：//github.com/omerb01/transboost。
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 .
