Jun 11, 2020 · Here we investigate self-training as another method to utilize additional data on the same setup and contrast it against ImageNet pre-training.

An increasingly popular pre-training method is self-supervised learning. Self-supervised learning methods pre-train on a dataset without using labels with the ...

Self-training works well exactly on the same setup that pre-training does not work (using ImageNet to help COCO), and on the PASCAL segmentation dataset, ...

Dec 6, 2020 · Here we investigate self-training as another method to utilize additional data on the same setup and contrast it against ImageNet pre-training.

This paper investigates self-training methods for utilizing additional data and compares self-training against supervised/self-supervised pre-training methods.

Oct 8, 2021 · This paper goes into more depth than those papers — covering data augmentation, different pre-training methods, and different pre-trained ...

Jun 16, 2020 · Here we investigate self-training as another method to utilize additional data on the same setup and contrast it against ImageNet pre-training.

Duration: 17:53
Posted: Jun 18, 2020

Self-training works across dataset sizes and is additive to pre-training. Next we analyze the performance of self-training as we vary the COCO labeled dataset ...

Jun 28, 2020 · This new paper not only talks about pre-training but also investigates self-training and how it compares to pre-training and self-supervised learning for the ...