Let Go of Your Labels with Unsupervised Transfer
Foundation vision-language models have enabled remarkable zero-shot transferability of the pre-trained representations to a wide range of downstream tasks. However, to solve a new task, zero-shot transfer still necessitates human guidance to define visual categories that appear in the data. Here, we show that fully unsupervised transfer emerges when searching for the labeling of a dataset that induces maximal margin classifiers in representation spaces of different foundation models. We present TURTLE, a fully unsupervised method that effectively employs this guiding principle to uncover the underlying labeling of a downstream dataset without any supervision and task-specific representation learning. We evaluate TURTLE on a diverse benchmark suite of 26 datasets and show that it achieves new state-of-the-art unsupervised performance. Furthermore, TURTLE, although being fully unsupervised, outperforms zero-shot transfer baselines on a wide range of datasets. In particular, TURTLE matches the average performance of CLIP zero-shot on 26 datasets by employing the same representation space, spanning a wide range of architectures and model sizes. By guiding the search for the underlying labeling using the representation spaces of two foundation models, TURTLE surpasses zero-shot transfer and unsupervised prompt tuning baselines, demonstrating the surprising power and effectiveness of unsupervised transfer.
PDF Abstract International Conference 2024 PDF International Conference 2024 Abstract
CIFAR-10
ImageNet
CIFAR-100
MNIST
KITTI
UCF101
Kinetics
Oxford 102 Flower
STL-10
DTD
Stanford Cars
Food-101
Caltech-101
EuroSAT
FGVC-Aircraft
GTSRB
Hateful Memes
FER2013
RESISC45
PCam
Kinetics-700
Birdsnap
SUN397
Country211
Rendered SST2
