Share your thoughts, 1 month free Claude Pro on usSee more
WorkDL logo mark

Visual Representation Learning with Self-Supervised Attention for Low-Label High-data Regime

About

Self-supervision has shown outstanding results for natural language processing, and more recently, for image recognition. Simultaneously, vision transformers and its variants have emerged as a promising and scalable alternative to convolutions on various computer vision tasks. In this paper, we are the first to question if self-supervised vision transformers (SSL-ViTs) can be adapted to two important computer vision tasks in the low-label, high-data regime: few-shot image classification and zero-shot image retrieval. The motivation is to reduce the number of manual annotations required to train a visual embedder, and to produce generalizable and semantically meaningful embeddings. For few-shot image classification we train SSL-ViTs without any supervision, on external data, and use this trained embedder to adapt quickly to novel classes with limited number of labels. For zero-shot image retrieval, we use SSL-ViTs pre-trained on a large dataset without any labels and fine-tune them with several metric learning objectives. Our self-supervised attention representations outperforms the state-of-the-art on several public benchmarks for both tasks, namely miniImageNet and CUB200 for few-shot image classification by up-to 6%-10%, and Stanford Online Products, Cars196 and CUB200 for zero-shot image retrieval by up-to 4%-11%. Code is available at \url{https://github.com/AutoVision-cloud/SSL-ViT-lowlabel-highdata}.

Prarthana Bhattacharyya, Chenge Li, Xiaonan Zhao, Istv\'an Feh\'erv\'ari, Jason Sun• 2022

Related benchmarks

TaskDatasetResultRank
Few-shot Image ClassificationAIDER subset simulation
Average Accuracy (AA)77.2
36
Image ClassificationMEDIC subset
AA65.4
36
Few-shot classificationCDD 5-way 1-shot
AA63.8
19
Few-shot classificationCDD 5-way 5-shot
Average Accuracy (AA)73.6
17
Showing 4 of 4 rows

Other info

Follow for update