Can I read Self-Supervised Learning for Fine-Grained Visual Categorization on EtoBox?

Self-Supervised Learning for Fine-Grained Visual Categorization by Maaz, Muhammad; Rasheed, Hanoona Abdul; Gaddam, Dhanalaxmi is a scholarly article available to read on EtoBox.

What is Self-Supervised Learning for Fine-Grained Visual Categorization about?

Recent research in self-supervised learning (SSL) has shown its capability in learning useful semantic representations from images for classification tasks. Through our work, we study the usefulness of SSL for Fine-Grained Visual Categorization (FGVC). FGVC aims to distinguish objects of visually similar sub categories within a general category. The small inter-class, but large intra-class variations within the dataset makes it a challenging task. The limited availability of annotated labels for such a fine-grained data encourages the need for SSL, where additional supervision can boost learning without the cost of extra annotations. Our baseline achieves $86.36\%$ top-1 classification accuracy on CUB-200-2011 dataset by utilizing random crop augmentation during training and center crop augmentation during testing. In this work, we explore the usefulness of various pretext tasks, specifically, rotation, pretext invariant representation learning (PIRL), and deconstruction and construction learning (DCL) for FGVC. Rotation as an auxiliary task promotes the model to learn global features, and diverts it from focusing on the subtle details. PIRL that uses jigsaw patches attempts to foc

Author

Maaz, Muhammad; Rasheed, Hanoona Abdul; Gaddam, Dhanalaxmi

Published

2021

Language

EN