ePrints@IIScePrints@IISc Home | About | Browse | Latest Additions | Advanced Search | Contact | Help

SML: Semantic meta-learning for few-shot semantic segmentation�

Pambala, AK and Dutta, T and Biswas, S (2021) SML: Semantic meta-learning for few-shot semantic segmentation�. In: Pattern Recognition Letters, 147 . pp. 93-99.

pat_rec_let_2021.pdf - Published Version

Download (1MB) | Preview
Official URL: https://doi.org/10.1016/j.patrec.2021.03.036


The significant amount of training data required for training Convolutional Neural Networks has become a bottleneck for applications like semantic segmentation. Few-shot semantic segmentation algorithms address this problem, with an aim to achieve good performance in the low-data regime, with few annotated training images. Recent approaches based on class-prototypes computed from available training data have achieved immense success for this task. In this work, we propose a novel meta-learning framework, Semantic Meta-Learning (SML), which incorporates class level semantic descriptions in the generated prototypes for this problem. In addition, we propose to use the well-established technique, ridge regression, to not only bring in the class-level semantic information, but also to effectively utilise the information available from multiple images present in the training data for prototype computation. This has a simple closed-form solution, and thus can be implemented easily and efficiently. Extensive experiments on the benchmark PASCAL-5i dataset under different experimental settings demonstrate the effectiveness of the proposed framework. © 2021

Item Type: Journal Article
Publication: Pattern Recognition Letters
Publisher: Elsevier B.V.
Additional Information: The copyright for this article belongs to Authors
Keywords: Image segmentation; Neural networks; Regression analysis; Semantic Web, Attribute; Class level; Convolutional neural network; Few-shot learning; Learning semantics; Metalearning; Performance; Segmentation algorithms; Semantic segmentation; Training data, Semantics
Department/Centre: Division of Electrical Sciences > Electrical Engineering
Date Deposited: 23 Jul 2021 08:44
Last Modified: 23 Jul 2021 08:44
URI: http://eprints.iisc.ac.in/id/eprint/68864

Actions (login required)

View Item View Item