Generalized Few-Shot Semantic Segmentation: All You Need is Fine-Tuning

Autor:	Myers-Dean, Josh, Zhao, Yinan, Price, Brian, Cohen, Scott, Gurari, Danna
Rok vydání:	2021
Předmět:	Computer Science - Computer Vision and Pattern Recognition Computer Science - Machine Learning
Druh dokumentu:	Working Paper
Popis:	Generalized few-shot semantic segmentation was introduced to move beyond only evaluating few-shot segmentation models on novel classes to include testing their ability to remember base classes. While the current state-of-the-art approach is based on meta-learning, it performs poorly and saturates in learning after observing only a few shots. We propose the first fine-tuning solution, and demonstrate that it addresses the saturation problem while achieving state-of-the-art results on two datasets, PASCAL-5i and COCO-20i. We also show that it outperforms existing methods, whether fine-tuning multiple final layers or only the final layer. Finally, we present a triplet loss regularization that shows how to redistribute the balance of performance between novel and base categories so that there is a smaller gap between them. Comment: Includes supplementary materials
Databáze:	arXiv
Externí odkaz:	http://arxiv.org/abs/2112.10982 Zobrazit plný text záznamu View this record from Arxiv