Auto-FSL: Searching the Attribute Consistent Network for Few-Shot Learning
- 29 April 2021
- journal article
- research article
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Circuits and Systems for Video Technology
- Vol. 32 (3) , 1213-1223
Abstract
Prevailing deep methods for image recognition require massive labeled samples in each visual category for training. However, large amounts of data annotations are timeconsuming, and some uncommon categories only have rare samples available. For this issue, we focus on more challenging few-shot learning (FSL) task, where just few labeled images are used in the training stage. Existing FSL models are constructed with various convolutional neural networks (CNNs), which are trained on an auxiliary base dataset and evaluated for new fewshot predictions on a novel dataset. The performance of these models is difficult to break through because of the domain shift between base and novel datasets and the monotonous network architectures. Considering that, we propose a novel automatic attribute consistent network called Auto-ACNet to overcome the above problems. On one hand, Auto-ACNet utilizes the attribute information about base and novel categories to guide the procedure of representation learning. It introduces the consistent and non-consistent subnets to capture the common and different attributes of image pair, which helps to mitigate the domain shift problem. On the other hand, the architecture of Auto-ACNet is searched with the popular neural architecture search (NAS) technique DARTS, for obtaining a superior FSL network automatically. And the DARTS’s search space is improved by adding the position-aware module to extract the attribute characteristics better. Extensive experimental results on two datasets indicate that the proposed Auto-ACNet achieves significant improvement over the state-of-the-art competitors in this literature.Keywords
Funding Information
- Consulting research project of Chinese academy of engineering The Online and Offline Mixed Educational Service System for The Belt and Road Training in MOOC China
- Project of China Knowledge Centre for Engineering Science and Technology
- Innovation Research Team of Ministry of Education (IRT_17R86)
- Innovative Research Group of the National Natural Science Foundation of China (61721002)
- National Natural Science Foundation of China (61877050, 61937001, 62050194)
- China Postdoctoral Science Foundation (2020M683493)
- National Key Research and Development Program of China (2020AAA0108800)
This publication has 42 references indexed in Scilit:
- Compound Memory Networks for Few-Shot Video Classification2018
- Zero-Shot Learning—A Comprehensive Evaluation of the Good, the Bad and the UglyIEEE Transactions on Pattern Analysis and Machine Intelligence, 2018
- Semantics-Aware Visual Object TrackingIEEE Transactions on Circuits and Systems for Video Technology, 2018
- Learning to Compare: Relation Network for Few-Shot Learning2018
- A Generative Approach to Zero-Shot and Few-Shot Action Recognition2018
- Simple to complex cross-modal learning to rankComputer Vision and Image Understanding, 2017
- Learning Robust Visual-Semantic Embeddings2017
- T-CNN: Tubelets With Convolutional Neural Networks for Object Detection From VideosIEEE Transactions on Circuits and Systems for Video Technology, 2017
- Semantic Pooling for Complex Event Analysis in Untrimmed VideosIEEE Transactions on Pattern Analysis and Machine Intelligence, 2016
- One-shot learning of object categoriesIEEE Transactions on Pattern Analysis and Machine Intelligence, 2006