Instance-Level Embedding Adaptation for Few-Shot Learning
Open Access
- 21 March 2019
- journal article
- research article
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Access
- Vol. 7, 100501-100511
Abstract
Few-shot learning aims to recognize novel categories from just a few labeled instances. Existing metric learning-based approaches perform classifications by nearest neighbor search in the embedding space. The embedding function is a deep neural network and usually shared by all novel categories. However, these brute approaches lack a fast adaptation mechanism like meta-learning when dealing with novel categories. To tackle this, we present a novel instance-level embedding adaptation mechanism, aiming at rapidly adapting embedding deep features to improve their generalization ability in recognizing novel categories. To this end, we design an Attention Adaptation Module to pull a query instance and its corresponding class center as close as possible. Note that, each query instance is pulled closer to its corresponding class center before performing nearest neighbor classifications. This instance-level reduction of intra-class distance increases the probability of correct classifications, and thus improves the generalization ability to embed deep features and promoting the performance. The extensive experiments are conducted on two benchmark datasets: miniImageNet and CUB. Our approach yields very promising results on both datasets. In addition, in a realistic cross-domain evaluation setting, our method also achieves the-state-of-the-art performance.Keywords
Funding Information
- National Basic Research Program of China (2018YFB1308000)
- National Natural Science Foundation of China (61772508, U1713213)
- Guangdong Technology Project (2016B010108010, 2017B010110007, 2016B010125003)
- Shenzhen Technology Project (JCYJ20170413152535587, JCYJ20180507182610734)
- CAS Key Technology Talent Program, Shenzhen Engineering Laboratory for 3D Content Generating Technologies ([2017]476)
- Chinese Academy of Sciences (2014DP173025)
This publication has 19 references indexed in Scilit:
- New Secret Sharing Scheme Based on Faster R-CNNs Image RetrievalIEEE Access, 2018
- Human Action Recognition by Learning Spatio-Temporal Features With Deep Neural NetworksIEEE Access, 2018
- Skeleton embedded motion body partition for human action recognition using depth sequencesSignal Processing, 2018
- Low-Shot Visual Recognition by Shrinking and Hallucinating Features2017
- Deep Residual Learning for Image Recognition2016
- Wide Residual Networks2016
- Manifold Ranking-Based Matrix Factorization for Saliency DetectionIEEE Transactions on Neural Networks and Learning Systems, 2015
- A Survey on Transfer LearningIEEE Transactions on Knowledge and Data Engineering, 2009
- ImageNet: A large-scale hierarchical image database2009
- One-shot learning of object categoriesIEEE Transactions on Pattern Analysis and Machine Intelligence, 2006