Abstract | ||
---|---|---|
Few-shot learning (FSL) aims to recognize target classes by adapting the prior knowledge learned from source classes. Such knowledge usually resides in a deep embedding model for a general matching purpose of the support and query image pairs. The objective of this paper is to repurpose the contrastive learning for such matching to learn a few-shot embedding model. We make the following contributions: (i) We investigate the contrastive learning with Noise Contrastive Estimation (NCE) in a supervised manner for training a fewshot embedding model; (ii) We propose a novel contrastive training scheme dubbed infoPatch, exploiting the patch-wise relationship to substantially improve the popular infoNCE; (iii) We show that the embedding learned by the proposed infoPatch is more effective; (iv) Our model is thoroughly evaluated on few-shot recognition task; and demonstrates state-of-the-art results on minilmageNet and appealing performance on tie redlmageNet, Fewshot-CIFAR100 (FC-100). |
Year | Venue | DocType |
---|---|---|
2021 | THIRTY-FIFTH AAAI CONFERENCE ON ARTIFICIAL INTELLIGENCE, THIRTY-THIRD CONFERENCE ON INNOVATIVE APPLICATIONS OF ARTIFICIAL INTELLIGENCE AND THE ELEVENTH SYMPOSIUM ON EDUCATIONAL ADVANCES IN ARTIFICIAL INTELLIGENCE | Conference |
Volume | ISSN | Citations |
35 | 2159-5399 | 0 |
PageRank | References | Authors |
0.34 | 0 | 7 |
Name | Order | Citations | PageRank |
---|---|---|---|
Chen Liu | 1 | 0 | 1.35 |
Yanwei Fu | 2 | 543 | 51.93 |
Chengming Xu | 3 | 0 | 1.35 |
Siqian Yang | 4 | 0 | 0.68 |
Jilin Li | 5 | 48 | 8.94 |
Chengjie Wang | 6 | 43 | 19.03 |
Li Zhang | 7 | 4 | 1.39 |