Transfer learning based few-shot classification using optimal transport mapping from preprocessed latent space of backbone neural network

9 Feb 2021  ·  Tomáš Chobola, Daniel Vašata, Pavel Kordík ·

MetaDL Challenge 2020 focused on image classification tasks in few-shot settings. This paper describes second best submission in the competition... Our meta learning approach modifies the distribution of classes in a latent space produced by a backbone network for each class in order to better follow the Gaussian distribution. After this operation which we call Latent Space Transform algorithm, centers of classes are further aligned in an iterative fashion of the Expectation Maximisation algorithm to utilize information in unlabeled data that are often provided on top of few labelled instances. For this task, we utilize optimal transport mapping using the Sinkhorn algorithm. Our experiments show that this approach outperforms previous works as well as other variants of the algorithm, using K-Nearest Neighbour algorithm, Gaussian Mixture Models, etc. read more

PDF Abstract
Task Dataset Model Metric Name Metric Value Global Rank Result Benchmark
Few-Shot Image Classification CIFAR-FS 5-way (1-shot) LST+MAP Accuracy 87.79 # 1
Few-Shot Image Classification CIFAR-FS 5-way (5-shot) LST+MAP Accuracy 90.73 # 2
Few-Shot Image Classification CUB 200 5-way 1-shot LST+MAP Accuracy 91.68 # 2
Few-Shot Image Classification CUB 200 5-way 5-shot LST+MAP Accuracy 94.09 # 2

Methods


No methods listed for this paper. Add relevant methods here