Learning to learn via Self-Critique

24 May 2019  ·  Antreas Antoniou, Amos Storkey ·

In few-shot learning, a machine learning system learns from a small set of labelled examples relating to a specific task, such that it can generalize to new examples of the same task. Given the limited availability of labelled examples in such tasks, we wish to make use of all the information we can. Usually a model learns task-specific information from a small training-set (support-set) to predict on an unlabelled validation set (target-set). The target-set contains additional task-specific information which is not utilized by existing few-shot learning methods. Making use of the target-set examples via transductive learning requires approaches beyond the current methods; at inference time, the target-set contains only unlabelled input data-points, and so discriminative learning cannot be used. In this paper, we propose a framework called Self-Critique and Adapt or SCA, which learns to learn a label-free loss function, parameterized as a neural network. A base-model learns on a support-set using existing methods (e.g. stochastic gradient descent combined with the cross-entropy loss), and then is updated for the incoming target-task using the learnt loss function. This label-free loss function is itself optimized such that the learnt model achieves higher generalization performance. Experiments demonstrate that SCA offers substantially reduced error-rates compared to baselines which only adapt on the support-set, and results in state of the art benchmark performance on Mini-ImageNet and Caltech-UCSD Birds 200.

PDF Abstract
Task Dataset Model Metric Name Metric Value Global Rank Result Benchmark
Few-Shot Image Classification CUB 200 5-way 1-shot Self-Critique and Adapt + High-End MAML++ Accuracy 70.46 # 26
Few-Shot Image Classification CUB 200 5-way 1-shot High-End MAML++ Accuracy 67.48 # 29
Few-Shot Image Classification CUB 200 5-way 5-shot Self-Critique and Adapt + High-End MAML++ Accuracy 85.63 # 23
Few-Shot Image Classification CUB 200 5-way 5-shot High-End MAML++ Accuracy 83.8 # 24
Few-Shot Image Classification Mini-Imagenet 5-way (1-shot) Self-Critique and Adapt + High-End MAML++ Accuracy 62.86 # 60
Few-Shot Image Classification Mini-Imagenet 5-way (5-shot) Self-Critique and Adapt + High-End MAML++ Accuracy 77.64 # 58

Methods


No methods listed for this paper. Add relevant methods here