Unsupervised Embedding Adaptation via Early-Stage Feature Reconstruction for Few-Shot Classification
This work addresses the challenge of adapting embeddings for few-shot learning, which is crucial for AI systems that need to learn from limited data, though it is incremental as it builds on existing methods.
The paper tackles the problem of few-shot classification by proposing unsupervised embedding adaptation, achieving state-of-the-art performance with 1.2% to 2.0% accuracy improvements over previous methods in 1-shot settings on datasets like mini-ImageNet.
We propose unsupervised embedding adaptation for the downstream few-shot classification task. Based on findings that deep neural networks learn to generalize before memorizing, we develop Early-Stage Feature Reconstruction (ESFR) -- a novel adaptation scheme with feature reconstruction and dimensionality-driven early stopping that finds generalizable features. Incorporating ESFR consistently improves the performance of baseline methods on all standard settings, including the recently proposed transductive method. ESFR used in conjunction with the transductive method further achieves state-of-the-art performance on mini-ImageNet, tiered-ImageNet, and CUB; especially with 1.2%~2.0% improvements in accuracy over the previous best performing method on 1-shot setting.