Task Adaptive Feature Transformation for One-Shot Learning
This addresses the challenge of overfitting in one-shot learning for computer vision tasks, though it appears incremental as it builds on existing feature adaptation approaches.
The paper tackles the problem of one-shot learning by introducing a non-linear embedding adaptation layer that fine-tunes pre-trained features, significantly improving transductive entropy-based inference in low-shot regimes. It reports consistent improvements over state-of-the-art methods on various benchmarks.
We introduce a simple non-linear embedding adaptation layer, which is fine-tuned on top of fixed pre-trained features for one-shot tasks, improving significantly transductive entropy-based inference for low-shot regimes. Our norm-induced transformation could be understood as a re-parametrization of the feature space to disentangle the representations of different classes in a task specific manner. It focuses on the relevant feature dimensions while hindering the effects of non-relevant dimensions that may cause overfitting in a one-shot setting. We also provide an interpretation of our proposed feature transformation in the basic case of few-shot inference with K-means clustering. Furthermore, we give an interesting bound-optimization link between K-means and entropy minimization. This emphasizes why our feature transformation is useful in the context of entropy minimization. We report comprehensive experiments, which show consistent improvements over a variety of one-shot benchmarks, outperforming recent state-of-the-art methods.