Negative Margin Matters: Understanding Margin in Few-shot Classification
This addresses the challenge of few-shot learning for AI systems by showing that negative margins, contrary to common practice, improve novel class discrimination.
The paper tackles the problem of few-shot classification by introducing a negative margin loss in metric learning, which achieves state-of-the-art accuracy on three standard benchmarks, outperforming regular softmax loss.
This paper introduces a negative margin loss to metric learning based few-shot learning methods. The negative margin loss significantly outperforms regular softmax loss, and achieves state-of-the-art accuracy on three standard few-shot classification benchmarks with few bells and whistles. These results are contrary to the common practice in the metric learning field, that the margin is zero or positive. To understand why the negative margin loss performs well for the few-shot classification, we analyze the discriminability of learned features w.r.t different margins for training and novel classes, both empirically and theoretically. We find that although negative margin reduces the feature discriminability for training classes, it may also avoid falsely mapping samples of the same novel class to multiple peaks or clusters, and thus benefit the discrimination of novel classes. Code is available at https://github.com/bl0/negative-margin.few-shot.