Learning Noisy Few-Shot Classification Without Relying on Pseudo-Noise Data

Recently, noisy few-shot learning (NFSL) has been exploring the model robustness to label noise, breaking the limitation of completely accurate labeling in small sample scenarios. Existing NFSL methods directly employ delicately designed pseudo-noise to simulate and adapt to noisy environments. However, determining the optimal combination of pseudo-noise is challenging and improperly configuring pseudo-noise may lead to adverse effects on the training models. To deal with the problems, this letter proposes a novel <bold xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink">A</b>daptive <bold xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink">M</b>ult<bold xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink">I</b>-view <bold xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink">D</b>enoising <bold xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink">E</b>valuation (AMIDE) framework, which establishes an adaptive and robust embedding and classifier without relying on pseudo-noise. In the training phase, we design an adaptive label smoothing scheme, where soft labels with learnable smooth coefficients are inferred from data distribution to mitigate overconfident labeling. In the testing stage, we propose a multi-view fused evaluation scheme, where different network layers are treated as distinct views to generate potential clean features and modify prototypes, thereby enhancing the accuracy of evaluation. In this way, the impact of noise is effectively alleviated from two perspectives. Extensive experiments on several few-shot classification benchmarks show the superiority and robustness of our method.