PADDLES: Phase-Amplitude Spectrum Disentangled Early Stopping for Learning with Noisy Labels
This addresses the issue of label noise in CNNs for machine learning practitioners, though it is an incremental improvement on existing early stopping strategies.
The paper tackles the problem of convolutional neural networks overfitting to noisy labels by proposing PADDLES, a method that disentangles phase and amplitude spectra for early stopping, which outperforms other methods and achieves state-of-the-art performance on synthetic and real-world datasets.
Convolutional Neural Networks (CNNs) have demonstrated superiority in learning patterns, but are sensitive to label noises and may overfit noisy labels during training. The early stopping strategy averts updating CNNs during the early training phase and is widely employed in the presence of noisy labels. Motivated by biological findings that the amplitude spectrum (AS) and phase spectrum (PS) in the frequency domain play different roles in the animal's vision system, we observe that PS, which captures more semantic information, can increase the robustness of DNNs to label noise, more so than AS can. We thus propose early stops at different times for AS and PS by disentangling the features of some layer(s) into AS and PS using Discrete Fourier Transform (DFT) during training. Our proposed Phase-AmplituDe DisentangLed Early Stopping (PADDLES) method is shown to be effective on both synthetic and real-world label-noise datasets. PADDLES outperforms other early stopping methods and obtains state-of-the-art performance.