May the Forgetting Be with You: Alternate Replay for Learning with Noisy Labels


Monica Millunzi (University of Modena and Reggio Emilia), Lorenzo Bonicelli (University of Modena and Reggio Emilia), Angelo Porrello (University of Modena and Reggio Emilia, AimageLab), Jacopo Credi (Chalmers University of Technology), Petter N. Kolm (NYU Courant), Simone Calderara (University of Modena and Reggio Emilia)
The 35th British Machine Vision Conference
PDFPosterVideo (Right click to download)Supplementary

Abstract

Forgetting presents a significant challenge during incremental training, making it particularly demanding for contemporary AI systems to assimilate new knowledge in streaming data environments. To address this issue, most approaches in Continual Learning (CL) rely on the replay of a restricted buffer of past data. However, the presence of noise in real-world scenarios, where human annotation is constrained by time limitations or where data is automatically gathered from the web, frequently renders these strategies vulnerable. In this study, we address the problem of CL under Noisy Labels (CLN) by introducing Alternate Experience Replay (AER), which *takes advantage of forgetting* to maintain a clear distinction between clean, complex, and noisy samples in the memory buffer. The idea is that complex or mislabeled examples, which hardly fit the previously learned data distribution, are most likely to be forgotten. To grasp the benefits of such a separation, we equip AER with Asymmetric Balanced Sampling (ABS): a new sample selection strategy that prioritizes purity on the current task while retaining relevant samples from the past. Through extensive computational comparisons, we demonstrate the effectiveness of our approach in terms of both accuracy and purity of the obtained buffer, resulting in a remarkable average gain of $4.71$% points in accuracy with respect to existing loss-based purification strategies. Code is available at https://github.com/aimagelab/mammoth.

Citation

@inproceedings{Millunzi_2024_BMVC,
author    = {Monica Millunzi and Lorenzo Bonicelli and Angelo Porrello and Jacopo Credi and Petter N. Kolm and Simone Calderara},
title     = {May the Forgetting Be with You: Alternate Replay for Learning with Noisy Labels},
booktitle = {35th British Machine Vision Conference 2024, {BMVC} 2024, Glasgow, UK, November 25-28, 2024},
publisher = {BMVA},
year      = {2024},
url       = {https://papers.bmvc2024.org/0680.pdf}
}


Copyright © 2024 The British Machine Vision Association and Society for Pattern Recognition
The British Machine Vision Conference is organised by The British Machine Vision Association and Society for Pattern Recognition. The Association is a Company limited by guarantee, No.2543446, and a non-profit-making body, registered in England and Wales as Charity No.1002307 (Registered Office: Dept. of Computer Science, Durham University, South Road, Durham, DH1 3LE, UK).

Imprint | Data Protection