Accelerating Self-Supervised Learning via Efficient Training Strategies


KOÇYİĞİT M. T., Hospedales T. M., Bilen H.

23rd IEEE/CVF Winter Conference on Applications of Computer Vision, WACV 2023, Hawaii, Amerika Birleşik Devletleri, 3 - 07 Ocak 2023, ss.5643-5653, (Tam Metin Bildiri)

  • Yayın Türü: Bildiri / Tam Metin Bildiri
  • Doi Numarası: 10.1109/wacv56688.2023.00561
  • Basıldığı Şehir: Hawaii
  • Basıldığı Ülke: Amerika Birleşik Devletleri
  • Sayfa Sayıları: ss.5643-5653
  • Anahtar Kelimeler: Algorithms: Machine learning architectures, and algorithms (including transfer), formulations, Image recognition and understanding (object detection, categorization, segmentation, scene modeling, visual reasoning)
  • Boğaziçi Üniversitesi Adresli: Evet

Özet

Recently the focus of the computer vision community has shifted from expensive supervised learning towards self-supervised learning of visual representations. While the performance gap between supervised and self-supervised has been narrowing, the time for training self-supervised deep networks remains an order of magnitude larger than its supervised counterparts, which hinders progress, imposes carbon cost, and limits societal benefits to institutions with substantial resources. Motivated by these issues, this paper investigates reducing the training time of recent self-supervised methods by various model-agnostic strategies that have not been used for this problem. In particular, we study three strategies: an extendable cyclic learning rate schedule, a matching progressive augmentation magnitude and image resolutions schedule, and a hard positive mining strategy based on augmentation difficulty. We show that all three methods combined lead up to 2.7 times speed-up in the training time of several self-supervised methods while retaining comparable performance to the standard self-supervised learning setting.