Details

Autor(en) / Beteiligte

• Singh, Mannat
• Gustafson, Laura
• Adcock, Aaron
• De Freitas Reis, Vinicius
• Gedik, Bugra
• Kosaraju, Raj Prateek
• Mahajan, Dhruv
• Girshick, Ross
• Dollar, Piotr
• Van Der Maaten, Laurens

Titel

Revisiting Weakly Supervised Pre-Training of Visual Perception Models

Ist Teil von

• 2022 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR), 2022, p.794-804

Ort / Verlag

IEEE

Erscheinungsjahr

2022

Link zum Volltext

• IEEE_Xplore

Quelle

IEEE Electronic Library (IEL)

Beschreibungen/Notizen

• Model pre-training is a cornerstone of modern visual recognition systems. Although fully supervised pre-training on datasets like ImageNet is still the de-facto standard, recent studies suggest that large-scale weakly supervised pretraining can outperform fully supervised approaches. This paper revisits weakly-supervised pre-training of models using hashtag supervision with modern versions of residual networks and the largest-ever dataset of images and corresponding hashtags. We study the performance of the resulting models in various transfer-learning settings including zero-shot transfer. We also compare our models with those obtained via large-scale self-supervised learning. We find our weakly-supervised models to be very competitive across all settings, and find they substantially outperform their self-supervised counterparts. We also include an investigation into whether our models learned potentially troubling associations or stereotypes. Overall, our results provide a compelling argument for the use of weakly supervised learning in the development of visual recognition systems. Our models, Supervised Weakly through hashtAGs (SWAG), are available publicly.