Self-supervised learning promises to leverage vast amounts of data, but existing methods remain slow and expensive. Introducing contrastive detection, a new objective that learns useful representations for many tasks, with up to 10x less computation: dpmd.ai/3jsOV9l 1/ 
Contrastive detection amplifies the learning signal from each image by carving it into pieces and learning from each simultaneously. This works particularly well when transferring to challenging tasks like detection, segmentation, and depth estimation. 2/
These results raise the possibility of learning algorithms that are more widely accessible, requiring neither human annotations nor vast amounts of computation.
To be presented at #ICCV2021 by @olivierhenaff @skandakoppula @jalayrac @avdnoord @OriolVinyalsML & @joaocarreira 3/3
To be presented at #ICCV2021 by @olivierhenaff @skandakoppula @jalayrac @avdnoord @OriolVinyalsML & @joaocarreira 3/3
• • •
Missing some Tweet in this thread? You can try to
force a refresh
