Abstract: We present DetCo, a simple yet effective self-supervised approach for object detection. Unsupervised pre-training methods have been recently designed for object detection, but they are ...
The opening of a new mass transit line in a major city should be a moment of celebration for residents. But if — and forgive us if we still count this as a significant “if” — the Eglinton Crosstown ...
Abstract: One-stage object detection is commonly implemented by optimizing two sub-tasks: object classification and localization, using heads with two parallel branches, which might lead to a certain ...
Some results have been hidden because they may be inaccessible to you
Show inaccessible results