Timezone: »

Aligning Pretraining for Detection via Object-Level Contrastive Learning
Fangyun Wei · Yue Gao · Zhirong Wu · Han Hu · Stephen Lin

Tue Dec 07 08:30 AM -- 10:00 AM (PST) @

Image-level contrastive representation learning has proven to be highly effective as a generic model for transfer learning. Such generality for transfer learning, however, sacrifices specificity if we are interested in a certain downstream task. We argue that this could be sub-optimal and thus advocate a design principle which encourages alignment between the self-supervised pretext task and the downstream task. In this paper, we follow this principle with a pretraining method specifically designed for the task of object detection. We attain alignment in the following three aspects: 1) object-level representations are introduced via selective search bounding boxes as object proposals; 2) the pretraining network architecture incorporates the same dedicated modules used in the detection pipeline (e.g. FPN); 3) the pretraining is equipped with object detection properties such as object-level translation invariance and scale invariance. Our method, called Selective Object COntrastive learning (SoCo), achieves state-of-the-art results for transfer performance on COCO detection using a Mask R-CNN framework. Code is available at https://github.com/hologerry/SoCo.

Author Information

Fangyun Wei (Microsoft Research Asia)
Yue Gao (Microsoft Research Asia)
Zhirong Wu (Microsoft)
Han Hu (Microsoft Research Asia)
Stephen Lin (Microsoft Research)

Related Events (a corresponding poster, oral, or spotlight)

More from the Same Authors