@inproceedings{wei2021aligning,
author = {Wei, Fangyun and Gao, Yue and Wu, Zhirong and Hu, Han and Lin, Stephen},
title = {Aligning Pretraining for Detection via Object-Level Contrastive Learning},
booktitle = {NeurIPS 2021},
year = {2021},
month = {December},
abstract = {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 and models will be made available.},
url = {http://approjects.co.za/?big=en-us/research/publication/aligning-pretraining-for-detection-via-object-level-contrastive-learning/},
}