DetCo: Unsupervised Contrastive Learning for Object Detection

by   Enze Xie, et al.

Unsupervised contrastive learning achieves great success in learning image representations with CNN. Unlike most recent methods that focused on improving accuracy of image classification, we present a novel contrastive learning approach, named DetCo, which fully explores the contrasts between global image and local image patches to learn discriminative representations for object detection. DetCo has several appealing benefits. (1) It is carefully designed by investigating the weaknesses of current self-supervised methods, which discard important representations for object detection. (2) DetCo builds hierarchical intermediate contrastive losses between global image and local patches to improve object detection, while maintaining global representations for image recognition. Theoretical analysis shows that the local patches actually remove the contextual information of an image, improving the lower bound of mutual information for better contrastive learning. (3) Extensive experiments on PASCAL VOC, COCO and Cityscapes demonstrate that DetCo not only outperforms state-of-the-art methods on object detection, but also on segmentation, pose estimation, and 3D shape prediction, while it is still competitive on image classification. For example, on PASCAL VOC, DetCo-100ep achieves 57.4 mAP, which is on par with the result of MoCov2-800ep. Moreover, DetCo consistently outperforms supervised method by 1.6/1.2/1.0 AP on Mask RCNN-C4/FPN/RetinaNet with 1x schedule. Code will be released at \href{}{\color{blue}{\tt}} and \href{}{\color{blue}{\tt}}.


page 8

page 11

page 12

page 13

page 14


Unsupervised Pretraining for Object Detection by Patch Reidentification

Unsupervised representation learning achieves promising performances in ...

Online Bag-of-Visual-Words Generation for Unsupervised Representation Learning

Learning image representations without human supervision is an important...

What makes for good views for contrastive learning

Contrastive learning between multiple views of the data has recently ach...

Conditional Negative Sampling for Contrastive Learning of Visual Representations

Recent methods for learning unsupervised visual representations, dubbed ...

Revisiting Contrastive Methods for Unsupervised Learning of Visual Representations

Contrastive self-supervised learning has outperformed supervised pretrai...

Crafting GBD-Net for Object Detection

The visual cues from multiple support regions of different sizes and res...

nnDetection: A Self-configuring Method for Medical Object Detection

Simultaneous localisation and categorization of objects in medical image...

Code Repositories


A PyTorch implementation of DetCo

view repo