Instance Localization for Self-supervised Detection Pretraining

Abstract

Prior research on self-supervised learning has led to considerable progress on image classification, but often with degraded transfer performance on object detection. The objective of this paper is to advance self-supervised pretrained models specifically for object detection. Based on the inherent difference between classification and detection, we propose a new self-supervised pretext task, called instance localization. Image instances are pasted at various locations and scales onto background images. The pretext task is to predict the instance category given the composited images as well as the foreground bounding boxes. We show that integration of bounding boxes into pretraining promotes better task alignment and architecture alignment for transfer learning. In addition, we propose an augmentation method on the bounding boxes to further enhance the feature alignment. As a result, our model becomes weaker at Imagenet semantic classification but stronger at image patch localization, with an overall stronger pretrained model for object detection. Experimental results demonstrate that our approach yields state-of-the-art transfer learning results for object detection on PASCAL VOC and MSCOCO.

arXiv commentTo appear in CVPR 2021. Code is available at https://github.com/limbo0000/InstanceLoc

References in corpus (10)

• Faster R-CNN: Towards Real-Time Object Detection with Region Proposal Networks
• Rethinking Atrous Convolution for Semantic Image Segmentation
• A Simple Framework for Contrastive Learning of Visual Representations
• Improved Baselines with Momentum Contrastive Learning
• SGDR: Stochastic Gradient Descent with Warm Restarts
• What Makes for Good Views for Contrastive Learning?
• What makes instance discrimination good for transfer learning?
• Revisiting Feature Alignment for One-stage Object Detection
• Video Representation Learning with Visual Tempo Consistency
• Distilling Localization for Self-Supervised Representation Learning

Cited by in corpus (2)

• MST: Masked Self-Supervised Transformer for Visual Representation
• Unsupervised Object-Level Representation Learning from Scene Images