Instance Localization for Self-supervised Detection Pretraining

02/16/2021
by   Ceyuan Yang, et al.
10

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.

READ FULL TEXT

page 3

page 4

research
05/10/2022

CoDo: Contrastive Learning with Downstream Background Invariance for Detection

The prior self-supervised learning researches mainly select image-level ...
research
04/11/2023

MOST: Multiple Object localization with Self-supervised Transformers for object discovery

We tackle the challenging task of unsupervised object localization in th...
research
06/08/2021

DETReg: Unsupervised Pretraining with Region Priors for Object Detection

Unsupervised pretraining has recently proven beneficial for computer vis...
research
07/17/2020

Improving Object Detection with Selective Self-supervised Self-training

We study how to leverage Web images to augment human-curated object dete...
research
02/05/2021

Custom Object Detection via Multi-Camera Self-Supervised Learning

This paper proposes MCSSL, a self-supervised learning approach for build...
research
06/04/2021

Aligning Pretraining for Detection via Object-Level Contrastive Learning

Image-level contrastive representation learning has proven to be highly ...
research
06/25/2022

Self-Supervised 3D Monocular Object Detection by Recycling Bounding Boxes

Modern object detection architectures are moving towards employing self-...

Please sign up or login with your details

Forgot password? Click here to reset