A Self-supervised Learning System for Object Detection in Videos Using Random Walks on Graphs

TL;DR

This paper introduces a self-supervised learning system that leverages graph-based random walks on object sequences from videos to improve clustering of unseen object categories.

Contribution

The novel system uses depth-based segmentation, sequence tracking, and graph random walks to generate triplet training data for unsupervised object detection.

Findings

Improves clustering accuracy of unknown objects

Outperforms recent unsupervised clustering methods

Effective on multiple public datasets

Abstract

This paper presents a new self-supervised system for learning to detect novel and previously unseen categories of objects in images. The proposed system receives as input several unlabeled videos of scenes containing various objects. The frames of the videos are segmented into objects using depth information, and the segments are tracked along each video. The system then constructs a weighted graph that connects sequences based on the similarities between the objects that they contain. The similarity between two sequences of objects is measured by using generic visual features, after automatically re-arranging the frames in the two sequences to align the viewpoints of the objects. The graph is used to sample triplets of similar and dissimilar examples by performing random walks. The triplet examples are finally used to train a siamese neural network that projects the generic visual features into a low-dimensional manifold. Experiments on three public datasets, YCB-Video, CORe50 and RGBD-Object, show that the projected low-dimensional features improve the accuracy of clustering unknown objects into novel categories, and outperform several recent unsupervised clustering techniques.