ODIP: Towards Automatic Adaptation for Object Detection by Interactive Perception

TL;DR

ODIP introduces an interactive perception-based object detection method that adapts to new domains automatically by interacting with a grasping system, eliminating the need for human annotations and outperforming existing approaches.

Contribution

This work presents a novel interactive perception framework for object detection that enables automatic domain adaptation without human-labeled data.

Findings

ODIP outperforms generic object detectors.

ODIP surpasses state-of-the-art few-shot detectors.

ODIP adapts to novel objects without human annotations.

Abstract

Object detection plays a deep role in visual systems by identifying instances for downstream algorithms. In industrial scenarios, however, a slight change in manufacturing systems would lead to costly data re-collection and human annotation processes to re-train models. Existing solutions such as semi-supervised and few-shot methods either rely on numerous human annotations or suffer low performance. In this work, we explore a novel object detector based on interactive perception (ODIP), which can be adapted to novel domains in an automated manner. By interacting with a grasping system, ODIP accumulates visual observations of novel objects, learning to identify previously unseen instances without human-annotated data. Extensive experiments show ODIP outperforms both the generic object detector and state-of-the-art few-shot object detector fine-tuned in traditional manners. A demo video is provided to further illustrate the idea.