Semi Supervised Deep Quick Instance Detection and Segmentation

TL;DR

This paper introduces a semi-supervised deep learning framework for rapid instance detection and segmentation that learns incrementally from real-time data, synthesizes cluttered scenes, and improves over previous versions with online learning capabilities.

Contribution

The paper presents a novel semi-supervised, online learning framework with clutter synthesis and instance detection, advancing real-time incremental learning in dense clutter environments.

Findings

Achieved top rankings in Amazon Robotics Challenge 2017.

Enhanced framework with online learning and instance detection features.

Demonstrated real-time scene synthesis and incremental learning capabilities.

Abstract

In this paper, we present a semi supervised deep quick learning framework for instance detection and pixel-wise semantic segmentation of images in a dense clutter of items. The framework can quickly and incrementally learn novel items in an online manner by real-time data acquisition and generating corresponding ground truths on its own. To learn various combinations of items, it can synthesize cluttered scenes, in real time. The overall approach is based on the tutor-child analogy in which a deep network (tutor) is pretrained for class-agnostic object detection which generates labeled data for another deep network (child). The child utilizes a customized convolutional neural network head for the purpose of quick learning. There are broadly four key components of the proposed framework semi supervised labeling, occlusion aware clutter synthesis, a customized convolutional neural network head, and instance detection. The initial version of this framework was implemented during our participation in Amazon Robotics Challenge (ARC), 2017. Our system was ranked 3rd, 4th and 5th worldwide in pick, stow-pick and stow task respectively. The proposed framework is an improved version over ARC17 where novel features such as instance detection and online learning has been added.