Two-Dimensional Quantum Material Identification via Self-Attention and Soft-labeling in Deep Learning

TL;DR

This paper introduces a novel deep learning approach for 2D quantum material identification that effectively handles missing annotations using self-attention and soft-labeling, improving detection performance.

Contribution

It presents a new mechanism for detecting false negatives and an attention-based loss strategy to enhance instance segmentation in 2D quantum material detection.

Findings

Outperforms previous methods on 2D material detection datasets

Effectively detects false negative objects in dense images

Reduces negative impact of missing annotations on model training

Abstract

In quantum machine field, detecting two-dimensional (2D) materials in Silicon chips is one of the most critical problems. Instance segmentation can be considered as a potential approach to solve this problem. However, similar to other deep learning methods, the instance segmentation requires a large scale training dataset and high quality annotation in order to achieve a considerable performance. In practice, preparing the training dataset is a challenge since annotators have to deal with a large image, e.g 2K resolution, and extremely dense objects in this problem. In this work, we present a novel method to tackle the problem of missing annotation in instance segmentation in 2D quantum material identification. We propose a new mechanism for automatically detecting false negative objects and an attention based loss strategy to reduce the negative impact of these objects contributing to the overall loss function. We experiment on the 2D material detection datasets, and the experiments show our method outperforms previous works.