Interactive Instance Annotation with Siamese Networks

TL;DR

SiamAnno introduces a Siamese network-based framework for cross-domain instance annotation, enabling one-shot learning to predict object boundaries from bounding boxes, significantly reducing annotation effort and handling domain shifts.

Contribution

This work is the first to apply Siamese networks to instance annotation, achieving state-of-the-art results in cross-domain scenarios without fine-tuning.

Findings

SiamAnno outperforms previous methods on multiple datasets.

It effectively handles domain and environment shifts.

Provides a strong baseline for future cross-domain annotation research.

Abstract

Annotating instance masks is time-consuming and labor-intensive. A promising solution is to predict contours using a deep learning model and then allow users to refine them. However, most existing methods focus on in-domain scenarios, limiting their effectiveness for cross-domain annotation tasks. In this paper, we propose SiamAnno, a framework inspired by the use of Siamese networks in object tracking. SiamAnno leverages one-shot learning to annotate previously unseen objects by taking a bounding box as input and predicting object boundaries, which can then be adjusted by annotators. Trained on one dataset and tested on another without fine-tuning, SiamAnno achieves state-of-the-art (SOTA) performance across multiple datasets, demonstrating its ability to handle domain and environment shifts in cross-domain tasks. We also provide more comprehensive results compared to previous work, establishing a strong baseline for future research. To our knowledge, SiamAnno is the first model to explore Siamese architecture for instance annotation.