AMSnet 2.0: A Large AMS Database with AI Segmentation for Net Detection

TL;DR

This paper introduces AMSnet 2.0, a comprehensive dataset of 2,686 circuits with high-quality schematic images, netlists, and positional data, enabling improved AI understanding and reconstruction of circuit schematics.

Contribution

It presents a novel segmentation-based net detection method and expands the AMSnet dataset to include diverse schematic images with detailed annotations.

Findings

Enhanced dataset with 2,686 circuits and detailed schematic data

Robust segmentation method for net detection in complex schematics

Improved digital reconstruction capabilities for circuit schematics

Abstract

Current multimodal large language models (MLLMs) struggle to understand circuit schematics due to their limited recognition capabilities. This could be attributed to the lack of high-quality schematic-netlist training data. Existing work such as AMSnet applies schematic parsing to generate netlists. However, these methods rely on hard-coded heuristics and are difficult to apply to complex or noisy schematics in this paper. We therefore propose a novel net detection mechanism based on segmentation with high robustness. The proposed method also recovers positional information, allowing digital reconstruction of schematics. We then expand AMSnet dataset with schematic images from various sources and create AMSnet 2.0. AMSnet 2.0 contains 2,686 circuits with schematic images, Spectre-formatted netlists, OpenAccess digital schematics, and positional information for circuit components and nets, whereas AMSnet only includes 792 circuits with SPICE netlists but no digital schematics.