zpyuan/SymbolicCapsuleNetwork

Symbolic Capsule Network

Symbolic Capsule Network (SCN) is a capsule-enhanced real-time vision model for COCO object detection and instance segmentation.
This release provides two model variants:

• Symbolic Capsule Network Detection
• Symbolic Capsule Network Segmentation

SCN introduces capsule-style structured feature representation into a YOLO-style dense prediction pipeline, aiming to improve semantic compositionality while preserving practical real-time performance.

Available Models

Model	Task	Dataset	Input Size	Best Validation Performance
Symbolic Capsule Network Detection	Object Detection	COCO 2017	640	Box mAP50 0.55776, Box mAP50-95 0.40319
Symbolic Capsule Network Segmentation	Instance Segmentation	COCO 2017	640	Mask mAP50 0.53316, Mask mAP50-95 0.34080

Model Description

Symbolic Capsule Network is designed for real-time dense visual prediction.
The model replaces part of the standard feature interaction pipeline with capsule-inspired transformations and structured routing, enabling richer intermediate representations for localization and mask prediction.

This page focuses on two public COCO releases:

1. Detection model
2. Segmentation model

Performance on COCO 2017

Detection

Best result from the current training record:

• Box mAP50: 0.55776
• Box mAP50-95: 0.40319

Segmentation

Best result from the current training record:

• Mask mAP50: 0.53316
• Mask mAP50-95: 0.34080

Usage

Detection

from ultralytics import YOLO

model = YOLO("symbolic_capsule_network_detection.pt")
results = model("image.jpg")
results[0].show()