Car Damage Mask R-CNN (R-101-DC5)

Instance segmentation of 7 types of physical damage on cars, for insurance, rental and resale inspection workflows. Given a photo, the model outputs a pixel mask, a bounding box, a damage class and a confidence score for every damaged region it finds.

Examples

Five damaged regions across three classes

Tear and paint scratches

Side panel

Single crease, high confidence

A failure case — read this one. The dent on this hood is obvious to a human, but at the default threshold of 0.7 the model returns nothing. It only appears at 0.5, scoring 0.57:

The demo images do not cover all 7 classes — the only available example of Vỡ kính / Broken glass had a readable licence plate and a phone number burned into the frame, so it was excluded rather than published.

Installation

pip install cardamage

Quick start

import torch
from PIL import Image
from cardamage import AutoModel

device = torch.device("cuda" if torch.cuda.is_available() else "cpu")
model = AutoModel.from_pretrained("Naiscorp/car-damage-maskrcnn-r101-dc5").to(device).eval()

overlay = model.inference(Image.open("car.jpg"))   # PIL.Image with masks drawn
overlay.save("damage.png")

Structured output instead of a picture:

r = model.predict(Image.open("car.jpg"))
r["boxes"]      # (N, 4) float32, xyxy in ORIGINAL image coordinates
r["scores"]     # (N,)   float32
r["classes"]    # (N,)   int64, 0..6
r["labels"]     # list[str], Vietnamese
r["labels_en"]  # list[str], English
r["masks"]      # (N, H, W) bool, pasted back to the original resolution

Labels

Architecture

Training schedule

This is an intermediate checkpoint, not the end of the planned schedule. It is the one that has been running in production, which is why it is the one released.

Inference defaults (all overridable, all recorded in config.json):

Training data

Internal dataset, collected in Vietnam, annotated with VGG Image Annotator and converted to COCO instance-segmentation format. The dataset itself is not published. The statistics below describe the annotated split the model was trained and evaluated on.

Per-class instance counts:

Benchmarks

Accuracy

Measured on the 417-image test split described above, taken from the internal project report Car Damage Analysis (HCMC, June 2025):

Latency

Measured directly on this checkpoint, 1280×720 input (resized to 1333×750), full pipeline including preprocessing and mask pasting:

License and attribution

model.py re-implements the inference algorithms of Detectron2 (Copyright 2019-present, Facebook, Inc. — licensed under the Apache License, Version 2.0), keeping the original module and parameter names so that checkpoints trained with Detectron2 load without any key remapping.