YOLOX-Pylon-S

A YOLOX-S detector extended with one additional class — traffic cones (traffic_cone) — on top of the 80 COCO classes, for 81 classes total. The adaptation is trained so the original COCO capabilities are kept, not traded away: on this checkpoint the retained COCO score actually lands above the official YOLOX-S baseline, while the added cone class scores higher than every one of the 80 original classes.

Cones are the public demo class. The same adaptation recipe adds arbitrary custom classes (defects, parts, PPE, and similar) to a proven detector without losing what it already knows.

Part of the YOLOX-Pylon family: S · M · L · X (in training).

Built by Empirisch Tech GmbH (Vienna, Austria) under the Chaperone AI brand — see About Empirisch Tech below.

Results

Evaluated on COCO val2017 plus a held-out traffic-cone split, 81 classes in a single pass, 640×640 input, IoU 0.50:0.95 unless noted.

Metric	Value
mAP 50:95 (81 classes)	42.0
mAP 50:95, original 80 COCO classes only	41.6
AP50 / AP75	60.2 / 45.8
AP small / medium / large	24.5 / 46.1 / 53.5
AR@100	56.3
traffic_cone AP / AR	74.5 / 77.7
Inference (forward + NMS, batch 1, fp16)	1.72 ms

Two things worth noting:

• Retention is better than free. The official YOLOX-S baseline is 40.5 mAP on COCO. After adding the cone class, this checkpoint scores 41.6 on the same 80 classes — 1.1 points above the base it started from (a side effect of the additional training schedule).
• The added class is the best class. At 74.5 AP, traffic_cone outscores all 80 original classes on this checkpoint — the next best are stop sign (71.8), giraffe (69.5), and bear (69.3).

Full per-class AP (81 classes)

class	AP	class	AP	class	AP
person	55.632	bicycle	30.285	car	51.554
motorcycle	44.826	airplane	65.935	bus	69.032
train	61.938	truck	46.615	boat	26.122
traffic light	38.914	fire hydrant	69.017	stop sign	71.756
parking meter	47.091	bench	29.711	bird	35.062
cat	62.883	dog	58.504	horse	59.151
sheep	49.890	cow	54.719	elephant	65.400
bear	69.281	zebra	66.671	giraffe	69.549
backpack	17.542	umbrella	39.401	handbag	13.586
tie	30.176	suitcase	41.589	frisbee	62.697
skis	24.562	snowboard	32.899	sports ball	46.214
kite	44.614	baseball bat	28.172	baseball glove	38.296
skateboard	50.527	surfboard	36.032	tennis racket	45.279
bottle	38.133	wine glass	33.070	cup	39.283
fork	33.245	knife	16.844	spoon	15.319
bowl	42.512	banana	25.952	apple	18.219
sandwich	30.984	orange	29.727	broccoli	22.596
carrot	23.408	hot dog	32.177	pizza	52.505
donut	47.748	cake	39.168	chair	32.042
couch	44.568	potted plant	27.697	bed	42.693
dining table	30.536	toilet	65.092	tv	56.373
laptop	60.517	mouse	59.313	remote	23.742
keyboard	50.499	cell phone	33.708	microwave	53.325
oven	33.296	toaster	39.092	sink	39.782
refrigerator	54.511	book	13.306	clock	49.399
vase	36.430	scissors	28.823	teddy bear	44.074
hair drier	1.065	toothbrush	18.352	traffic_cone	74.516

Comparison with other detectors

Small-tier detectors, published COCO val2017 figures from the official YOLOX and Ultralytics model tables.

Model	COCO mAP 50:95	Params	Custom classes	License
yolox-pylon-s (this model)	41.6 kept + traffic_cone 74.5	9.0M	yours added, COCO kept	Apache-2.0
YOLOX-S (base)	40.5	9.0M	COCO only	Apache-2.0
YOLO11s	47.0	9.4M	COCO only	AGPL-3.0 / commercial
YOLO26s	48.6	9.5M	COCO only	AGPL-3.0 / commercial

How to read this honestly: the newest Ultralytics releases post higher raw COCO scores — several years of architecture progress at similar parameter counts. This model optimizes for a different job: extending a commercially permissive base with new classes while retaining its original capabilities. The relevant scores are the retention delta (+1.1 over its own baseline) and the added-class AP (74.5), not the raw COCO leaderboard. The Apache-2.0 license also means the weights can be deployed commercially without a per-deployment license or an obligation to open-source derivative work, which AGPL-3.0 models require.

Larger siblings for scale (same recipe, same eval protocol):

Family member	mAP (81 cls)	COCO kept	Cone AP	Inference
yolox-pylon-s	42.0	41.6	74.5	1.7 ms
yolox-pylon-m	47.2	46.8	77.5	2.6 ms
yolox-pylon-l	48.9	48.5	78.6	3.7 ms
yolox-pylon-x	in training	—	—	—

Usage

The checkpoint loads with the official YOLOX codebase. The only change from stock YOLOX-S is num_classes = 81, with traffic_cone as class index 80.

import torch
from yolox.exp import get_exp
from yolox.utils import postprocess

# stock yolox-s exp, patched to 81 classes
exp = get_exp(exp_name="yolox-s")
exp.num_classes = 81

model = exp.get_model()
ckpt = torch.load("yolox-pylon-s.pth", map_location="cpu")
model.load_state_dict(ckpt["model"])
model.eval().cuda()

# img: float32 tensor [1, 3, 640, 640], preprocessed YOLOX-style
with torch.no_grad():
    outputs = model(img)
outputs = postprocess(outputs, num_classes=81, conf_thre=0.25, nms_thre=0.45)

COCO_CLASSES = [...]                        # standard 80-class list
CLASSES = COCO_CLASSES + ["traffic_cone"]   # index 80

Or with the repo's demo tool:

git clone https://github.com/Megvii-BaseDetection/YOLOX && cd YOLOX
python tools/demo.py image \
    -f exps/default/yolox_s.py \
    -c yolox-pylon-s.pth \
    --path your_image.jpg --conf 0.25 --nms 0.45 --tsize 640 --device gpu
# patch exps/default/yolox_s.py with self.num_classes = 81 first

Training

• Base: YOLOX-S (9.0M params), initialized from COCO-pretrained weights
• Data: COCO train2017 plus a labeled traffic-cone dataset, trained jointly so the original 80 classes stay in the mix during adaptation
• Eval: COCO val2017 plus a held-out cone split, single 81-class evaluation pass
• Input: 640×640

Intended use and limitations

Intended for roadside and infrastructure perception where traffic cones matter (work zones, lane closures, autonomous driving research) and as a template for class-extension on YOLOX. The model detects boxes for 81 classes; it does not segment, track, or estimate distance. Accuracy on small objects (24.5 AP) follows the usual small-model pattern — if small or distant cones dominate your footage, prefer yolox-pylon-m or yolox-pylon-l. As with any detector, validate on your own cameras before production use.

About Empirisch Tech

YOLOX-Pylon is built by Empirisch Tech GmbH, a Vienna-based AI company, under its Chaperone AI brand. The company runs one recipe across three domains — adapt a proven foundation model to a specific domain, keep what the base already knows, and ship the checkpoint together with the data it was trained on:

• Language — Thinking-LQ-1.0 (84% MedQA, within 4 points of GPT-4o at ~20GB) and Coder-LQ-1.0
• Physics — Chaperone-Flow-1.0 (Poseidon-B extended to new CFD regimes, 1.8% wake error) and Palace-LoRA (electromagnetics solver configs)
• Vision — the YOLOX-Pylon family and a road-scene anomaly segmentation pipeline

The models power the company's production platforms, including NumericalAI (GPU physics simulation) and Simvera (industrial perception trained in simulation, deployed on real cameras). Everything is self-hosted in the company's own Vienna datacenter — no third-party model APIs. Empirisch Tech is a member of the NVIDIA Inception and Microsoft for Startups programs, and its open checkpoints have passed 30,000 downloads on Hugging Face.

Custom builds: the cone class took one adaptation run. For your own classes, cameras, or datasets, reach out via chaperoneai.com/contact.

License

Apache-2.0, matching the YOLOX base.

Citation

@article{yolox2021,
  title={YOLOX: Exceeding YOLO Series in 2021},
  author={Ge, Zheng and Liu, Songtao and Wang, Feng and Li, Zeming and Sun, Jian},
  journal={arXiv preprint arXiv:2107.08430},
  year={2021}
}