referee-hands-s
A 1.5M-parameter MobileNetV3-small classifier for hand/gripper visibility in
robot-training footage. 96px inputs, sized for microcontroller-class deployment.
The published 97.8% result is from a 45-clip, in-domain development sheet that
was repeatedly consulted during development and has not yet passed the declared
independent two-grader gate. It is reproducible development evidence, not a
frozen external benchmark.
Benchmark
97.8% clip accuracy on
referee-lab/hands-visible (45-clip
provisional development sheet, robot + wildlife domains) — matching gemma3:27b
on that sheet at 1/18,000th the parameters.
| Model | Params | Accuracy |
|---|
| gemma3:27b | 27B | 97.8% |
| referee-hands-s | 1.5M | 97.8% |
| referee-hands-s, cross-video split | 1.5M | 95.6% |
| qwen2.5vl:32b | 32B | 74.4% |
| constant-answer floor | — | 68.9% |
The cross-video row keeps every training frame at least 60 seconds away from
any test clip on its source stream. Under that separation the model scores
100% on real footage (41/41); its two misses are synthetic drawn-hand control
clips outside the training distribution.
Intended use and scope
Version 1 targets fixed-camera and wrist-camera robot workspace footage —
the domain it was trained on (DROID, ALOHA-sim, KABR negatives). Human
egocentric and general webcam scenes are outside the v1 training distribution;
a mixed-domain v2 is in development. Use for capture-pipeline gating in the
supported domain.
Usage
1import torch
2from torchvision import models, transforms
3from safetensors.torch import load_file
4
5net = models.mobilenet_v3_small()
6net.classifier[3] = torch.nn.Linear(net.classifier[3].in_features, 1)
7net.load_state_dict(load_file("model.safetensors"))
8net.eval()
9tf = transforms.Compose([transforms.Resize((96, 96)), transforms.ToTensor()])
10p = torch.sigmoid(net(tf(img).unsqueeze(0)).squeeze()) # P(hand/gripper visible)
Clip-level verdict: sample ~12 frames, yes if max(p) > 0.5.
Training: distilled from gemma3:27b pseudo-labels on CC BY / CC0 / MIT media.
Benchmark, gates, and tooling:
https://github.com/publu/referee-lab
