Scene tags (Places365)

--scenes (or "scenes": {"enabled": true} on the scan request) runs a Places365 (opens in new tab)-CNN (Zhou et al., TPAMI 2017) on every passing image and records its top-k scene categories (365 of them: beach, bedroom, gas_station, forest_path, …) with their softmax probabilities, plus an indoor/outdoor call. environment_conf is the probability mass on categories of that environment, not upstream's top-10 vote. Results land on results[].scene and in the CSV report.

Filters

Top-1 accuracy on Places365 is about 55% (top-5 about 85%), and neighbouring categories overlap (lagoon / beach / coast), which is why filters match any of the recorded top-k rather than only the first:

• --scene beach,coast / scenes: keep images with one of these among their top-k at probability ≥ --min-scene-conf / min_scene_conf (default 0.1, so a label lingering in the tail at 3% does not count). Unknown labels are rejected with 422 rather than silently matching nothing.
• --environment outdoor / scene_environments: indoor or outdoor, held to the same floor.
• --diversify-scenes / diversify_scenes (with --max-keep): the diversity cap also spreads the selection across backdrops, so an identity set is not two hundred bathroom selfies.

Excluded images say why: scene-excluded, scene-low-confidence, scene-environment-excluded, scene-environment-low-confidence, or scene-missing.

Installing the model

The weights are converted once to ONNX, like the face models:

pip install "argus-curator[places365-convert]"   # torch, only for this step
argus-curator places365-convert                  # resnet18 (default) or --arch resnet50
# -> ~/.cache/argus_curator/models/places365_resnet18.onnx

Upstream serves the checkpoints over plain HTTP, so each is pinned by sha256. ResNet-50 is twice the size for about one point of top-1 (55.6% vs 54.5%). Point elsewhere with --places365-model / ARGUS_CURATOR_PLACES365_MODEL.