# Inference for Detections
Object detection models label each sample with a [`Detections`](../../api/fiftyone.core.labels.md#fiftyone.core.labels.Detections) field, which
you generate by passing a model to
[`apply_model()`](../../api/fiftyone.core.collections.md#fiftyone.core.collections.SampleCollection.apply_model).
The same field type also covers polygon and instance segmentation output,
since [`Detection`](../../api/fiftyone.core.labels.md#fiftyone.core.labels.Detection) instances can optionally carry a mask.
The Model Zoo includes detectors like Faster R-CNN and the YOLO family, and
the [Object Detection Guide](../../getting_started/object_detection/index.md#detection-guide) walks through applying
both a zoo detector and a custom one to the same dataset.
For a custom model, you can either construct [`Detection`](../../api/fiftyone.core.labels.md#fiftyone.core.labels.Detection) instances yourself
in a loop, or configure a
[`TorchImageModel`](../../api/fiftyone.utils.torch.md#fiftyone.utils.torch.TorchImageModel) with a
[`DetectorOutputProcessor`](../../api/fiftyone.utils.torch.md#fiftyone.utils.torch.DetectorOutputProcessor)
so it works with `apply_model()` directly, as described in
[Inference with custom models](index.md#running-inference-custom).