FocsleFocsle
KV

OSNet-AIN

2%
by KAIST Vision

Tiny pedestrian re-ID. The default for cross-camera tracking on dashcam-class silicon.

Re-IDMITINT8pedestrianreidtiny
88K downloads 7.2K deploymentsUpdated Oct 22, 2027
Headline:6.1ms · Ambarella CV5 · INT8

About this model

Tiny pedestrian re-ID. The default for cross-camera tracking on dashcam-class silicon.

Authored by kaist-vision. Curated into the Fo’c’sle reference set on 2027-10-22. All cross-chip benchmarks below were collected in matched-pair runs in the HIL lab using the same input pipeline, same upstream preprocessing, and the same downstream consumer. See the methodology page for the full protocol.

Task
Re-ID
Parameters
2.2 M
Benchmarked on
6 chips
Deployments
7.2K

Architecture

Embedding + similarity
Inferred from upstream weights · simplified
CropBackbonePoolingMargin headEmbedding

Headline benchmarks

Training data

Pretrained on the upstream maintainer’s released checkpoint. Edge-distillation pass uses 2.4M frames from the Fo’c’sle distillation corpus (consented public data + opt-in publisher contributions). Quantization-aware fine-tune uses 320K calibration samples drawn from the target task’s eval domain.

  • Pretraining corpus: upstream maintainer release
  • Distillation corpus: 2,400,000 frames
  • Calibration set: 320,000 samples (per task)
  • Eval set: standard benchmark + matched-pair HIL runs