dtourolle
4925443e56
Splits the rep4 write-up's key findings into their own linkable pages: - best-model.md: calibration curves first (discriminative power, independent of any threshold), then F1 on the benchmark — LVFace-B Glint360K wins both. - gallery-scope.md: whole vs. cast-restricted gallery, isolated from model and expansion choice — restriction wins on every axis, but isn't a shipped runtime feature yet. - pose-expansion.md: the training-set expand_gallery effect, and the held-out replication attempt that found it doesn't reproduce (5 films, 2 models, after catching and fixing a replay-timeout truncation bug and a bbox first-match-instead-of-best-match bug in the comparison harness itself). An honest null result, with the methodology errors documented since they're exactly the kind that manufacture a false "it works!" finding. - lvface-deep-dive.md: the winning model's held-out generalization gap, its two failure modes (frozen-bbox ghost tracks), and a verified case (cross- checked against Jellyfin's independent cast metadata) where LVFace correctly identified an actor that X-Ray's ground truth failed to credit. Adds a "report-highlights" artifact-registry package (scripts/artifacts/ push_artifacts.sh, pull_artifacts.sh) for hand-picked illustrative frames that aren't reproducible via the automated best/worst montage selection, and wires pulling it into scripts/docs/build_site.sh.
2.9 KiB
Which embedding model is best?
Four candidates went into the bake-off: three ArcFace variants (w600k-R50,
R18, w600k-MBF) and LVFace-B (Glint360K), a Vision-Transformer embedder that's
a drop-in replacement for ArcFace's [N,3,112,112] input / 512-d output. The
open question: is LVFace (455MB) actually better, or just the biggest?
First signal: calibration curves
Each gallery carries a fitted Platt sigmoid P(match | cosine similarity) = σ(a·sim + b), embedded directly in the gallery's HDF5 file
(src/gallery/gallery_calibration.hpp). This is a property of the embedding
space alone — computed from intra/inter-actor reference-image pairs, no
tracking or scene logic involved — so it's a clean first read on discriminative
power before running a single benchmark.
| model | a (steepness) |
boundary at P=0.5 |
|---|---|---|
| LVFace-B Glint360K | 17.7 | sim 0.228 |
| ArcFace w600k-MBF | 16.2 | sim 0.267 |
| ArcFace w600k-R50 | 15.4 | sim 0.301 |
| ArcFace R18 | 15.3 | sim 0.309 |
LVFace has both the steepest transition and the lowest decision boundary — it separates same-actor from different-actor reference pairs more confidently, at a lower similarity threshold, than any ArcFace variant. That's a genuine head start before the tracking/scoring pipeline is even involved.
Second signal: F1 on the actual benchmark
Best full-gallery (no cast-restriction) result per model, from the 16-combo
rep4 matrix (rep4-optimizer-results.md):
| model | F1 | P | R | misID |
|---|---|---|---|---|
| LVFace-B Glint360K | 75.3% | 89.7% | 65.4% | 232 |
| ArcFace w600k-MBF | 74.2% | 87.4% | 64.4% | 57 |
| ArcFace R18 | 69.1% | 87.6% | 57.7% | 242 |
| ArcFace w600k-R50 | 68.5% | 94.0% | 54.1% | 150 |
LVFace wins outright, with the highest recall of any full-mode combo. This
reverses an earlier conclusion from a prior (superseded) benchmarking pass
using a scene-union metric, which found the three models statistically
indistinguishable (~85% each) and concluded LVFace wasn't worth its size — that
metric hid out-of-cast false positives behind a gallery∩cast recall mask (see
optimizer-experiments.md); the per-second metric used here does not.
Held-out validation (5 films never seen by the optimizer) confirms LVFace's lead holds up out of sample — see the deep-dive page for the full breakdown, including where it fails.
Caveat: model choice is an operational change
Switching the default embedder isn't just flipping a config value — the
gallery itself is model-specific (embeddings from different models aren't
comparable), so any existing gallery built against ArcFace w600k-R50 needs to
be rebuilt from source images against LVFace before the new default takes
effect. scripts/optimizer/reembed_gallery.py does this from a reference
gallery's cached source images without re-downloading anything.