loglens-nano — the benchmark models (128K–202K params)

Checkpoints from the LogLens study of fixed logarithmic memory schedules for multi-timescale change localization on fixed cameras.

Read this first: these are benchmark models — they prove what a from-scratch nano model can and cannot do. On the synthetic benchmarks they are strong (tables below). On real footage they hit a measured clutter wall (unlearnable below ~1% object-to-frame ratio against real backgrounds), and the deployable real-scene system is training-free: frozen CLIP + the same log schedule + a cosine-gap readout (0.796 on real gold, zero parameters). Code and findings in the repo.

Files

file what result
log_K8_s0.pt temporal LogLensNet, auto-base log schedule, K=8 (128K params) 0.901 ± .017 TriClock (3 seeds)
logtuned_K8_s0.pt boundary-aligned schedule 0.922 ± .009
log_K8_s0.onnx ONNX export (543 KB) 0.7 ms/query CPU-only on AGX Orin, ~3 KB memory state
logzoom_K5_s0.pt tri-axis HDNet, saliency-guided log-zoom (202K params) 0.807 ± .012 TriClock-HD
oraclebox_K5_s0.pt tri-axis, oracle glimpses (ceiling reference) 0.999

The two headline findings these models carry

  1. Schedule geometry beats capacity: same model, same budget — a log- spaced memory schedule scores 0.90 where a sliding window scores 0.48; optimal K is width-independent across a 16× parameter range.
  2. Coverage is information-sufficiency; guidance is learnability: full-coverage unguided tiling has every needed pixel (oracle ceiling 1.0) and learns nothing (0.25 floor); centered glimpses at the same resolution reach 0.991.

Demo: https://huggingface.co/spaces/resoajoe/loglens · Benchmark: https://huggingface.co/datasets/resoa/triclock

Downloads last month

-

Downloads are not tracked for this model. How to track
Inference Providers NEW
This model isn't deployed by any Inference Provider. 🙋 Ask for provider support