From c95dd308fd8a9158d4e6193243eaa164ba1e0520 Mon Sep 17 00:00:00 2001 From: ruv Date: Sun, 31 May 2026 03:37:19 -0400 Subject: [PATCH] docs(study): cross-dataset confirmed on harder NTU-Fi-HumanID task Re-ran transfer on 14-class person-ID (harder than 6-activity HAR): same null-transfer result (MM-Fi pretrain 91.7% = random 92.8%). Unified root cause: CSI in-domain classification lives in the target-trained readout (random projection already separable); learned reps don't transfer across subjects/rooms/datasets. WiFi-CSI is distribution-locked. Addresses the 'HAR too easy' caveat. Co-Authored-By: claude-flow --- docs/benchmarks/mmfi-wifi-sensing-study.md | 10 ++++++++-- 1 file changed, 8 insertions(+), 2 deletions(-) diff --git a/docs/benchmarks/mmfi-wifi-sensing-study.md b/docs/benchmarks/mmfi-wifi-sensing-study.md index 41655ecd..e8e512ea 100644 --- a/docs/benchmarks/mmfi-wifi-sensing-study.md +++ b/docs/benchmarks/mmfi-wifi-sensing-study.md @@ -117,8 +117,14 @@ architecture-agnostic LoRA on the pose head, tested). probe. CSI representations are **distribution-locked** (same root cause as the within-MM-Fi cross-subject/-environment collapse); the practical answer is on-target training/few-shot, not transferable zero-shot features. Caveat: NTU-Fi's 6 coarse activities are an *easy* target (random - features → 93%), so it weakly stresses representation quality. A harder cross-dataset pose benchmark - remains open. + features → 93%), so it weakly stresses representation quality — but re-running on the harder + **NTU-Fi-HumanID** task (14-class gait person-ID, chance 7.1%) gave the *same* result (MM-Fi + pretrain 91.7% ≈ random 92.8%). **Unified root cause:** for CSI, in-domain classification lives in + the *target-trained readout* (a random 256-d projection of 3,420-d CSI is already linearly + separable), while the *learned representation* fails to transfer across subjects, rooms, and + datasets alike. WiFi-CSI sensing is **distribution-locked**; the answer is on-target few-shot + calibration, not transferable features. A harder cross-dataset *pose* benchmark (vs classification) + remains the one open variant. - Random-split numbers are reported only to compare to prior work on the same protocol; they are in-domain and partly leaky. The cross-subject / cross-environment numbers are the honest ones. - Action-recognition accuracy is window-level (MM-Fi's own HAR experiment is clip-level); not directly