icassp2027-experiment/results/easycom_sparse_supervision_vs_lora_2026-08-24/README.md

EasyCom: sparse supervision versus Thinker LoRA

Recorded on 2026-08-24 from user-reported remote evaluation tables. These are single-run diagnostic results, not final multi-seed paper numbers.

Experiment contract

• Dataset and split: EasyCom with EgoSpeak's official nine training sessions and test Sessions 3, 2, and 1.
• Prediction rate: 5 Hz; ten future horizons from 0.2 to 2.0 seconds.
• Video sampling: 2 FPS.
• Evaluator: EgoSpeak full-timeline AP/mAP plus strict causal-valid AP/mAP.
• Sparse policy: ordinary anchors at 1 Hz plus 5 Hz anchors around annotated target transitions.
• Evaluation is dense at every 5 Hz test timestamp.
• Frozen sparse run: previously extracted frozen Thinker states; only the head is trained for 50 epochs on sparse target indices.
• LoRA three-epoch run: initialized with the trained frozen head, then updated the Thinker LoRA and head for three epochs.

The remote metrics.json, exact checkpoint configuration, git revision, and feature-root path were not copied into this repository. The context/feature identity with the frozen 8-second control must therefore be verified before publication.

Summary

All values are percentages.

Experiment	0.2s full mAP	Full mean mAP	Strict mean mAP
Frozen Thinker dense-cache control	71.69695	58.16091	58.17146
Frozen states + sparse supervision, 50 epochs	71.69194	57.20379	57.21367
Sparse LoRA epoch 1	67.40167	56.52480	56.53450
Frozen-head initialized LoRA, 3 epochs	71.08589	56.19608	56.20535
Sparse LoRA weights-only epoch 2	65.55214	54.19850	54.20711

The epoch-2 continuation is archived separately in ../easycom_omni_lora_sparse_epoch2_2026-08-24/.

Frozen states with sparse supervision

Horizon	Full mAP	Strict mAP	Full background AP	Full wearer AP	Full others AP
0.2s	71.69194	71.69383	54.64681	76.09602	84.33299
0.4s	65.98617	65.98941	46.86427	70.48309	80.61116
0.6s	61.14072	61.14698	41.30997	64.40092	77.71127
0.8s	57.39854	57.40704	37.50173	59.07507	75.61882
1.0s	54.57513	54.58522	35.47209	54.41110	73.84220
1.2s	53.70320	53.71497	35.16647	52.41903	73.52409
1.4s	52.74547	52.75864	34.64200	50.53203	73.06238
1.6s	52.04826	52.06226	34.36442	49.18784	72.59253
1.8s	51.55154	51.56613	34.13135	48.17972	72.34356
2.0s	51.19693	51.21218	33.99937	47.47712	72.11430
Mean	57.20379	57.21367	—	—	—

Frozen-head initialized LoRA after three epochs

Horizon	Full mAP	Strict mAP	Full background AP	Full wearer AP	Full others AP
0.2s	71.08589	71.08773	53.71399	75.95995	83.58373
0.4s	65.20613	65.20927	46.04420	69.65188	79.92232
0.6s	60.10484	60.11088	40.44134	62.71065	77.16253
0.8s	56.35250	56.36069	36.98112	56.61255	75.46383
1.0s	53.48271	53.49230	35.10974	51.63824	73.70016
1.2s	52.50271	52.51364	34.83634	49.81663	72.85516
1.4s	51.46987	51.48201	34.06639	48.01675	72.32646
1.6s	50.91134	50.92429	34.04663	46.85967	71.82772
1.8s	50.54008	50.55369	33.82003	46.15156	71.64864
2.0s	50.30475	50.31903	33.74069	45.80527	71.36829
Mean	56.19608	56.20535	—	—	—

0.2-second diagnosis

Sparse supervision alone changes 0.2-second full-timeline mAP by only -0.00501 relative to the frozen dense-cache control. The three-epoch LoRA run changes it by -0.61106. The much larger epoch-1 and weights-only epoch-2 regressions show that short-horizon degradation is primarily associated with updating the Thinker representation, not with dropping ordinary supervision anchors.

The next required control is a 2-by-2 checkpoint evaluation: frozen Thinker with frozen head, frozen Thinker with LoRA-trained head, LoRA Thinker with frozen head, and LoRA Thinker with LoRA-trained head. Select LoRA checkpoints on a training-session development split using 0.2-second mAP rather than the official test sessions.

Provenance

• Source: user-reported remote infer_turn_head.py and eval_omni_turn_lora.py console tables.
• Raw remote metrics archived: no.
• Multi-seed: no.
• Publication status: diagnostic only.