zhangsiyuan
bd1f51c496
Merged code repo (CompanionGuard-RL) into single project-level git. Reorganized root: docs/, reference/, experiments/, tmp/active|archives/. Gitignored: data/, checkpoints/, .venv, experiment logs, tmp/archives. Co-Authored-By: Claude Sonnet 4.6 <noreply@anthropic.com>
122 lines
3.6 KiB
YAML
122 lines
3.6 KiB
YAML
# Multimodal noise configuration for robustness experiments (P0-4)
|
||
# Each variant defines noise applied per modality.
|
||
# Run: python scripts/preprocess/generate_noise.py \
|
||
# --config configs/noise_configs.yaml \
|
||
# --data_dir $ZSY/multimodal_affect/data/iemocap
|
||
|
||
variants:
|
||
|
||
# ── Variant 1: Light Gaussian across all modalities ───────────────────
|
||
- name: gaussian_light
|
||
description: "Mild Gaussian noise on all modalities (σ=0.05)"
|
||
noise:
|
||
text:
|
||
type: gaussian
|
||
intensity: 0.05
|
||
audio:
|
||
type: gaussian
|
||
intensity: 0.05
|
||
visual:
|
||
type: gaussian
|
||
intensity: 0.05
|
||
|
||
# ── Variant 2: Heavy Gaussian ─────────────────────────────────────────
|
||
- name: gaussian_heavy
|
||
description: "Strong Gaussian noise on all modalities (σ=0.20)"
|
||
noise:
|
||
text:
|
||
type: gaussian
|
||
intensity: 0.20
|
||
audio:
|
||
type: gaussian
|
||
intensity: 0.20
|
||
visual:
|
||
type: gaussian
|
||
intensity: 0.20
|
||
|
||
# ── Variant 3: Missing modality – audio dropped ───────────────────────
|
||
- name: missing_audio
|
||
description: "Audio features zeroed out (100% drop)"
|
||
noise:
|
||
text:
|
||
type: gaussian
|
||
intensity: 0.0
|
||
audio:
|
||
type: masking
|
||
intensity: 1.0 # mask ALL dims
|
||
visual:
|
||
type: gaussian
|
||
intensity: 0.0
|
||
|
||
# ── Variant 4: Missing modality – visual dropped ──────────────────────
|
||
- name: missing_visual
|
||
description: "Visual features zeroed out"
|
||
noise:
|
||
text:
|
||
type: gaussian
|
||
intensity: 0.0
|
||
audio:
|
||
type: gaussian
|
||
intensity: 0.0
|
||
visual:
|
||
type: missing_modality
|
||
intensity: 1.0
|
||
|
||
# ── Variant 5: Text word-drop ─────────────────────────────────────────
|
||
- name: text_word_drop_30
|
||
description: "30% token dropout in text modality"
|
||
noise:
|
||
text:
|
||
type: word_drop
|
||
intensity: 0.30
|
||
audio:
|
||
type: gaussian
|
||
intensity: 0.0
|
||
visual:
|
||
type: gaussian
|
||
intensity: 0.0
|
||
|
||
# ── Variant 6: Audio feature masking ─────────────────────────────────
|
||
- name: audio_masking_50
|
||
description: "50% of audio feature dimensions masked"
|
||
noise:
|
||
text:
|
||
type: gaussian
|
||
intensity: 0.0
|
||
audio:
|
||
type: masking
|
||
intensity: 0.50
|
||
visual:
|
||
type: gaussian
|
||
intensity: 0.0
|
||
|
||
# ── Variant 7: Realistic mixed noise ─────────────────────────────────
|
||
- name: realistic_mixed
|
||
description: >
|
||
Realistic scenario: moderate text corruption, noisy audio,
|
||
partial visual occlusion
|
||
noise:
|
||
text:
|
||
type: word_drop
|
||
intensity: 0.15
|
||
audio:
|
||
type: gaussian
|
||
intensity: 0.10
|
||
visual:
|
||
type: occlusion
|
||
intensity: 0.25
|
||
|
||
# ── Variant 8: Asynchronous noise (time-shifted audio) ───────────────
|
||
- name: audio_time_mask
|
||
description: "Audio time-step masking (30%) simulates dropped frames"
|
||
noise:
|
||
text:
|
||
type: gaussian
|
||
intensity: 0.0
|
||
audio:
|
||
type: time_mask
|
||
intensity: 0.30
|
||
visual:
|
||
type: gaussian
|
||
intensity: 0.0
|