← 研踪 PaperTrailarXiv:2611.19754 · v1
Input-Space versus Feature-Level Conditioning for Robust Facial Expression Recognition
首次提交 2026-11-15 11:35
版本更新 2026-11-15 11:35
雷达观测 2026-11-17 12:06
摘要
Facial expression recognition (FER) degrades sharply when illumination, exposure or resolution departs from the training distribution. Two remedies dominate practice: enriching the input signal, or conditioning intermediate features on an estimated image quality. The two are rarely compared under matched backbones, training budgets and condition annotations, and their cost is seldom reported. We present a controlled comparison on RAF-DB. Input-space conditioning uses four deterministic, label-free views (logarithmic stretching, inverse-logarithmic stretching, down-up resampling and identity), each processed by a shared backbone with a branch-specific BatchNorm and linear head, with the branch logits averaged. Feature-space conditioning is implemented as FiLM and Conditional BatchNorm under an identical protocol. Across six backbone architectures the input-space variant improves top-1 accuracy on every one (mean +0.94 percentage points; bootstrap interval [0.51, 1.63]; sign test p = 0.016), with a seed-controlled estimate of +0.42 percentage points on ResNet-18, whereas feature-level conditioning yields +0.10 and +0.03 percentage points. We attribute the gap to the information content of the heuristic condition label rather than to the conditioning mechanism. The gain costs 4.00x FLOPs, 4.18x latency and 3.79x training time, i.e. 0.26 percentage points per additional GFLOP, and we state an explicit rule for when the trade is worth making.
作者备注:8 pages, 2 figures, 4 tables
观测到的版本
相邻记录可能跳过中间版本;首次发现 v2 及以上也会标为版本更新。
v1 · 2026-11-15 11:35 · 最新观测版本
Input-Space versus Feature-Level Conditioning for Robust Facial Expression Recognition
Facial expression recognition (FER) degrades sharply when illumination, exposure or resolution departs from the training distribution. Two remedies dominate practice: enriching the input signal, or conditioning intermediate features on an estimated image quality. The two are rarely compared under matched backbones, training budgets and condition annotations, and their cost is seldom reported. We present a controlled comparison on RAF-DB. Input-space conditioning uses four deterministic, label-free views (logarithmic stretching, inverse-logarithmic stretching, down-up resampling and identity), each processed by a shared backbone with a branch-specific BatchNorm and linear head, with the branch logits averaged. Feature-space conditioning is implemented as FiLM and Conditional BatchNorm under an identical protocol. Across six backbone architectures the input-space variant improves top-1 accuracy on every one (mean +0.94 percentage points; bootstrap interval [0.51, 1.63]; sign test p = 0.016), with a seed-controlled estimate of +0.42 percentage points on ResNet-18, whereas feature-level conditioning yields +0.10 and +0.03 percentage points. We attribute the gap to the information content of the heuristic condition label rather than to the conditioning mechanism. The gain costs 4.00x FLOPs, 4.18x latency and 3.79x training time, i.e. 0.26 percentage points per additional GFLOP, and we state an explicit rule for when the trade is worth making.
查看此版本解读 →查看此版本原文 ↗