cs.CVNov 8, 2026

Let the Gallery Learn Itself: Training-Free Iterative Side-View Face Recognition

Authors: Zijun Huang, Suncheng Xiang

Organizations: Shanghai Jiao Tong University

Abstract

What if a face recognition system could learn from every encounter without a single gradient update? We present Gallery Self-Evolution (GSE), a training-free framework where the gallery itself adapts at test time. The core mechanism---dedup-FIFO curation---archives novel appearance samples after successful recognition while permanently locking the enrollment template, bounded at 30 embeddings per identity. On CFP-FP and IJB-C benchmarks, GSE closes the side-view gap by +23 points at 45° yaw and boosts TAR@FAR=0.001 by +9.4 points, all at CPU-level cost. No retraining. No GPU. Just a gallery that grows smarter every time it meets you.

Figures & tables

Explore similar work

CardsList
  1. AIFR: Adaptive Identity Feature Recovery for Diffusion-Based Makeup and Anime Portraits

    Nov 11, 2026Linyan Dai, Xinwei Zhang, Yaxin Xiao +5Face Recognition

  2. Online semi-supervised perception: Real-time learning without explicit feedback

    Apr 30, 2026Branislav Kveton, Michal Valko, Matthai Phillipose +1Graph-Based Semi-Supervised LearningSemi-Supervised Learning