# A Comparative Transfer-Learning Study of CNN Backbones for Partial Face Recognition on the SoF Dataset

arXiv: https://arxiv.org/abs/2609.31677 · HTML: https://mlsanity.com/paper/2609.31677/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Builds on 12 of its 26 references that are in the map.
- First posted on arXiv 16 Sep 2026.

## Builds on (most cited first, 12 of 12)

- [Deep Residual Learning for Image Recognition](https://mlsanity.com/paper/1512.03385/) (2015)
- [An Image is Worth 16x16 Words: Transformers for Image Recognition at Scale](https://mlsanity.com/paper/2010.11929/) (2020)
- [Very Deep Convolutional Networks for Large-Scale Image Recognition](https://mlsanity.com/paper/1409.1556/) (2014)
- [FaceNet: A Unified Embedding for Face Recognition and Clustering](https://mlsanity.com/paper/1503.03832/) (2015)
- [VGGFace2: A dataset for recognising faces across pose and age](https://mlsanity.com/paper/1710.08092/) (2017)
- [MS-Celeb-1M: A Dataset and Benchmark for Large-Scale Face Recognition](https://mlsanity.com/paper/1607.08221/) (2016)
- [Don't Decay the Learning Rate, Increase the Batch Size](https://mlsanity.com/paper/1711.00489/) (2017)
- [Face Transformer for Recognition](https://mlsanity.com/paper/2103.14803/) (2021)
- [Efficient Masked Face Recognition Method during the COVID-19 Pandemic](https://mlsanity.com/paper/2105.03026/) (2021)
- [AFIF4: Deep Gender Classification based on AdaBoost-based Fusion of Isolated Facial Features and Foggy Faces](https://mlsanity.com/paper/1706.04277/) (2017)
- [Partial Face Detection in the Mobile Domain](https://mlsanity.com/paper/1704.02117/) (2017)
- [Attention-based Partial Face Recognition](https://mlsanity.com/paper/2106.06415/) (2021)

## Abstract (arXiv)

Face recognition is widely deployed in surveillance, access control, and forensic workflows, yet accuracy degrades sharply once the face is occluded by accessories, foreground objects, or the frame edge. Because most faces in the wild are partial, robust partial face recognition (PFR) remains open. This paper compares three pretrained convolutional backbones, ResNet-50, VGG-16, and FaceNet, fine-tuned for PFR by transfer learning under identical preprocessing, splitting, and optimization protocols on the Specs-on-Faces (SoF) dataset. All three arms use a common 160x160 input and a frozen backbone with a trainable head under a fixed epoch budget and no per-backbone hyperparameter search. The FaceNet configuration, denoted PFN (Partial FaceNet), substantially outperforms the other two, reaching 97.4% test accuracy with macro-averaged 87.04% precision, 84.61% recall, and 84.17% F1 over the 112 identity classes, the highest accuracy and recall reported on SoF.