# Open-Set Face Recognition with Maximal Entropy and Objectosphere Loss

arXiv: https://arxiv.org/abs/2311.00400 · HTML: https://mlsanity.com/paper/2311.00400/

## Key facts

- Cited by 5 papers in the map (data through 14 Oct 2026).
- Builds on 20 of its 48 references that are in the map.
- First posted on arXiv 1 Nov 2023.

## Builds on (most cited first, 20 of 20)

- [FaceNet: A Unified Embedding for Face Recognition and Clustering](https://mlsanity.com/paper/1503.03832/) (2015)
- [CosFace: Large Margin Cosine Loss for Deep Face Recognition](https://mlsanity.com/paper/1801.09414/) (2018)
- [VGGFace2: A dataset for recognising faces across pose and age](https://mlsanity.com/paper/1710.08092/) (2017)
- [Joint Face Detection and Alignment using Multi-task Cascaded Convolutional Networks](https://mlsanity.com/paper/1604.02878/) (2016)
- [SphereFace: Deep Hypersphere Embedding for Face Recognition](https://mlsanity.com/paper/1704.08063/) (2017)
- [Circle Loss: A Unified Perspective of Pair Similarity Optimization](https://mlsanity.com/paper/2002.10857/) (2020)
- [AdaFace: Quality Adaptive Margin for Face Recognition](https://mlsanity.com/paper/2204.00964/) (2022)
- [Large-Margin Softmax Loss for Convolutional Neural Networks](https://mlsanity.com/paper/1612.02295/) (2016)
- [Reducing Network Agnostophobia](https://mlsanity.com/paper/1811.04110/) (2018)
- [OpenGAN: Open-Set Recognition via Open Data Generation](https://mlsanity.com/paper/2104.02939/) (2021)
- [Learning Placeholders for Open-Set Recognition](https://mlsanity.com/paper/2103.15086/) (2021)
- [Counterfactual Zero-Shot and Open-Set Visual Recognition](https://mlsanity.com/paper/2103.00887/) (2021)
- [Learning a Neural-network-based Representation for Open Set Recognition](https://mlsanity.com/paper/1802.04365/) (2018)
- [Toward Open-Set Face Recognition](https://mlsanity.com/paper/1705.01567/) (2017)
- [Unconstrained Face Detection and Open-Set Face Recognition Challenge](https://mlsanity.com/paper/1708.02337/) (2017)
- [Triplet Probabilistic Embedding for Face Verification and Clustering](https://mlsanity.com/paper/1604.05417/) (2016)
- [Unconstrained Face Verification using Deep CNN Features](https://mlsanity.com/paper/1508.01722/) (2015)
- [One-to-many face recognition with bilinear CNNs](https://mlsanity.com/paper/1506.01342/) (2015)
- [Large-Scale Open-Set Classification Protocols for ImageNet](https://mlsanity.com/paper/2210.06789/) (2022)
- [Open-set Face Recognition using Ensembles trained on Clustered Data](https://mlsanity.com/paper/2308.07445/) (2023)

## Built on by (most cited first, 5 of 5)

- [Are you In or Out (of gallery)? Wisdom from the Same-Identity Crowd](https://mlsanity.com/paper/2508.06357/) (2025)
- [Watchlist Challenge: 3rd Open-set Face Detection and Identification](https://mlsanity.com/paper/2409.07220/) (2024)
- [FaceGCD: Generalized Face Discovery via Dynamic Prefix Generation](https://mlsanity.com/paper/2507.22353/) (2025)
- [Nearest-Class Mean and Logits Agreement for Wildlife Open-Set Recognition](https://mlsanity.com/paper/2510.17338/) (2025)
- [Rank-1 Identity Consensus Predicts Gallery Enrollment in 1:N Face Matching More Accurately than Score Thresholding](https://mlsanity.com/paper/2607.12903/) (2026)

## Abstract (arXiv)

Open-set face recognition characterizes a scenario where unknown individuals, unseen during the training and enrollment stages, appear on operation time. This work concentrates on watchlists, an open-set task that is expected to operate at a low False Positive Identification Rate and generally includes only a few enrollment samples per identity. We introduce a compact adapter network that benefits from additional negative face images when combined with distinct cost functions, such as Objectosphere Loss (OS) and the proposed Maximal Entropy Loss (MEL). MEL modifies the traditional Cross-Entropy loss in favor of increasing the entropy for negative samples and attaches a penalty to known target classes in pursuance of gallery specialization. The proposed approach adopts pre-trained deep neural networks (DNNs) for face recognition as feature extractors. Then, the adapter network takes deep feature representations and acts as a substitute for the output layer of the pre-trained DNN in exchange for an agile domain adaptation. Promising results have been achieved following open-set protocols for three different datasets: LFW, IJB-C, and UCCS as well as state-of-the-art performance when supplementary negative data is properly selected to fine-tune the adapter network.