NPCFace: Negative-Positive Collaborative Training for Large-scale Face Recognition

2020-07-20 · Dan Zeng, Hailin Shi, Hang Du, Jun Wang, Zhen Lei, Tao Mei

The training scheme of deep face recognition has greatly evolved in the past years, yet it encounters new challenges in the large-scale data situation where massive and diverse hard cases occur. Especially in the range of low false accept rate (FAR), there are various hard cases in both positives (intra-class) and negatives (inter-class). In this paper, we study how to make better use of these hard samples for improving the training. The literature approaches this by margin-based formulation in either positive logit or negative logits. However, the correlation between hard positive and hard negative is overlooked, and so is the relation between the margins in positive and negative logits. We find such correlation is significant, especially in the large-scale dataset, and one can take advantage from it to boost the training via relating the positive and negative margins for each training sample. To this end, we propose an explicit collaboration between positive and negative margins sample-wisely. Given a batch of hard samples, a novel Negative-Positive Collaboration loss, named NPCFace, is formulated, which emphasizes the training on both negative and positive hard cases via the collaborative-margin mechanism in the softmax logits, and also brings better interpretation of negative-positive hardness correlation. Besides, the emphasis is implemented with an improved formulation to achieve stable convergence and flexible parameter setting. We validate the effectiveness of our approach on various benchmarks of large-scale face recognition, and obtain advantageous results especially in the low FAR range.

📄 PDF Abstract BibTeX arXiv:2007.10172

Code (0)

등록된 구현이 없습니다.

Tasks

Face Recognition

Methods 이 논문이 사용한 방법론

Softmax The Softmax output function transforms a previous layer's output into a vector of probabilities. It is commonly used for multiclass classification. Given an input vector $x$…

Bootstrapping User and Item Representations for One-Class Collaborative Filtering

2021-05-13 · Dongha Lee, SeongKu Kang, Hyunjun Ju, Chanyoung Park 외

The goal of one-class collaborative filtering (OCCF) is to identify the user-item pairs that are positively-related but have not been interacted yet, where only a small portion of positive user-item interactions (e.g., u…

Collaborative Filtering Data Augmentation

SelfCF: A Simple Framework for Self-supervised Collaborative Filtering

2021-07-07 · Xin Zhou, Aixin Sun, Yong liu, Jie Zhang 외

Collaborative filtering (CF) is widely used to learn informative latent representations of users and items from observed interactions. Existing CF-based methods commonly adopt negative sampling to discriminate different …

Collaborative Filtering Self-Supervised Learning

Adaptive Hardness Negative Sampling for Collaborative Filtering

2024-01-10 · Riwei Lai, Rui Chen, Qilong Han, Chi Zhang 외

Negative sampling is essential for implicit collaborative filtering to provide proper negative training signals so as to achieve desirable performance. We experimentally unveil a common limitation of all existing negativ…

Collaborative Filtering

SimCE: Simplifying Cross-Entropy Loss for Collaborative Filtering

2024-06-23 · Xiaodong Yang, Huiyuan Chen, Yuchen Yan, Yuxin Tang 외

The learning objective is integral to collaborative filtering systems, where the Bayesian Personalized Ranking (BPR) loss is widely used for learning informative backbones. However, BPR often experiences slow convergence…

Collaborative Filtering Recommendation Systems

TFPS: A Temporal Filtration-enhanced Positive Sample Set Construction Method for Implicit Collaborative Filtering

2026-02-26 · Jiayi Wu, Zhengyu Wu, Xunkai Li, Rong-Hua Li 외 arxiv

The negative sampling strategy can effectively train collaborative filtering (CF) recommendation models based on implicit feedback by constructing positive and negative samples. However, existing methods primarily optimi…