AI Paper Atlas

Research map / Benchmarks / YTF

YTF leaderboard

30 papers at ICML, NeurIPS, ICLR, CVPR, AAAI, ICCV and ECCV, and the journals TPAMI, IJCV and JMLR report results on YTF. Best accuracy: 97.92 (Ours (all) + PA, CVPR 2020).

Numbers are as each paper reports them, read by AI from its results tables and not checked by hand. Papers can differ in setting (training data, model size, extra data); the topic column shows what each paper is about. Open the paper before you compare or quote a number.

YTF · accuracy

18 papers, each with its best reported number for its own method; higher is better.

#accuracy ↑MethodPaperTopic
197.92Ours (all) + PA
Modified 100-layer ResNet
Towards Universal Representation Learning for Deep Face Recognition
CVPR 2020 · Table: Type I datasets
Recognition and long-tail
297.6CosFaceCosFace: Large Margin Cosine Loss for Deep Face Recognition
CVPR 2018 · Table: Face verification on LF
Recognition and long-tail
397.36CNN_ours
ResNet-64
Noise-Tolerant Paradigm for Training Face Recognition CNNs
CVPR 2019 · Table 2
Noisy labels
497.1(c) Feature-pair attention w/ pair selection (AFRN, K=442)Attentional Feature-Pair Relation Networks for Accurate Face Recognition
ICCV 2019 · Table 1
Recognition and long-tail
596.78DUL_cls
AM-Softmax ResNet64
Data Uncertainty Learning in Face Recognition
CVPR 2020 · Table 2
Recognition and long-tail
696.3model C (f^g + PRN+)Pairwise Relational Networks for Face Recognition
ECCV 2018 · Table 3
Recognition and long-tail
796.16DMFR(disentangle)
CosFace
Demodalizing Face Recognition with Synthetic Samples
AAAI 2021 · Table 2
Recognition and long-tail
896.12Ours (NRC+CD)
ResNet50
Unequal-Training for Deep Face Recognition With Long-Tailed Noisy Data
CVPR 2019 · Table 1
Noisy labels
995SphereFace
64-layer CNN
SphereFace: Deep Hypersphere Embedding for Face Recognition
CVPR 2017 · LFW and YTF results table
Recognition and long-tail
1082.25SR-CDLDiscriminative Covariance Oriented Representation Learning for Face Recognition With Image Sets
CVPR 2017 · Table 2
Recognition and long-tail
8 more papers on this leaderboard, the baselines reported on it and a CSV download are free with a scime account.
Sign in free to see all

YTF · verification accuracy (%)

12 papers, each with its best reported number for its own method; higher is better.

2 more papers on this leaderboard, the baselines reported on it and a CSV download are free with a scime account.
Sign in free to see all

Not affiliated with any conference, journal or the benchmark's authors. Corrections: contact@latenticlabs.com.