Wasserstein CNN: Learning Invariant Features for NIR-VIS Face Recognition

8 Aug 2017Ran HeXiang WuZhenan SunTieniu Tan

Heterogeneous face recognition (HFR) aims to match facial images acquired from different sensing modalities with mission-critical applications in forensics, security and commercial sectors. However, HFR is a much more challenging problem than traditional face recognition because of large intra-class variations of heterogeneous face images and limited training samples of cross-modality face image pairs... (read more)

PDF Abstract
TASK DATASET MODEL METRIC NAME METRIC VALUE GLOBAL RANK RESULT BENCHMARK
Face Verification BUAA-VisNir W-CNN He et al. (2018) TAR @ FAR=0.001 91.9 # 3
TAR @ FAR=0.01 96.0 # 2
Face Verification Oulu-CASIA NIR-VIS W-CNN He et al. (2018) TAR @ FAR=0.001 54.6 # 3
TAR @ FAR=0.01 81.5 # 3

Results from Other Papers


TASK DATASET MODEL METRIC NAME METRIC VALUE GLOBAL RANK SOURCE PAPER COMPARE
Face Verification CASIA NIR-VIS 2.0 W-CNN He et al. (2018) TAR @ FAR=0.001 98.4 # 3

Methods used in the Paper


METHOD TYPE
🤖 No Methods Found Help the community by adding them if they're not listed; e.g. Deep Residual Learning for Image Recognition uses ResNet