Dynamic Multi-Task Learning for Face Recognition with Facial Expression

8 Nov 2019Zuheng MingJunshi XiaMuhammad Muzzamil LuqmanJean-Christophe BurieKaixing Zhao

Benefiting from the joint learning of the multiple tasks in the deep multi-task networks, many applications have shown the promising performance comparing to single-task learning. However, the performance of multi-task learning framework is highly dependant on the relative weights of the tasks... (read more)

PDF Abstract

Results from the Paper


TASK DATASET MODEL METRIC NAME METRIC VALUE GLOBAL RANK RESULT BENCHMARK
Face Verification CK+ Dynamic MTL Accuracy 99 # 1
Face Verification Labeled Faces in the Wild Dynamic MTL Accuracy 99.21% # 15
Facial Expression Recognition Oulu-CASIA Dynamic MTL Accuracy (10-fold) 89.6 # 2
Face Verification Oulu-CASIA Dynamic MTL Accuracy 99.14 # 1
Face Verification YouTube Faces DB Dynamic MTL Accuracy 94.3% # 10

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