Papers › Increasingly Packing Multiple Facial-Informatics Modules in A Unified Deep-Learning...

Increasingly Packing Multiple Facial-Informatics Modules in A Unified Deep-Learning Model via Lifelong Learning

10 Jun 2019Proceedings of the 2019 on International Conference on Multimedia Retrieval 2019 6archive 2025-07-28

Steven C. Y. Hung, Jia-Hong Lee, Timmy S. T. Wan, Chein-Hung Chen, Yi-Ming Chan, Chu-Song Chen

Simultaneously running multiple modules is a key requirement for a smart multimedia system for facial applications including face recognition, facial expression understanding, and gender identification. To effectively integrate them, a continual learning approach to learn new tasks without forgetting is introduced. Unlike previous methods growing monotonically in size, our approach maintains the compactness in continual learning. The proposed packing-and-expanding method is effective and easy to implement, which can iteratively shrink and enlarge the model to integrate new functions. Our integrated multitask model can achieve similar accuracy with only 39.9% of the original size.

PaperPDFCode

Code

ivclab/PAE officialtf report
ivclab/CPG pytorchBSD-3-Clause report

Repository list and official/mentioned flags are the archive's, frozen 2025-07-28. Reachability, where shown, is from one Syntology probe window (2026-09-16 to 2026-09-18); repositories not probed show nothing. GitHub stars are not tracked.

Code Syntology ran Syntology

Not run by Syntology. Nothing on this page verifies that the listed code works.

Tasks

Age And Gender ClassificationContinual LearningFace RecognitionFace VerificationFacial Expression Recognition (FER)Gender PredictionLifelong learning

Results from the paper archive 2025-07-28

TaskDatasetModelMetricValueRank at snapshotLeaderboardReport
Age And Gender Classification Adience Age PAENet (single crop, tensorflow) Accuracy (5-fold) 57.3 #11 of 16 Archive leaderboard report
Age And Gender Classification Adience Gender PAENet (single crop, tensorflow) Accuracy (5-fold) 89.08 #6 of 10 Archive leaderboard report
Continual Learning Cifar100 (20 tasks) PAENet Average Accuracy 77.1 #7 of 9 Archive leaderboard report
Facial Expression Recognition (FER) AffectNet PAENet Accuracy (7 emotion) 65.29 #44 of 50 Archive leaderboard report
Gender Prediction FotW Gender PAENet Accuracy (%) 92.93 #1 of 2 Archive leaderboard report

Ranks are positions in the archive's leaderboards as they stood at the 2025-07-28 snapshot. Results published since then are not among these rows, so a rank here is not a current standing.

Report a problem or propose a change · a person checks every report against the paper or source before anything changes; decisions are listed on /corrections