Timezone: »

Self-Paced Learning with Diversity
Lu Jiang · Deyu Meng · Shoou-I Yu · Zhenzhong Lan · Shiguang Shan · Alexander Hauptmann

Thu Dec 11 11:00 AM -- 03:00 PM (PST) @ Level 2, room 210D

Self-paced learning (SPL) is a recently proposed learning regime inspired by the learning process of humans and animals that gradually incorporates easy to more complex samples into training. Existing methods are limited in that they ignore an important aspect in learning: diversity. To incorporate this information, we propose an approach called self-paced learning with diversity (SPLD) which formalizes the preference for both easy and diverse samples into a general regularizer. This regularization term is independent of the learning objective, and thus can be easily generalized into various learning tasks. Albeit non-convex, the optimization of the variables included in this SPLD regularization term for sample selection can be globally solved in linearithmic time. We demonstrate that our method significantly outperforms the conventional SPL on three real-world datasets. Specifically, SPLD achieves the best MAP so far reported in literature on the Hollywood2 and Olympic Sports datasets.

Author Information

Lu Jiang (Carnegie Mellon University)
Deyu Meng (Carnegie Mellon University)
Shoou-I Yu (Carnegie Mellon University)
Zhenzhong Lan (Carnegie Mellon University)
Shiguang Shan (Chinese Academy of Sciences)
Alexander Hauptmann (Carnegie Mellon University)

More from the Same Authors