Learning Deep Parsimonious Representations

NeurIPS 2016 Renjie LiaoAlex SchwingRichard ZemelRaquel Urtasun

In this paper we aim at facilitating generalization for deep networks while supporting interpretability of the learned representations. Towards this goal, we propose a clustering based regularization that encourages parsimonious representations... (read more)

PDF Abstract
TASK DATASET MODEL METRIC NAME METRIC VALUE GLOBAL RANK LEADERBOARD
Few-Shot Image Classification CUB-200 - 0-Shot Learning Sample Clustering Accuracy 44.3% # 3