Deep Feature Factorization For Concept Discovery

We propose Deep Feature Factorization (DFF), a method capable of localizing similar semantic concepts within an image or a set of images. We use DFF to gain insight into a deep convolutional neural network's learned features, where we detect hierarchical cluster structures in feature space. This is visualized as heat maps, which highlight semantically matching regions across a set of images, revealing what the network `perceives' as similar. DFF can also be used to perform co-segmentation and co-localization, and we report state-of-the-art results on these tasks.

PDF Abstract ECCV 2018 PDF ECCV 2018 Abstract

Datasets


Task Dataset Model Metric Name Metric Value Global Rank Result Benchmark
Unsupervised Human Pose Estimation Tai-Chi-HD DFF MAE 494.48 # 6

Results from Other Papers


Task Dataset Model Metric Name Metric Value Rank Source Paper Compare
Unsupervised Facial Landmark Detection MAFL Unaligned DFF NME 31.30 # 7

Methods


No methods listed for this paper. Add relevant methods here