SOTAVerified

Deep Feature Factorization For Concept Discovery

2018-06-26ECCV 2018Code Available0· sign in to hype

Edo Collins, Radhakrishna Achanta, Sabine Süsstrunk

Code Available — Be the first to reproduce this paper.

Reproduce

Code

Abstract

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.

Tasks

Reproductions