Deep Feature Factorization For Concept Discovery

06/26/2018
by   Edo Collins, et al.
0

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.

READ FULL TEXT

page 1

page 3

page 9

page 14

research
08/02/2019

Recognizing Image Objects by Relational Analysis Using Heterogeneous Superpixels and Deep Convolutional Features

Superpixel-based methodologies have become increasingly popular in compu...
research
11/21/2016

Efficient Convolutional Neural Network with Binary Quantization Layer

In this paper we introduce a novel method for segmentation that can bene...
research
04/17/2019

Image Resizing by Reconstruction from Deep Features

Traditional image resizing methods usually work in pixel space and use v...
research
03/19/2020

Deep convolutional embedding for digitized painting clustering

Clustering artworks is difficult because of several reasons. On one hand...
research
04/22/2022

SegDiscover: Visual Concept Discovery via Unsupervised Semantic Segmentation

Visual concept discovery has long been deemed important to improve inter...
research
11/16/2016

Deep Feature Interpolation for Image Content Changes

We propose Deep Feature Interpolation (DFI), a new data-driven baseline ...
research
12/03/2019

A Step Towards Exposing Bias in Trained Deep Convolutional Neural Network Models

We present Smooth Grad-CAM++, a technique which combines two recent tech...

Please sign up or login with your details

Forgot password? Click here to reset