Co-localization with Category-Consistent CNN Features and Geodesic Distance Propagation

12/10/2016
by   Hieu Le, et al.
0

Co-localization is the problem of localizing objects of the same class using only the set of images that contain them. This is a challenging task because the object detector must be built without negative examples that can lead to more informative supervision signals. The main idea of our method is to cluster the feature space of a generically pre-trained CNN, to find a set of CNN features that are consistently and highly activated for an object category, which we call category-consistent CNN features. Then, we propagate their combined activation map using superpixel geodesic distances for co-localization. In our first set of experiments, we show that the proposed method achieves state-of-the-art performance on three related benchmarks: PASCAL 2007, PASCAL-2012, and the Object Discovery dataset. We also show that our method is able to detect and localize truly unseen categories, on six held-out ImageNet categories with accuracy that is significantly higher than previous state-of-the-art. Our intuitive approach achieves this success without any region proposals or object detectors, and can be based on a CNN that was pre-trained purely on image classification tasks without further fine-tuning.

READ FULL TEXT

page 1

page 4

page 5

page 6

page 7

page 9

research
10/26/2017

Class Correlation affects Single Object Localization using Pre-trained ConvNets

The problem of object localization has become one of the mainstream prob...
research
04/11/2019

An Analysis of Pre-Training on Object Detection

We provide a detailed analysis of convolutional neural networks which ar...
research
06/24/2015

Deep CNN Ensemble with Data Augmentation for Object Detection

We report on the methods used in our recent DeepEnsembleCoco submission ...
research
07/20/2017

Unsupervised Object Discovery and Co-Localization by Deep Descriptor Transforming

Reusable model design becomes desirable with the rapid expansion of comp...
research
05/08/2017

Deep Descriptor Transforming for Image Co-Localization

Reusable model design becomes desirable with the rapid expansion of mach...
research
08/28/2020

Background Splitting: Finding Rare Classes in a Sea of Background

We focus on the real-world problem of training accurate deep models for ...
research
11/04/2014

Do Convnets Learn Correspondence?

Convolutional neural nets (convnets) trained from massive labeled datase...

Please sign up or login with your details

Forgot password? Click here to reset