Class Correlation affects Single Object Localization using Pre-trained ConvNets

10/26/2017
by   Pokkalla Harsha Vardhan, et al.
0

The problem of object localization has become one of the mainstream problems of vision. Most of the algorithms proposed involve the design for the model to be specifically for localizing objects. In this paper, we explore whether a pre-trained canonical ConvNet (without fine-tuning) trained purely for object classification on one dataset with global image level labels can be used to localize objects in images containing a single instance on a separate dataset while generalizing to novel classes. We propose a simple algorithm involving cropping and blackening out regions in the image space called Explicit Image Space based Search (EISS) for locating the most responsive regions in an image in the context of object localization. EISS brings to light the interesting phenomenon of a ConvNets responding more to features within objects as opposed to object level descriptors, as the classes in the training data get more correlated (visually/semantically similar).

READ FULL TEXT

page 1

page 4

research
12/10/2016

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

Co-localization is the problem of localizing objects of the same class u...
research
02/26/2019

Mining Objects: Fully Unsupervised Object Discovery and Localization From a Single Image

The goal of our work is to discover dominant objects without using any a...
research
05/08/2017

Deep Descriptor Transforming for Image Co-Localization

Reusable model design becomes desirable with the rapid expansion of mach...
research
09/15/2022

One-Shot Transfer of Affordance Regions? AffCorrs!

In this work, we tackle one-shot visual search of object parts. Given a ...
research
12/14/2015

Learning Deep Features for Discriminative Localization

In this work, we revisit the global average pooling layer proposed in [1...
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
07/02/2016

Active Object Localization in Visual Situations

We describe a method for performing active localization of objects in in...

Please sign up or login with your details

Forgot password? Click here to reset