Self-informed neural network structure learning

12/20/2014
by   David Warde-Farley, et al.
0

We study the problem of large scale, multi-label visual recognition with a large number of possible classes. We propose a method for augmenting a trained neural network classifier with auxiliary capacity in a manner designed to significantly improve upon an already well-performing model, while minimally impacting its computational footprint. Using the predictions of the network itself as a descriptor for assessing visual similarity, we define a partitioning of the label space into groups of visually similar entities. We then augment the network with auxilliary hidden layer pathways with connectivity only to these groups of label units. We report a significant improvement in mean average precision on a large-scale object recognition task with the augmented model, while increasing the number of multiply-adds by less than 3

READ FULL TEXT

page 1

page 2

page 3

page 4

research
08/28/2017

Automatic Dataset Augmentation

Large scale image dataset and deep convolutional neural network (DCNN) a...
research
09/21/2017

Multi-label Pixelwise Classification for Reconstruction of Large-scale Urban Areas

Object classification is one of the many holy grails in computer vision ...
research
02/07/2018

VISER: Visual Self-Regularization

In this work, we propose the use of large set of unlabeled images as a s...
research
03/29/2020

Adaptive Object Detection with Dual Multi-Label Prediction

In this paper, we propose a novel end-to-end unsupervised deep domain ad...
research
05/19/2021

Correlated Input-Dependent Label Noise in Large-Scale Image Classification

Large scale image classification datasets often contain noisy labels. We...
research
12/06/2019

DeepEthnic: Multi-Label Ethnic Classification from Face Images

Ethnic group classification is a well-researched problem, which has been...
research
06/24/2017

Deep Mixture of Diverse Experts for Large-Scale Visual Recognition

In this paper, a deep mixture of diverse experts algorithm is developed ...

Please sign up or login with your details

Forgot password? Click here to reset