DeepAI
Log In Sign Up

Mimicking Ensemble Learning with Deep Branched Networks

02/21/2017
by   Byungju Kim, et al.
0

This paper proposes a branched residual network for image classification. It is known that high-level features of deep neural network are more representative than lower-level features. By sharing the low-level features, the network can allocate more memory to high-level features. The upper layers of our proposed network are branched, so that it mimics the ensemble learning. By mimicking ensemble learning with single network, we have achieved better performance on ImageNet classification task.

READ FULL TEXT
08/29/2020

New feature for Complex Network based on Ant Colony Optimization for High Level Classification

Low level classification extracts features from the elements, i.e. physi...
04/19/2016

Deep Saliency with Encoded Low level Distance Map and High Level Features

Recent advances in saliency detection have utilized deep learning to obt...
11/26/2018

Combining High-Level Features of Raw Audio Waves and Mel-Spectrograms for Audio Tagging

In this paper, we describe our contribution to Task 2 of the DCASE 2018 ...
11/15/2018

Selective Feature Connection Mechanism: Concatenating Multi-layer CNN Features with a Feature Selector

Different layers of deep convolutional neural networks(CNN) can encode d...
08/07/2020

Revisiting Mid-Level Patterns for Distant-Domain Few-Shot Recognition

Cross-domain few-shot learning (FSL) is proposed recently to transfer kn...
07/12/2022

Contrastive Deep Supervision

The success of deep learning is usually accompanied by the growth in neu...
11/29/2018

On the Transferability of Representations in Neural Networks Between Datasets and Tasks

Deep networks, composed of multiple layers of hierarchical distributed r...