DeepAI AI Chat
Log In Sign Up

CLCNet: Rethinking of Ensemble Modeling with Classification Confidence Network

by   Yao-Ching Yu, et al.

In this paper, we propose a Classification Confidence Network (CLCNet) that can determine whether the classification model classifies input samples correctly. It can take a classification result in the form of vector in any dimension, and return a confidence score as output, which represents the probability of an instance being classified correctly. We can utilize CLCNet in a simple cascade structure system consisting of several SOTA (state-of-the-art) classification models, and our experiments show that the system can achieve the following advantages: 1. The system can customize the average computation requirement (FLOPs) per image while inference. 2. Under the same computation requirement, the performance of the system can exceed any model that has identical structure with the model in the system, but different in size. In fact, this is a new type of ensemble modeling. Like general ensemble modeling, it can achieve higher performance than single classification model, yet our system requires much less computation than general ensemble modeling. We have uploaded our code to a github repository:


page 1

page 2

page 3

page 4


Towards Inference Efficient Deep Ensemble Learning

Ensemble methods can deliver surprising performance gains but also bring...

Self-Ensemble Protection: Training Checkpoints Are Good Data Protectors

As data become increasingly vital for deep learning, a company would be ...

Deep Network Ensemble Learning applied to Image Classification using CNN Trees

Traditional machine learning approaches may fail to perform satisfactori...

Ensemble-based gradient inference for particle methods in optimization and sampling

We propose an approach based on function evaluations and Bayesian infere...

The choice of scaling technique matters for classification performance

Dataset scaling, also known as normalization, is an essential preprocess...

A Comparative Analysis of the Ensemble Methods for Drug Design

Quantitative structure-activity relationship (QSAR) is a computer modeli...

Code Repositories



view repo