Efficient Adaptive Ensembling for Image Classification

06/15/2022
by   Antonio Bruno, et al.
0

In recent times, except for sporadic cases, the trend in Computer Vision is to achieve minor improvements over considerable increases in complexity. To reverse this tendency, we propose a novel method to boost image classification performances without an increase in complexity. To this end, we revisited ensembling, a powerful approach, not often adequately used due to its nature of increased complexity and training time, making it viable by specific design choices. First, we trained end-to-end two EfficientNet-b0 models (known to be the architecture with the best overall accuracy/complexity trade-off in image classification) on disjoint subsets of data (i.e. bagging). Then, we made an efficient adaptive ensemble by performing fine-tuning of a trainable combination layer. In this way, we were able to outperform the state-of-the-art by an average of 0.5% on the accuracy with restrained complexity both in terms of number of parameters (by 5-60 times), and FLoating point Operations Per Second (by 10-100 times) on several major benchmark datasets, fully embracing the green AI.

READ FULL TEXT

page 1

page 2

page 3

page 4

research
01/09/2020

Compression of convolutional neural networks for high performance imagematching tasks on mobile devices

Deep neural networks have demonstrated state-of-the-art performance for ...
research
02/16/2023

Efficiency 360: Efficient Vision Transformers

Transformers are widely used for solving tasks in natural language proce...
research
10/11/2021

Investigating Transfer Learning Capabilities of Vision Transformers and CNNs by Fine-Tuning a Single Trainable Block

In recent developments in the field of Computer Vision, a rise is seen i...
research
11/07/2018

FLOPs as a Direct Optimization Objective for Learning Sparse Neural Networks

There exists a plethora of techniques for inducing structured sparsity i...
research
01/12/2020

Bag of Tricks for Retail Product Image Classification

Retail Product Image Classification is an important Computer Vision and ...
research
10/08/2018

Light-Weight RefineNet for Real-Time Semantic Segmentation

We consider an important task of effective and efficient semantic image ...
research
06/20/2022

Contextual Squeeze-and-Excitation for Efficient Few-Shot Image Classification

Recent years have seen a growth in user-centric applications that requir...

Please sign up or login with your details

Forgot password? Click here to reset