Papers › Efficient Adaptive Ensembling for Image Classification

Efficient Adaptive Ensembling for Image Classification

15 Jun 2022Expert Systems, Wiley 2023 8arXiv:2206.07394archive 2025-07-28

Antonio Bruno, Davide Moroni, Massimo Martinelli

In recent times, with the exception of sporadic cases, the trend in Computer Vision is to achieve minor improvements compared to considerable increases in complexity. To reverse this trend, we propose a novel method to boost image classification performances without increasing complexity. To this end, we revisited ensembling, a powerful approach, often not used properly due to its more complex nature and the training time, so as to make it feasible through a specific design choice. First, we trained two EfficientNet-b0 end-to-end models (known to be the architecture with the best overall accuracy/complexity trade-off for 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 the number of parameters (by 5-60 times), and the FLoating point Operations Per Second (FLOPS) by 10-100 times on several major benchmark datasets.

Paper PDF Conference PDF

Code

No code repository is listed for this paper in the archive or in Syntology's graph.

Code Syntology ran Syntology

Not run by Syntology. Nothing on this page verifies that the listed code works.

Tasks

Classification Image Classification image-classification

Results from the paper archive 2025-07-28

Task	Dataset	Model	Metric	Value	Rank at snapshot	Leaderboard	Report
Image Classification	CIFAR-10	efficient adaptive ensembling	Accuracy	99.612	#263 of 265	Archive leaderboard	report
Image Classification	CIFAR-100	efficient adaptive ensembling	Accuracy	96.808	#209 of 211	Archive leaderboard	report
Image Classification	CINIC-10	efficient adaptive ensembling	Accuracy	95.064	#2 of 9	Archive leaderboard	report
Image Classification	Flower102	efficient adaptive ensembling	Accuracy	99.847	#1 of 1	Archive leaderboard	report
Image Classification	Pets SAM	efficient adaptive ensembling	Accuracy	98.22	#1 of 1	Archive leaderboard	report
Image Classification	Stanford Cars	efficient adaptive ensembling	Accuracy	96.868	#1 of 24	Archive leaderboard	report

Ranks are positions in the archive's leaderboards as they stood at the 2025-07-28 snapshot. Results published since then are not among these rows, so a rank here is not a current standing.

Methods

1x1 Convolution Adabelief Average Pooling Batch Normalization Convolution Dense Connections Depthwise Convolution Depthwise Separable Convolution Dropout EfficientNet Inverted Residual Block Pointwise Convolution RMSProp ReLU Sigmoid Activation Squeeze-and-Excitation Block

Report a problem or propose a change · a person checks every report against the paper or source before anything changes; decisions are listed on /corrections