{"about":{"site":"https://codewithpapers.app","non_affiliation":"Code with Papers and Syntology are not affiliated with, endorsed by, or sponsored by Papers with Code, Meta, or the pwc-archive mirror.","licence":"CC BY-SA 4.0","licence_url":"https://creativecommons.org/licenses/by-sa/4.0/legalcode","attribution":"https://codewithpapers.app/attribution","modified":"archive material modified by Syntology; see the attribution page"},"url":"/paper/efficient-adaptive-ensembling-for-image","title":"Efficient Adaptive Ensembling for Image Classification","arxiv_id":"2206.07394","date":"2022-06-15","proceeding":"Expert Systems, Wiley 2023 8","authors":["Antonio Bruno","Davide Moroni","Massimo Martinelli"],"abstract":"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.","url_abs":"https://arxiv.org/abs/2206.07394v3","url_pdf":"https://arxiv.org/pdf/2206.07394v3.pdf","source":{"archive":"pwc-archive (Hugging Face), CC BY-SA 4.0","snapshot":"2025-07-28","licence_url":"https://creativecommons.org/licenses/by-sa/4.0/legalcode","row_kind":"abstracts"},"code_links":[],"tasks":[{"task_slug":"classification-1","task_name":"Classification"},{"task_slug":"image-classification","task_name":"Image Classification"},{"task_slug":"image-classification","task_name":"image-classification"}],"methods":[{"method_slug":"1x1-convolution","method_name":"1x1 Convolution"},{"method_slug":"adabelief","method_name":"Adabelief"},{"method_slug":"average-pooling","method_name":"Average Pooling"},{"method_slug":"batch-normalization","method_name":"Batch Normalization"},{"method_slug":"convolution","method_name":"Convolution"},{"method_slug":"dense-connections","method_name":"Dense Connections"},{"method_slug":"depthwise-convolution","method_name":"Depthwise Convolution"},{"method_slug":"depthwise-separable-convolution","method_name":"Depthwise Separable Convolution"},{"method_slug":"dropout","method_name":"Dropout"},{"method_slug":"efficientnet","method_name":"EfficientNet"},{"method_slug":"inverted-residual-block","method_name":"Inverted Residual Block"},{"method_slug":"pointwise-convolution","method_name":"Pointwise Convolution"},{"method_slug":"rmsprop","method_name":"RMSProp"},{"method_slug":"relu","method_name":"ReLU"},{"method_slug":"sigmoid-activation","method_name":"Sigmoid Activation"},{"method_slug":"squeeze-and-excitation-block","method_name":"Squeeze-and-Excitation Block"}],"datasets_introduced":[],"methods_introduced":[],"results":[{"leaderboard":"/sota/image-classification-on-cifar-10","task":"Image Classification","dataset":"CIFAR-10","model":"efficient adaptive ensembling","rank_in_archive_order":263,"of":265,"metrics":{"Accuracy":"99.612"},"uses_additional_data":true},{"leaderboard":"/sota/image-classification-on-cifar-100","task":"Image Classification","dataset":"CIFAR-100","model":"efficient adaptive ensembling","rank_in_archive_order":209,"of":211,"metrics":{"Accuracy":"96.808"},"uses_additional_data":true},{"leaderboard":"/sota/image-classification-on-cinic-10","task":"Image Classification","dataset":"CINIC-10","model":"efficient adaptive ensembling","rank_in_archive_order":2,"of":9,"metrics":{"Accuracy":"95.064"},"uses_additional_data":false},{"leaderboard":"/sota/image-classification-on-flower102","task":"Image Classification","dataset":"Flower102","model":"efficient adaptive ensembling","rank_in_archive_order":1,"of":1,"metrics":{"Accuracy":"99.847"},"uses_additional_data":false},{"leaderboard":"/sota/image-classification-on-pets-sam","task":"Image Classification","dataset":"Pets SAM","model":"efficient adaptive ensembling","rank_in_archive_order":1,"of":1,"metrics":{"Accuracy":"98.22"},"uses_additional_data":false},{"leaderboard":"/sota/image-classification-on-stanford-cars","task":"Image Classification","dataset":"Stanford Cars","model":"efficient adaptive ensembling","rank_in_archive_order":1,"of":24,"metrics":{"Accuracy":"96.868"},"uses_additional_data":false}],"syntology":{"atlas_url":null,"mcp":null,"developers":"https://syntology.ai/developers"},"arxiv_metadata":null,"syntology_extracted_results":null}