</> Code with Papers by Syntology

Papers › CLCNet: Rethinking of Ensemble Modeling with Classification Confidence Network

CLCNet: Rethinking of Ensemble Modeling with Classification Confidence Network

19 May 2022arXiv:2205.09612archive 2025-07-28

Yao-Ching Yu, Shi-Jinn Horng

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: https://github.com/yaoching0/CLCNet-Rethinking-of-Ensemble-Modeling.

PaperPDFCode

Code

yaoching0/clcnet-rethinking-of-ensemble-modeling officialmentioned in papermentioned on GitHubpytorch report

Repository list and official/mentioned flags are the archive's, frozen 2025-07-28. Reachability, where shown, is from one Syntology probe window (2026-09-16 to 2026-09-18); repositories not probed show nothing. GitHub stars are not tracked.

Code Syntology ran Syntology

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

Tasks

ClassificationEnsemble LearningImage Classification

Results from the paper archive 2025-07-28

TaskDatasetModelMetricValueRank at snapshotLeaderboardReport
Image Classification ImageNet CLCNet (S:ViT+D:EffNet-B7) (retrain) GFLOPs 51.93 #131 of 1060 Archive leaderboard report
Image Classification ImageNet CLCNet (S:ViT+D:EffNet-B7) (retrain) Top 1 Accuracy 86.61% #131 of 1060 Archive leaderboard report
Image Classification ImageNet CLCNet (S:ViT+D:VOLO-D3) (retrain) GFLOPs 57.46 #142 of 1060 Archive leaderboard report
Image Classification ImageNet CLCNet (S:ViT+D:VOLO-D3) (retrain) Top 1 Accuracy 86.46% #142 of 1060 Archive leaderboard report
Image Classification ImageNet CLCNet (S:ConvNeXt-L+D:EffNet-B7) (retrain) GFLOPs 45.43 #143 of 1060 Archive leaderboard report
Image Classification ImageNet CLCNet (S:ConvNeXt-L+D:EffNet-B7) (retrain) Top 1 Accuracy 86.42% #143 of 1060 Archive leaderboard report
Image Classification ImageNet CLCNet (S:D1+D:D5) GFLOPs 47.43 #243 of 1060 Archive leaderboard report
Image Classification ImageNet CLCNet (S:D1+D:D5) Top 1 Accuracy 85.28% #243 of 1060 Archive leaderboard report
Image Classification ImageNet CLCNet (S:B4+D:B7) GFLOPs 18.58 #383 of 1060 Archive leaderboard report
Image Classification ImageNet CLCNet (S:B4+D:B7) Top 1 Accuracy 83.88% #383 of 1060 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.

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