Papers › Beta-Rank: A Robust Convolutional Filter Pruning Method For Imbalanced Medical Image Analysis

Beta-Rank: A Robust Convolutional Filter Pruning Method For Imbalanced Medical Image Analysis

15 Apr 2023arXiv:2304.07461archive 2025-07-28

Morteza Homayounfar, Mohamad Koohi-Moghadam, Reza Rawassizadeh, Varut Vardhanabhuti

As deep neural networks include a high number of parameters and operations, it can be a challenge to implement these models on devices with limited computational resources. Despite the development of novel pruning methods toward resource-efficient models, it has become evident that these models are not capable of handling "imbalanced" and "limited number of data points". We proposed a novel filter pruning method by considering the input and output of filters along with the values of the filters that deal with imbalanced datasets better than others. Our pruning method considers the fact that all information about the importance of a filter may not be reflected in the value of the filter. Instead, it is reflected in the changes made to the data after the filter is applied to it. In this work, three methods are compared with the same training conditions except for the ranking values of each method, and 14 methods are compared from other papers. We demonstrated that our model performed significantly better than other methods for imbalanced medical datasets. For example, when we removed up to 58% of FLOPs for the IDRID dataset and up to 45% for the ISIC dataset, our model was able to yield an equivalent (or even superior) result to the baseline model. To evaluate FLOP and parameter reduction using our model in real-world settings, we built a smartphone app, where we demonstrated a reduction of up to 79% in memory usage and 72% in prediction time. All codes and parameters for training different models are available at https://github.com/mohofar/Beta-Rank

PaperPDFCode

Code

mohofar/beta-rank officialmentioned in paperpytorch 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

Image ClassificationMedical Image AnalysisMedical Image ClassificationNetwork Pruning

Results from the paper archive 2025-07-28

TaskDatasetModelMetricValueRank at snapshotLeaderboardReport
Image Classification CIFAR-10 Beta-Rank Percentage correct 93.97 #166 of 265 Archive leaderboard report
Image Classification CIFAR-100 Beta-Rank Accuracy 74.01 #158 of 211 Archive leaderboard report
Image Classification CIFAR-100 Beta-Rank Percentage correct 74.01 #158 of 211 Archive leaderboard report
Medical Image Classification IDRiD Beta-Rank Accuracy 81.88 #1 of 2 Archive leaderboard report
Medical Image Classification ISIC 2017 Beta-Rank Accuracy 72.44 #1 of 1 Archive leaderboard report
Network Pruning CIFAR-100 Beta-Rank Accuracy 74.01 #3 of 5 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

ConvolutionPruning

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