Papers › Unsharp Masking Layer: Injecting Prior Knowledge in Convolutional Networks for Image...

Unsharp Masking Layer: Injecting Prior Knowledge in Convolutional Networks for Image Classification

29 Sep 2019ICANN 2019 2019 9archive 2025-07-28

Jose Carranza-Rojas, Saul Calderon-Ramirez, Adán Mora-Fallas, Michael Granados-Menani, Jordina Torrents-Barrena

Image enhancement refers to the enrichment of certain image features such as edges, boundaries, or contrast. The main objective is to process the original image so that the overall performance of visualization, classification and segmentation tasks is considerably improved. Traditional techniques require manual fine-tuning of the parameters to control enhancement behavior. To date, recent Convolutional Neural Network (CNN) approaches frequently employ the aforementioned techniques as an enriched pre-processing step. In this work, we present the first intrinsic CNN pre-processing layer based on the well-known unsharp masking algorithm. The proposed layer injects prior knowledge about how to enhance the image, by adding high frequency information to the input, to subsequently emphasize meaningful image features. The layer optimizes the unsharp masking parameters during model training, without any manual intervention. We evaluate the network performance and impact on two applications: CIFAR100 image classification, and the PlantCLEF identification challenge. Results obtained show a significant improvement over popular CNNs, yielding 9.49% and 2.42% for PlantCLEF and general-purpose CIFAR100, respectively. The design of an unsharp enhancement layer plainly boosts the accuracy with negligible performance cost on simple CNN models, as prior knowledge is directly injected to improve its robustness.

PaperPDFCode

Code

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

General ClassificationImage ClassificationImage EnhancementScene Text Detectionimage-classification

Results from the paper archive 2025-07-28

TaskDatasetModelMetricValueRank at snapshotLeaderboardReport
Image Classification CIFAR-100 ResNet20+UnsharpMaskLayer Percentage correct 60.36 #197 of 211 Archive leaderboard report
Scene Text Detection ICDAR 2013 USM (COCO TS + ICDAR–2013) F-Measure 80.40% #13 of 16 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 ConvolutionAverage PoolingBatch NormalizationBottleneck Residual BlockConvolutionGlobal Average PoolingKaiming InitializationMax PoolingReLUResidual BlockResidual Connection

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