Papers › Attentive Normalization

Attentive Normalization

4 Aug 2019ECCV 2020 8arXiv:1908.01259archive 2025-07-28

Xilai Li, Wei Sun, Tianfu Wu

In state-of-the-art deep neural networks, both feature normalization and feature attention have become ubiquitous. % with significant performance improvement shown in a vast amount of tasks. They are usually studied as separate modules, however. In this paper, we propose a light-weight integration between the two schema and present Attentive Normalization (AN). Instead of learning a single affine transformation, AN learns a mixture of affine transformations and utilizes their weighted-sum as the final affine transformation applied to re-calibrate features in an instance-specific way. The weights are learned by leveraging channel-wise feature attention. In experiments, we test the proposed AN using four representative neural architectures in the ImageNet-1000 classification benchmark and the MS-COCO 2017 object detection and instance segmentation benchmark. AN obtains consistent performance improvement for different neural architectures in both benchmarks with absolute increase of top-1 accuracy in ImageNet-1000 between 0.5\% and 2.7\%, and absolute increase up to 1.8\% and 2.2\% for bounding box and mask AP in MS-COCO respectively. We observe that the proposed AN provides a strong alternative to the widely used Squeeze-and-Excitation (SE) module. The source codes are publicly available at https://github.com/iVMCL/AOGNet-v2 (the ImageNet Classification Repo) and https://github.com/iVMCL/AttentiveNorm\_Detection (the MS-COCO Detection and Segmentation Repo).

PaperPDFConference PDFCode

In Syntology Open this paper in Syntology's Atlas, the map of the papers in Syntology's graph and their citations.

Code

iVMCL/AOGNet-v2 officialmentioned in papermentioned on GitHubpytorchNOASSERTION report
ivMCL/AttentiveNorm_Detection officialmentioned in papermentioned on GitHubpytorchApache-2.0 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 ClassificationInstance SegmentationObject DetectionSemantic Segmentationobject-detection

Results from the paper archive 2025-07-28

TaskDatasetModelMetricValueRank at snapshotLeaderboardReport
Image Classification ImageNet AOGNet-40M-AN GFLOPs 7.51 #602 of 1060 Archive leaderboard report
Image Classification ImageNet AOGNet-40M-AN Top 1 Accuracy 81.87% #602 of 1060 Archive leaderboard report
Instance Segmentation COCO minival Mask R-CNN-FPN (AOGNet-40M) AP50 63.2 #74 of 93 Archive leaderboard report
Instance Segmentation COCO minival Mask R-CNN-FPN (AOGNet-40M) AP75 43.3 #74 of 93 Archive leaderboard report
Instance Segmentation COCO minival Mask R-CNN-FPN (AOGNet-40M) mask AP 40.2 #74 of 93 Archive leaderboard report
Object Detection COCO minival Mask R-CNN-FPN (AOGNet-40M) AP50 66.2 #119 of 220 Archive leaderboard report
Object Detection COCO minival Mask R-CNN-FPN (AOGNet-40M) AP75 49.1 #119 of 220 Archive leaderboard report
Object Detection COCO minival Mask R-CNN-FPN (AOGNet-40M) box AP 44.9 #119 of 220 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 ConvolutionAttentive NormalizationAverage PoolingBatch NormalizationBottleneck Residual BlockConvolutionCosine AnnealingDepthwise ConvolutionDepthwise Separable ConvolutionFPNGlobal Average PoolingInverted Residual BlockKaiming InitializationLinear Warmup With Cosine AnnealingMask R-CNNMax PoolingPointwise ConvolutionRPNRandom Horizontal FlipRandom Resized CropReLUResidual BlockResidual ConnectionRoIAlignSGD with MomentumSoftmax

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