Papers › DAS: A Deformable Attention to Capture Salient Information in CNNs

DAS: A Deformable Attention to Capture Salient Information in CNNs

20 Nov 2023arXiv:2311.12091archive 2025-07-28

Farzad Salajegheh, Nader Asadi, Soroush Saryazdi, Sudhir Mudur

Convolutional Neural Networks (CNNs) excel in local spatial pattern recognition. For many vision tasks, such as object recognition and segmentation, salient information is also present outside CNN's kernel boundaries. However, CNNs struggle in capturing such relevant information due to their confined receptive fields. Self-attention can improve a model's access to global information but increases computational overhead. We present a fast and simple fully convolutional method called DAS that helps focus attention on relevant information. It uses deformable convolutions for the location of pertinent image regions and separable convolutions for efficiency. DAS plugs into existing CNNs and propagates relevant information using a gating mechanism. Compared to the O(n^2) computational complexity of transformer-style attention, DAS is O(n). Our claim is that DAS's ability to pay increased attention to relevant features results in performance improvements when added to popular CNNs for Image Classification and Object Detection. For example, DAS yields an improvement on Stanford Dogs (4.47%), ImageNet (1.91%), and COCO AP (3.3%) with base ResNet50 backbone. This outperforms other CNN attention mechanisms while using similar or less FLOPs. Our code will be publicly available.

PaperPDF

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

Code

No code repository is listed for this paper in the archive or in Syntology's graph.

Code Syntology ran Syntology

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

Tasks

Image ClassificationObject DetectionObject Recognitionimage-classificationobject-detection

Results from the paper archive 2025-07-28

TaskDatasetModelMetricValueRank at snapshotLeaderboardReport
Object Detection MSCOCO DAS Average mAP 39.7 #1 of 1 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

BASEFocus

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