mlsanityData to 7 Oct 2026

Poly Kernel Inception Network for Remote Sensing Detection

arXiv 2403.06258 ↗First posted 10 Mar 2024cs.CVcited by 52

Not on the map. Why?

Abstract (arXiv)

Object detection in remote sensing images (RSIs) often suffers from several increasing challenges, including the large variation in object scales and the diverse-ranging context. Prior methods tried to address these challenges by expanding the spatial receptive field of the backbone, either through large-kernel convolution or dilated convolution. However, the former typically introduces considerable background noise, while the latter risks generating overly sparse feature representations. In this paper, we introduce the Poly Kernel Inception Network (PKINet) to handle the above challenges. PKINet employs multi-scale convolution kernels without dilation to extract object features of varying scales and capture local context. In addition, a Context Anchor Attention (CAA) module is introduced in parallel to capture long-range contextual information. These two components work jointly to advance the performance of PKINet on four challenging remote sensing detection benchmarks, namely DOTA-v1.0, DOTA-v1.5, HRSC2016, and DIOR-R.

Key facts. Cited by 52 papers in the map (data through 7 Oct 2026). Builds on 50 of its 84 references that are in the map. First posted on arXiv 10 Mar 2024.

Builds on

50 of 84 references.

References · 50

  1. 2015Deep Residual Learning for Image Recognitioncited by 51,809
  2. 2014Adam: A Method for Stochastic Optimizationcited by 36,960
  3. 2014Microsoft COCO: Common Objects in Contextcited by 17,498
  4. 2014Very Deep Convolutional Networks for Large-Scale Image Recognitioncited by 15,267
  5. 2021Swin Transformer: Hierarchical Vision Transformer using Shifted Windowscited by 12,082
  6. 2015Faster R-CNN: Towards Real-Time Object Detection with Region Proposal Networkscited by 9,617
  7. 2017Mask R-CNNcited by 7,259
  8. 2015Rethinking the Inception Architecture for Computer Visioncited by 5,451
  9. 2016Feature Pyramid Networks for Object Detectioncited by 5,021
  10. 2016SGDR: Stochastic Gradient Descent with Warm Restartscited by 4,993
  11. 2022A ConvNet for the 2020scited by 3,545
  12. 2015SSD: Single Shot MultiBox Detectorcited by 3,125
38 more
  1. 2021Pyramid Vision Transformer: A Versatile Backbone for Dense Prediction without Convolutionscited by 1,960
  2. 2019FCOS: Fully Convolutional One-Stage Object Detectioncited by 1,573
  3. 2017DOTA: A Large-scale Dataset for Object Detection in Aerial Imagescited by 622
  4. 2019Hybrid Task Cascade for Instance Segmentationcited by 479
  5. 2019CSPNet: A New Backbone that can Enhance Learning Capability of CNNcited by 381
  6. 2019Object Detection in Optical Remote Sensing Images: A Survey and A New Benchmarkcited by 339
  7. 2022SegNeXt: Rethinking Convolutional Attention Design for Semantic Segmentationcited by 252
  8. 2021Oriented R-CNN for Object Detectioncited by 230
  9. 2022Visual Attention Networkcited by 210
  10. 2021Object Detection in Aerial Images: A Large-Scale Benchmark and Challengescited by 202
  11. 2021ReDet: A Rotation-equivariant Detector for Aerial Object Detectioncited by 202
  12. 2019R3Det: Refined Single-Stage Detector with Feature Refinement for Rotating Objectcited by 193
  13. 2022RTMDet: An Empirical Study of Designing Real-Time Object Detectorscited by 192
  14. 2020Align Deep Features for Oriented Object Detectioncited by 186
  15. 2021Rethinking Rotated Object Detection with Gaussian Wasserstein Distance Losscited by 156
  16. 2021FAIR1M: A Benchmark Dataset for Fine-grained Object Recognition in High-Resolution Remote Sensing Imagerycited by 143
  17. 2022More ConvNets in the 2020s: Scaling up Kernels Beyond 51x51 using Sparsitycited by 142
  18. 2019Gliding vertex on the horizontal bounding box for multi-oriented object detectioncited by 134
  19. 2021Learning High-Precision Bounding Box for Rotated Object Detection via Kullback-Leibler Divergencecited by 130
  20. 2022MMRotate: A Rotated Object Detection Benchmark using PyTorchcited by 115
  21. 2021Anchor-free Oriented Proposal Generator for Object Detectioncited by 104
  22. 2021Oriented RepPoints for Aerial Object Detectioncited by 102
  23. 2023InceptionNeXt: When Inception Meets ConvNeXtcited by 84
  24. 2020Dense Label Encoding for Boundary Discontinuity Free Rotation Detectioncited by 79
  25. 2019Learning Modulated Loss for Rotated Object Detectioncited by 73
  26. 2022The KFIoU Loss for Rotated Object Detectioncited by 73
  27. 2020Dynamic Refinement Network for Oriented and Densely Packed Object Detectioncited by 72
  28. 2020Dynamic Anchor Learning for Arbitrary-Oriented Object Detectioncited by 70
  29. 2020Oriented Object Detection in Aerial Images with Box Boundary-Aware Vectorscited by 63
  30. 2022AO2-DETR: Arbitrary-Oriented Object Detection Transformercited by 55
  31. 2023Adaptive Rotated Convolution for Rotated Object Detectioncited by 51
  32. 2022GhostNetV2: Enhance Cheap Operation with Long-Range Attentioncited by 44
  33. 2023Dynamic Coarse-to-Fine Learning for Oriented Tiny Object Detectioncited by 43
  34. 2021A General Gaussian Heatmap Label Assignment for Arbitrary-Oriented Object Detectioncited by 22
  35. 2021Oriented Object Detection with Transformercited by 20
  36. 2022G-Rep: Gaussian Representation for Arbitrary-Oriented Object Detectioncited by 20
  37. 2020Dynamic Scale Training for Object Detectioncited by 15
  38. 2021Rotation Equivariant Feature Image Pyramid Network for Object Detection in Optical Remote Sensing Imagerycited by 11

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2024: 9; 2025: 23; 2026: 20.

52 papers.

Sort:

By area:

  1. 2024STAR: A First-Ever Dataset and A Large-Scale Benchmark for Scene Graph Generation in Large-Size Satellite Imagerycited by 31
  2. 2024Cross-Modal Bidirectional Interaction Model for Referring Remote Sensing Image Segmentationcited by 26
  3. 2024DMM: Disparity-guided Multispectral Mamba for Oriented Object Detection in Remote Sensingcited by 19
  4. 2025Strip R-CNN: Large Strip Convolution for Remote Sensing Object Detectioncited by 14
  5. 2024SOOD++: Leveraging Unlabeled Data to Boost Oriented Object Detectioncited by 12
  6. 2025LWGANet: Addressing Spatial and Channel Redundancy in Remote Sensing Visual Tasks with Light-Weight Grouped Attentioncited by 10
  7. 2025Semi-supervised Semantic Segmentation for Remote Sensing Images via Multi-scale Uncertainty Consistency and Cross-Teacher-Student Attentioncited by 10
  8. 2025Frequency-Dynamic Attention Modulation for Dense Predictioncited by 10
  9. 2025OpenRSD: Towards Open-prompts for Object Detection in Remote Sensing Imagescited by 9
  10. 2024Knowledge Transfer with Simulated Inter-Image Erasing for Weakly Supervised Semantic Segmentationcited by 8
  11. 2025Semi-supervised Semantic Segmentation with Multi-Constraint Consistency Learningcited by 8
  12. 2024CCi-YOLOv8n: Enhanced Fire Detection with CARAFE and Context-Guided Modulescited by 7
38 more
  1. 2025LEGNet: A Lightweight Edge-Gaussian Network for Low-Quality Remote Sensing Image Object Detectioncited by 7
  2. 2025Seeing What Matters: Empowering CLIP with Patch Generation-to-Selectioncited by 7
  3. 2025Measuring the Impact of Rotation Equivariance on Aerial Object Detectioncited by 4
  4. 2026PCA-Seg: Revisiting Cost Aggregation for Open-Vocabulary Semantic and Part Segmentationcited by 4
  5. 2024Relating CNN-Transformer Fusion Network for Change Detectioncited by 3
  6. 2025MHAF-YOLO: Multi-Branch Heterogeneous Auxiliary Fusion YOLO for accurate object detectioncited by 3
  7. 2025Enhancing Layer Attention Efficiency through Pruning Redundant Retrievalscited by 3
  8. 2026Fourier Angle Alignment for Oriented Object Detection in Remote Sensingcited by 3
  9. 2026Beyond Quadratic: Linear-Time Change Detection with RWKVcited by 3
  10. 2024ContextDet: Temporal Action Detection with Adaptive Context Aggregationcited by 2
  11. 2025Efficient Token Compression for Vision Transformer with Spatial Information Preservedcited by 2
  12. 2025OmniESI: A unified framework for enzyme-substrate interaction prediction with progressive conditional deep learningcited by 2
  13. 2025MRC-DETR: An Adaptive Multi-Residual Coupled Transformer for Bare Board PCB Defect Detectioncited by 2
  14. 2025FSG-Net: Frequency-Spatial Synergistic Gated Network for High-Resolution Remote Sensing Change Detectioncited by 2
  15. 2025DEPFusion: Dual-Domain Enhancement and Priority-Guided Mamba Fusion for UAV Multispectral Object Detectioncited by 2
  16. 2026Open-Text Aerial Detection: A Unified Framework For Aerial Visual Grounding And Detectioncited by 2
  17. 2026Real-Time Oriented Object Detection Transformer in Remote Sensing Imagescited by 2
  18. 2025YOLO-RS: Remote Sensing Enhanced Crop Detection Methodscited by 1
  19. 2025MASF-YOLO: An Improved YOLOv11 Network for Small Object Detection on Drone Viewcited by 1
  20. 2026UniRoute: Unified Routing Mixture-of-Experts for Modality-Adaptive Remote Sensing Change Detectioncited by 1
  21. 2026RiO-DETR: DETR for Real-time Oriented Object Detectioncited by 1
  22. 2026Efficiency Follows Global-Local Decouplingcited by 1
  23. 2026Digital-to-Physical Transfer of Adversarial Patches for Aerial Vehicle Detectioncited by 1
  24. 2024Category-Aware Dynamic Label Assignment with High-Quality Oriented Proposalcited by 0
  25. 2025EDNet: Edge-Optimized Small Target Detection in UAV Imagery -- Faster Context Attention, Better Feature Fusion, and Hardware Accelerationcited by 0
  26. 2025HGNet: High-Order Spatial Awareness Hypergraph and Multi-Scale Context Attention Network for Colorectal Polyp Detectioncited by 0
  27. 2025Multi-needle Localization for Pelvic Seed Implant Brachytherapy based on Tip-handle Detection and Matchingcited by 0
  28. 2025A Spatial Semantics and Continuity Perception Attention for Remote Sensing Water Body Change Detectioncited by 0
  29. 2025Shift-Window Meets Dual Attention: A Multi-Model Architecture for Specular Highlight Removalcited by 0
  30. 2026Combating Noisy Labels through Fostering Self- and Neighbor-Consistencycited by 0
  31. 2026Towards Remote Sensing Change Detection with Neural Memorycited by 0
  32. 2026FGAA-FPN: Foreground-Guided Angle-Aware Feature Pyramid Network for Oriented Object Detectioncited by 0
  33. 2026RMK RetinaNet: Rotated Multi-Kernel RetinaNet for Robust Oriented Object Detection in Remote Sensing Imagerycited by 0
  34. 2026PKINet-v2: Towards Powerful and Efficient Poly-Kernel Remote Sensing Object Detectioncited by 0
  35. 2026PLAS-Net: Pixel-Level Area Segmentation for UAV-Based Beach Litter Monitoringcited by 0
  36. 2026SLIP-RS: Structured-Attribute Language-Image Pre-Training for Remote Sensing Object Detectioncited by 0
  37. 2026BMCR: Adaptive Backbone Module Composition via Reinforcement Learning for Remote Sensing Object Detectioncited by 0
  38. 2026Core-KAN: Continuous Vision Kernels with Kolmogorov-Arnold Networkscited by 0

50 most cited of 52 All 52 (JSON)