TasksSotADatasetsPapersMethodsSubmitAbout
Papers With Code 2

A community resource for machine learning research: papers, code, benchmarks, and state-of-the-art results.

Explore

Notable BenchmarksAll SotADatasetsPapersMethods

Community

Submit ResultsAbout

Data sourced from the PWC Archive (CC-BY-SA 4.0). Built by the community, for the community.

Methods/Adaptive Feature Pooling

Adaptive Feature Pooling

Computer VisionIntroduced 200020 papers
Source Paper

Description

Adaptive Feature Pooling pools features from all levels for each proposal in object detection and fuses them for the following prediction. For each proposal, we map them to different feature levels. Following the idea of Mask R-CNN, RoIAlign is used to pool feature grids from each level. Then a fusion operation (element-wise max or sum) is utilized to fuse feature grids from different levels.

The motivation for this technique is that in an FPN we assign proposals to different feature levels based on the size of proposals, which could be suboptimal if images with small differences are assigned to different levels, or if the importance of features is not strongly correlated to their level which they belong.

Papers Using This Method

YOLO-LLTS: Real-Time Low-Light Traffic Sign Detection via Prior-Guided Enhancement and Multi-Branch Feature Interaction2025-03-18A Lightweight Insulator Defect Detection Model Based on Drone Images2024-08-26CSTA: CNN-based Spatiotemporal Attention for Video Summarization2024-05-20PANet: A Physics-guided Parametric Augmentation Net for Image Dehazing by Hazing2024-04-14A Parallel Attention Network for Cattle Face Recognition2024-03-29Toward Robust Canine Cardiac Diagnosis: Deep Prototype Alignment Network-Based Few-Shot Segmentation in Veterinary Medicine2024-03-11More than the Sum of Its Parts: Ensembling Backbone Networks for Few-Shot Segmentation2024-02-09Bridging Synthetic and Real Worlds for Pre-training Scene Text Detectors2023-12-08Feature Aggregation in Joint Sound Classification and Localization Neural Networks2023-10-29PANet: LiDAR Panoptic Segmentation with Sparse Instance Proposal and Aggregation2023-06-27Unconstrained Face Sketch Synthesis via Perception-Adaptive Network and A New Benchmark2021-12-02PANet: Perspective-Aware Network with Dynamic Receptive Fields and Self-Distilling Supervision for Crowd Counting2021-10-31CPNet: Cycle Prototype Network for Weakly-supervised 3D Renal Compartments Segmentation on CT Images2021-08-15Weakly-supervised Part-Attention and Mentored Networks for Vehicle Re-Identification2021-07-17Pyramid Attention Networks for Image Restoration2020-04-28YOLOv4: Optimal Speed and Accuracy of Object Detection2020-04-23CSPNet: A New Backbone that can Enhance Learning Capability of CNN2019-11-27PANet: Few-Shot Image Semantic Segmentation with Prototype Alignment2019-08-18iSAID: A Large-scale Dataset for Instance Segmentation in Aerial Images2019-05-30Path Aggregation Network for Instance Segmentation2018-03-05