Tasks SotA Datasets Papers Methods Submit About

Papers With Code 2

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

Explore

Notable Benchmarks All SotA Datasets Papers Methods

Community

Submit Results About

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

Methods/RoIAlign

RoIAlign

Computer VisionIntroduced 2000611 papers

Description

Region of Interest Align, or RoIAlign, is an operation for extracting a small feature map from each RoI in detection and segmentation based tasks. It removes the harsh quantization of RoI Pool, properly aligning the extracted features with the input. To avoid any quantization of the RoI boundaries or bins (using $x/16$ instead of $[x/16]$ ), RoIAlign uses bilinear interpolation to compute the exact values of the input features at four regularly sampled locations in each RoI bin, and the result is then aggregated (using max or average).

Papers Using This Method

BlenderFusion: 3D-Grounded Visual Editing and Generative Compositing2025-06-20 A novel visual data-based diagnostic approach for estimation of regime transition in pool boiling2025-06-12 Bringing SAM to new heights: Leveraging elevation data for tree crown segmentation from drone imagery2025-06-05 Hierarchical Text Classification Using Contrastive Learning Informed Path Guided Hierarchy2025-06-04 Zero-to-Hero: Zero-Shot Initialization Empowering Reference-Based Video Appearance Editing2025-05-29 Force Prompting: Video Generation Models Can Learn and Generalize Physics-based Control Signals2025-05-26 OB3D: A New Dataset for Benchmarking Omnidirectional 3D Reconstruction Using Blender2025-05-26 Detailed Evaluation of Modern Machine Learning Approaches for Optic Plastics Sorting2025-05-22 SurgPose: Generalisable Surgical Instrument Pose Estimation using Zero-Shot Learning and Stereo Vision2025-05-16 KG-HTC: Integrating Knowledge Graphs into LLMs for Effective Zero-shot Hierarchical Text Classification2025-05-08 A Robust Deep Networks based Multi-Object MultiCamera Tracking System for City Scale Traffic2025-05-01 DARTer: Dynamic Adaptive Representation Tracker for Nighttime UAV Tracking2025-05-01 Transcending Dimensions using Generative AI: Real-Time 3D Model Generation in Augmented Reality2025-04-27 Learning Underwater Active Perception in Simulation2025-04-23 Real-time Seafloor Segmentation and Mapping2025-04-14 From Specificity to Generality: Revisiting Generalizable Artifacts in Detecting Face Deepfakes2025-04-07 BlenderGym: Benchmarking Foundational Model Systems for Graphics Editing2025-04-02 RipVIS: Rip Currents Video Instance Segmentation Benchmark for Beach Monitoring and Safety2025-04-01 AI-Assisted Colonoscopy: Polyp Detection and Segmentation using Foundation Models2025-03-31 Assessing SAM for Tree Crown Instance Segmentation from Drone Imagery2025-03-26