RoI Pooling, RoI Align & Deformable RoI Pooling
Understanding region-based feature extraction for object detection, from quantized pooling to sub-pixel alignment and adaptive sampling
6 min readConcept
Tagged with
computer vision
Explore machine learning concepts related to computer vision. Clear explanations and practical insights.
6
Concepts Found
Concepts Related to computer vision
Anchor-Based vs Anchor-Free Object Detection
Understanding the two fundamental paradigms of modern object detection: anchor-based methods like Faster R-CNN and RetinaNet vs anchor-free approaches like FCOS and CenterNet
8 min readConcept
NAS-FPN: Learning to Design Feature Pyramid Networks
Understanding how neural architecture search discovers optimal feature pyramid architectures that outperform hand-designed alternatives
9 min readConcept
Modern Object Detection: DETR and Transformer-Based Approaches
Understanding end-to-end object detection with transformers, from DETR's object queries to bipartite matching and attention-based localization
8 min readConcept
NMS & Soft-NMS: Removing Duplicate Detections
Understanding Non-Maximum Suppression algorithms for object detection post-processing, from greedy NMS to soft variants
7 min readConcept
Visual Complexity Analysis for Token Allocation
Advanced framework for intelligent token allocation in vision transformers based on visual complexity metrics
7 min readConcept