Feature Pyramid Networks
Learn how Feature Pyramid Networks build multi-scale feature representations through top-down pathways and lateral connections for robust object detection.
No direct links0 refs
👁️
Computer Vision
Object detection, feature pyramids, and visual recognition techniques.
8
Concepts
All Computer Vision Concepts
ASFF: Adaptive Spatial Feature Fusion
Learning where to fuse multi-scale features with per-pixel, per-level fusion weights. ASFF challenges FPN's uniform fusion assumption.
No direct links0 refs
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
No direct links0 refs
Anchor-Based vs Anchor-Free Object Detection
Compare anchor-based vs anchor-free object detection: Faster R-CNN and RetinaNet anchors vs FCOS and CenterNet point-based methods.
No direct links0 refs
NAS-FPN: Learning to Design Feature Pyramid Networks
Understanding how neural architecture search discovers optimal feature pyramid architectures that outperform hand-designed alternatives
No direct links0 refs
Modern Object Detection: DETR and Transformers
Understanding end-to-end object detection with transformers, from DETR's object queries to bipartite matching and attention-based localization
No direct links0 refs
NMS & Soft-NMS: Removing Duplicate Detections
Understanding Non-Maximum Suppression algorithms for object detection post-processing, from greedy NMS to soft variants
No direct links0 refs
Visual Complexity Analysis for Token Allocation
Learn how visual complexity analysis optimizes vision transformer token allocation using edge detection, FFT, and entropy metrics.
No direct links0 refs