3 repositorios
Methods like generalized focal loss to improve localization quality during training.
Distinct from Detection Model Validation: Distinct from model validation: focuses on training-time refinement logic rather than post-training evaluation.
Explore 3 awesome GitHub repositories matching artificial intelligence & ml · Bounding Box Refinement Techniques. Refine with filters or upvote what's useful.
PaddleDetection is an object detection framework designed for the end-to-end development, training, and deployment of computer vision models. It provides a comprehensive library of modular neural network architectures and pipelines that support object detection, instance segmentation, and multi-object tracking tasks. The project distinguishes itself through a configuration-driven approach that decouples model components like backbones and heads, allowing for the flexible assembly of custom vision workflows. It incorporates advanced techniques such as anchor-free detection logic, joint detecti
Refines bounding box quality during training using generalized focal loss techniques.
tensorrtx is a computer vision inference engine and model implementation library designed for graphics processor acceleration. It provides a framework for optimizing deep learning models through a GPU inference optimizer, a deep learning model converter for transforming weights from frameworks like TensorFlow and PyTorch, and a custom plugin library to implement operations not natively supported by the TensorRT API. The project distinguishes itself through a comprehensive collection of pre-defined network implementations, ranging from various YOLO versions and DETR transformers for object det
Provides post-processing logic to refine bounding box predictions and handle multi-output tensors after inference.
CenterNet es un framework de detección de objetos por puntos centrales y una tubería (pipeline) de visión artificial en tiempo real. Identifica objetos y poses prediciendo puntos centrales en lugar de utilizar cajas de anclaje (anchor boxes). El sistema funciona como un estimador de cajas delimitadoras 3D, un modelo de estimación de pose humana y una herramienta para la detección de objetos en tiempo real. Trata la ubicación de las articulaciones y las posiciones de los objetos como problemas de detección de puntos centrales para localizar entidades en imágenes y en el espacio tridimensional. Las capacidades cubren la detección de objetos 3D, la estimación de puntos clave humanos y el análisis de video en vivo. La tubería utiliza un proceso de inferencia de alimentación directa (feedforward) de una sola etapa para realizar análisis continuo en cámaras web o archivos de video.
Predicts local offsets to correct quantization errors and refine bounding box precision.