Using Sparse R-CNN As A Detection Model

Written by zetyquickly | Published 2021/05/02
Tech Story Tags: computer-vision | transformers | machine-learning | detector | object-detection | image-detection | yolo-object-detection | image-recognition

TLDR Sparse R-CNN is a new method that works with sparse convolutions on 3D computer vision tasks such that. It achieves near state-of-the-art performance in object detection and uses completely sparse and learnable bounding boxes generation. The architecture is elegant. It consists of FPN based backbone that acquires features from images, and. extractable features from. and. the main contribution to neural nets architecture of this very very. interactive head. Each feature is fed into its own “exclusive feature for object and classification, where each head is conditioned on specific. feature”via the TL;DR App

no story

Written by zetyquickly | Machine learning enthusiast. Research engineer at Skoltech.
Published by HackerNoon on 2021/05/02