Real-Time Panoptic Segmentation From Dense Detections
Authors: Rui Hou, Jie Li, Arjun Bhargava, Allan Raventos, Vitor Guizilini, Chao Fang, Jerome Lynch, Adrien Gaidon Description: Panoptic segmentation is a complex full scene parsing task requiring simultaneous instance and semantic segmentation at high resolution. Current state-of-the-art approaches cannot run in real-time, and simplifying these architectures to improve efficiency severely degrades their accuracy. In this paper, we propose a new single-shot panoptic segmentation network that leverages dense detections and a global self-attention mechanism to operate in real-time with performance approaching the state of the art. We introduce a novel parameter-free mask construction method that substantially reduces computational complexity by efficiently reusing information from the object detection and semantic segmentation sub-tasks. The resulting network has a simple data flow that requires no feature map re-sampling, enabling significant hardware acceleration. Our experiments on the Cityscapes and COCO benchmarks show that our network works at 30 FPS on 1024x2048 resolution, trading a 3% relative performance degradation from the current state of the art for up to 440% faster inference.
Видео Real-Time Panoptic Segmentation From Dense Detections канала ComputerVisionFoundation Videos
Видео Real-Time Panoptic Segmentation From Dense Detections канала ComputerVisionFoundation Videos
Показать
Комментарии отсутствуют
Информация о видео
17 июля 2020 г. 13:20:08
00:04:49
Другие видео канала
![Disp R-CNN: Stereo 3D Object Detection via Shape Prior Guided Instance Disparity Estimation](https://i.ytimg.com/vi/KnslISMQBlQ/default.jpg)
![High-Resolution Radar Dataset for Semi-Supervised Learning of Dynamic Objects](https://i.ytimg.com/vi/bixc-lUuZkw/default.jpg)
![Learning to Dress 3D People in Generative Clothing](https://i.ytimg.com/vi/NOEA-Rtq6vM/default.jpg)
![Learning Physics-Guided Face Relighting Under Directional Light](https://i.ytimg.com/vi/cYwsaUQFMU8/default.jpg)
![Orthogonal Convolutional Neural Networks](https://i.ytimg.com/vi/xq4udlgu6Z4/default.jpg)
![232 - Improving Video Captioning with Temporal Composition of a Visual-Syntactic Embedding](https://i.ytimg.com/vi/dW9FQnwrg_0/default.jpg)
![Match or No Match: Keypoint Filtering Based on Matching Probability](https://i.ytimg.com/vi/4jV3S04ejFc/default.jpg)
![DeepLPF: Deep Local Parametric Filters for Image Enhancement](https://i.ytimg.com/vi/Sxach3FM6FY/default.jpg)
![324 - Weakly Supervised Deep Reinforcement Learning for Video Summarization With Semantically Meani](https://i.ytimg.com/vi/gaq868XeWn8/default.jpg)
![Neural Architecture Search for Lightweight Non-Local Networks](https://i.ytimg.com/vi/2IUJqV7D4i0/default.jpg)
![Inverse Rendering for Complex Indoor Scenes: Shape, Spatially-Varying Lighting and SVBRDF From a...](https://i.ytimg.com/vi/RvWlDWtTozw/default.jpg)
![High-Frequency Component Helps Explain the Generalization of Convolutional Neural Networks](https://i.ytimg.com/vi/8H0QQbMFb-k/default.jpg)
![1257 - Multimodal Prototypical Networks for Few-shot Learning](https://i.ytimg.com/vi/nq2yYbGIRwc/default.jpg)
![1369 - CenterFusion:Center-based Radar and Camera Fusionfor 3D Object Detection](https://i.ytimg.com/vi/tr5jyfO55U8/default.jpg)
![515 - Cinematic-L1 Video Stabilization with a Log-Homography Model](https://i.ytimg.com/vi/IPchmdyc6wg/default.jpg)
![71 - DeepCSR: A 3D Deep Learning Approach For Cortical Surface Reconstruction](https://i.ytimg.com/vi/06dCg-PkL2w/default.jpg)
![Through the Looking Glass: Neural 3D Reconstruction of Transparent Shapes](https://i.ytimg.com/vi/zVu1v4rasAE/default.jpg)
![Rethinking Zero-Shot Video Classification: End-to-End Training for Realistic Applications](https://i.ytimg.com/vi/F5AB06sCJ90/default.jpg)
![12-in-1: Multi-Task Vision and Language Representation Learning](https://i.ytimg.com/vi/dPPpA5vBQc0/default.jpg)
![End-to-End Camera Calibration for Broadcast Videos](https://i.ytimg.com/vi/6GFegy63l-g/default.jpg)
![653 - Misclassification Risk and Uncertainty Quantification in Deep Classifiers](https://i.ytimg.com/vi/NgpXuwId2Pk/default.jpg)