Ashish Patel 🇮🇳’s Post

𝗗𝗮𝘆-𝟮𝟬𝟵 𝗖𝗼𝗺𝗽𝘂𝘁𝗲𝗿 𝗩𝗶𝘀𝗶𝗼𝗻 𝗟𝗲𝗮𝗿𝗻𝗶𝗻𝗴 𝗣𝗮𝗻𝗼𝗽𝘁𝗶𝗰 𝗦𝗲𝗴𝗺𝗲𝗻𝘁𝗮𝘁𝗶𝗼𝗻 by Facebook AI Research (FAIR), Heidelberg University, Germany Follow me for a similar post:  🇮🇳 Ashish Patel Interesting Facts : 🔸 This is a paper in CVPR 2019 with over 427 citations. ------------------------------------------------------------------- 𝗔𝗺𝗮𝘇𝗶𝗻𝗴 𝗥𝗲𝘀𝗲𝗮𝗿𝗰𝗵 : https://lnkd.in/esqh7U9 Code : https://lnkd.in/eZW2_3w ------------------------------------------------------------------- 𝗜𝗠𝗣𝗢𝗥𝗧𝗔𝗡𝗖𝗘 🔸 We propose and study a novel ‘Panoptic Segmentation’ (PS) task. Panoptic segmentation unifies the traditionally distinct tasks of instance segmentation (detect and segment each object instance) and semantic segmentation (assign a class label to each pixel).  🔸 The unification is natural and presents novel algorithmic challenges not present in either instance or semantic segmentation when studied in isolation. To measure performance on the task, we introduce a panoptic quality (PQ) measure and show that it is simple and interpretable.  🔸 Using PQ, we study human performance on three existing datasets that have the necessary annotations for PS, which helps us better understand the task and metric. We also propose a basic algorithmic approach to combine instance and semantic segmentation outputs into panoptic outputs and compare this to human performance. 🔸Consequently, our model is able to learn from the old pseudo labels at the early stage, and gradually switch to the new pseudo labels to prevent overfitting in the later stage. We evaluate our approach on the TigDog and VisDA 2019 datasets, where we outperform existing approaches by a large margin.  🔸 PS can serve as the foundation of future challenges in segmentation and visual recognition. Our goal is to drive research in novel directions by inviting the community to explore the proposed panoptic segmentation task. #computervision #artificialintelligence #deeplearning