Ashish Patel 🇮🇳’s Post

𝗗𝗮𝘆-𝟮𝟲𝟲 𝗖𝗼𝗺𝗽𝘂𝘁𝗲𝗿 𝗩𝗶𝘀𝗶𝗼𝗻 𝗟𝗲𝗮𝗿𝗻𝗶𝗻𝗴 𝗥𝗲𝘁𝗵𝗶𝗻𝗸𝗶𝗻𝗴 𝗟𝗲𝗮𝗿𝗻𝗮𝗯𝗹𝗲 𝗧𝗿𝗲𝗲 𝗙𝗶𝗹𝘁𝗲𝗿 𝗳𝗼𝗿 𝗚𝗲𝗻𝗲𝗿𝗶𝗰 𝗙𝗲𝗮𝘁𝘂𝗿𝗲 𝗧𝗿𝗮𝗻𝘀𝗳𝗼𝗿𝗺 by MEGVII旷视 Inc. Follow me for a similar post: 🇮🇳 Ashish Patel Interesting Facts : 🔸 This paper is published NeuroIPS2020 with 3 citations. ------------------------------------------------------------------- 𝗔𝗺𝗮𝘇𝗶𝗻𝗴 𝗥𝗲𝘀𝗲𝗮𝗿𝗰𝗵 : https://lnkd.in/eAcWiG9B Code : https://lnkd.in/d5Bki3Eu ------------------------------------------------------------------- 𝗜𝗠𝗣𝗢𝗥𝗧𝗔𝗡𝗖𝗘 🔸 The Learnable Tree Filter presents a remarkable approach to model structure-preserving relations for semantic segmentation. Nevertheless, the intrinsic geometric constraint forces it to focus on the regions with close spatial distance, hindering the effective long-range interactions.  🔸 To relax the geometric constraint, we give the analysis by reformulating it as a Markov Random Field and introduce a learnable unary term. Besides, we propose a learnable spanning tree algorithm to replace the original non-differentiable one, which further improves the flexibility and robustness.  🔸 With the above improvements, our method can better capture long-range dependencies and preserve structural details with linear complexity, which is extended to several vision tasks for more generic feature transform. Extensive experiments on object detection/instance segmentation demonstrate the consistent improvements over the original version.  🔸 For semantic segmentation, we achieve leading performance (82.1% mIoU) on the Cityscapes benchmark without bells-and-whistles. #computervision #artificialintelligence #machinelearning