Day-50 #ComputerVision Learning Hide-and-Seek (Weakly Supervised Object Localization & Action Localization) by University of California Follow me for similar post : 🇮🇳 Ashish Patel Interesting Facts : 🔸 It is published in 2017 #ICCV, which has already got over 233 citations. 🔸 Outperforms Backprop & CAM for WSOL. C3D Features Used with Hide-and-Seek for Weakly Supervised Action Localization ------------------------------------------------------------------- 𝗔𝗺𝗮𝘇𝗶𝗻𝗴 𝗥𝗲𝘀𝗲𝗮𝗿𝗰𝗵 : https://lnkd.in/eDu25cw official Code : https://bit.ly/3sck9nQ pytorch: https://bit.ly/37wx5x0 ------------------------------------------------------------------- 𝗜𝗠𝗣𝗢𝗥𝗧𝗔𝗡𝗖𝗘 🔸 Weakly-Supervised Object Localization (WSOL) is to localize the object while there is no object bounding box label but only the image-level label. 🔸 The main idea is to hide patches in a training image randomly, forcing the network to seek other relevant parts when the most discriminative part is hidden. 🔸 Thus, only input image needs to be modified during training. #computervision #artificialintelligence #analytics
For previous post visit this github : https://github.com/ashishpatel26/365-Days-Computer-Vision-Learning-Linkedin-Post
Thank you for sharing