Ashish Patel 🇮🇳’s Post

Day-54 Computer Vision Learning ADL: Attention-based Dropout Layer (Weakly Supervised Object Localization) by Yonsei University Follow me for similar post : 🇮🇳 Ashish Patel Interesting Facts : 🔸 It is published in 2019 CVPR, which has already got over 76 citations. 🔸 Outperforms SPG, ACoL, Hide-and-Seek & CAM ------------------------------------------------------------------- 𝗔𝗺𝗮𝘇𝗶𝗻𝗴 𝗥𝗲𝘀𝗲𝗮𝗿𝗰𝗵 : https://lnkd.in/etmiACh official Code : https://bit.ly/3aLg44f ------------------------------------------------------------------- 𝗜𝗠𝗣𝗢𝗥𝗧𝗔𝗡𝗖𝗘 🔸 Weakly Supervised Object Localization (WSOL) is to have object localization while without object bounding box labels, but with only image-level label, for training. 🔸 Attention-based Dropout Layer (ADL) is used to hide the most discriminative part from the model for capturing the integral extent of object, and highlight the informative region for improving the recognition power of the model. #computervision #artificialintelligence #technology

  • No alternative text description for this image

To view or add a comment, sign in

Explore content categories