Ashish Patel 🇮🇳’s Post

𝗗𝗮𝘆-𝟮𝟱𝟴 𝗖𝗼𝗺𝗽𝘂𝘁𝗲𝗿 𝗩𝗶𝘀𝗶𝗼𝗻 𝗟𝗲𝗮𝗿𝗻𝗶𝗻𝗴 𝗢𝗦𝟮𝗗:One-Stage One-Shot Object Detection by Matching Anchor Features by Yandex, Moscow, Russia Follow me for a similar post: 🇮🇳 Ashish Patel Interesting Facts : 🔸 This paper is published ECCV2020. ------------------------------------------------------------------- 𝗔𝗺𝗮𝘇𝗶𝗻𝗴 𝗥𝗲𝘀𝗲𝗮𝗿𝗰𝗵 : https://lnkd.in/eKnFcMJM Code: https://lnkd.in/eKD6--td ------------------------------------------------------------------- 𝗜𝗠𝗣𝗢𝗥𝗧𝗔𝗡𝗖𝗘 🔸 In this paper, we consider the task of one-shot object detection, which consists in detecting objects defined by a single demonstration. Differently from the standard object detection, the classes of objects used for training and testing do not overlap. We build a one-stage system that performs localization and recognition jointly.  🔸 We use dense correlation matching of learned local features to find correspondences, a feed-forward geometric transformation model to align features and bilinear resampling of the correlation tensor to compute the detection score of the aligned features.  🔸 All the components are differentiable, which allows end-to-end training. Experimental evaluation on several challenging domains (retail products, 3D objects, buildings and logos) shows that our method can detect unseen classes (e.g., the toothpaste when trained on groceries) and outperforms several baselines by a significant margin.  #computervision #artificialintelligence #machinelearning