Ashish Patel 🇮🇳’s Post

𝗗𝗮𝘆-𝟭𝟳𝟵 Computer Vision Learning 𝗜𝗻𝘀𝘁𝗮𝗻𝘁-𝗧𝗲𝗮𝗰𝗵𝗶𝗻𝗴: An End-to-End Semi-Supervised Object Detection Framework by 𝗔𝗹𝗶𝗯𝗮𝗯𝗮 𝗚𝗿𝗼𝘂𝗽 Follow me for a similar post:  🇮🇳 Ashish Patel Interesting Facts : 🔸 This is a paper in CVPR 2021 with over 1 citation. 🔸 It outperforms the supervised approach. ------------------------------------------------------------------- 𝗔𝗺𝗮𝘇𝗶𝗻𝗴 𝗥𝗲𝘀𝗲𝗮𝗿𝗰𝗵 : https://lnkd.in/eBHrqVs ------------------------------------------------------------------- 𝗜𝗠𝗣𝗢𝗥𝗧𝗔𝗡𝗖𝗘 🔸 Supervised learning-based object detection frameworks demand plenty of laborious manual annotations, which may not be practical in real applications. Semi-supervised object detection (SSOD) can effectively leverage unlabeled data to improve the model performance, which is of great significance for the application of object detection models. 🔸 Instant-Teaching, a complete end-to-end and effective SSOD framework, which uses instant pseudo labeling with extended weak-strong data augmentations for teaching during each training iteration. 🔸 To alleviate the confirmation bias problem and improve the quality of pseudo annotations, further proposes a co-rectify scheme based on Instant-Teaching, denoted as Instant-Teaching. Extensive experiments on both MS-COCO and PASCAL VOC datasets substantiate the superiority of our framework.  🔸 Specifically, this method surpasses state-of-the-art methods by 4.2 mAP on MS-COCO when using 2% labeled data. Even with full supervised information of MS-COCO, the proposed method still outperforms state-of-the-art methods by about 1.0 mAP. On PASCAL VOC, It achieved more than 5 mAP improvements by applying VOC07 as labeled data and VOC12 as unlabeled data. #computervision #artificialintelligence #data