CornerNet: Detecting Objects as Paired Keypoints (Paper Explained)
Many object detectors focus on locating the center of the object they want to find. However, this leaves them with the secondary problem of determining the specifications of the bounding box, leading to undesirable solutions like anchor boxes. This paper directly detects the top left and the bottom right corners of objects independently, along with descriptors that allows to match the two later and form a complete bounding box. For this, a new pooling method, called corner pooling, is introduced.
OUTLINE:
0:00 - Intro & High-Level Overview
1:40 - Object Detection
2:40 - Pipeline I - Hourglass
4:00 - Heatmap & Embedding Outputs
8:40 - Heatmap Loss
10:55 - Embedding Loss
14:35 - Corner Pooling
20:40 - Experiments
Paper: https://arxiv.org/abs/1808.01244
Code: https://github.com/princeton-vl/CornerNet
Abstract:
We propose CornerNet, a new approach to object detection where we detect an object bounding box as a pair of keypoints, the top-left corner and the bottom-right corner, using a single convolution neural network. By detecting objects as paired keypoints, we eliminate the need for designing a set of anchor boxes commonly used in prior single-stage detectors. In addition to our novel formulation, we introduce corner pooling, a new type of pooling layer that helps the network better localize corners. Experiments show that CornerNet achieves a 42.2% AP on MS COCO, outperforming all existing one-stage detectors.
Authors: Hei Law, Jia Deng
Links:
YouTube: https://www.youtube.com/c/yannickilcher
Twitter: https://twitter.com/ykilcher
BitChute: https://www.bitchute.com/channel/yannic-kilcher
Minds: https://www.minds.com/ykilcher
Видео CornerNet: Detecting Objects as Paired Keypoints (Paper Explained) канала Yannic Kilcher
OUTLINE:
0:00 - Intro & High-Level Overview
1:40 - Object Detection
2:40 - Pipeline I - Hourglass
4:00 - Heatmap & Embedding Outputs
8:40 - Heatmap Loss
10:55 - Embedding Loss
14:35 - Corner Pooling
20:40 - Experiments
Paper: https://arxiv.org/abs/1808.01244
Code: https://github.com/princeton-vl/CornerNet
Abstract:
We propose CornerNet, a new approach to object detection where we detect an object bounding box as a pair of keypoints, the top-left corner and the bottom-right corner, using a single convolution neural network. By detecting objects as paired keypoints, we eliminate the need for designing a set of anchor boxes commonly used in prior single-stage detectors. In addition to our novel formulation, we introduce corner pooling, a new type of pooling layer that helps the network better localize corners. Experiments show that CornerNet achieves a 42.2% AP on MS COCO, outperforming all existing one-stage detectors.
Authors: Hei Law, Jia Deng
Links:
YouTube: https://www.youtube.com/c/yannickilcher
Twitter: https://twitter.com/ykilcher
BitChute: https://www.bitchute.com/channel/yannic-kilcher
Minds: https://www.minds.com/ykilcher
Видео CornerNet: Detecting Objects as Paired Keypoints (Paper Explained) канала Yannic Kilcher
Показать
Комментарии отсутствуют
Информация о видео
Другие видео канала
DETR: End-to-End Object Detection with Transformers (Paper Explained)The AI Economist: Improving Equality and Productivity with AI-Driven Tax Policies (Paper Explained)CornerNet: Detecting Objects as Paired KeypointsDeep image reconstruction from human brain activity (Paper Explained)Philipp Krähenbühl - Point-based object detectionJEPA - A Path Towards Autonomous Machine Intelligence (Paper Explained)Why AI is Harder Than We Think (Machine Learning Research Paper Explained)[ML News] Text-to-Image models are taking over! (Imagen, DALL-E 2, Midjourney, CogView 2 & more)Attention Is All You NeedFocal Loss for Dense Object DetectionVideo PreTraining (VPT): Learning to Act by Watching Unlabeled Online Videos (Paper Explained)R-CNN, Fast R-CNN and Faster R-CNN explainedUnderstanding Focal LossThis A.I. creates infinite NFTs2017 RetinaNet paper summaryLongformer: The Long-Document TransformerLanguage Models are Open Knowledge Graphs (Paper Explained)OpenAI CLIP: ConnectingText and Images (Paper Explained)Detectron2 - Next Gen Object Detection Library - Yuxin Wu