PR-217: EfficientDet: Scalable and Efficient Object Detection
TensorFlow Korea 논문읽기모임 PR12 217번째 논문 review입니다
이번 논문은 GoogleBrain에서 쓴 EfficientDet입니다. EfficientNet의 후속작으로 accuracy와 efficiency를 둘 다 잡기 위한 object detection 방법을 제안한 논문입니다. 이를 위하여 weighted bidirectional feature pyramid network(BiFPN)과 EfficientNet과 유사한 방법의 detection용 compound scaling 방법을 제안하고 있는데요, 자세한 내용은 영상을 참고해주세요
논문링크: https://arxiv.org/abs/1911.09070
발표자료: https://www.slideshare.net/JinwonLee9/pr217-efficientdet-scalable-and-efficient-object-detection
Видео PR-217: EfficientDet: Scalable and Efficient Object Detection канала JinWon Lee
이번 논문은 GoogleBrain에서 쓴 EfficientDet입니다. EfficientNet의 후속작으로 accuracy와 efficiency를 둘 다 잡기 위한 object detection 방법을 제안한 논문입니다. 이를 위하여 weighted bidirectional feature pyramid network(BiFPN)과 EfficientNet과 유사한 방법의 detection용 compound scaling 방법을 제안하고 있는데요, 자세한 내용은 영상을 참고해주세요
논문링크: https://arxiv.org/abs/1911.09070
발표자료: https://www.slideshare.net/JinwonLee9/pr217-efficientdet-scalable-and-efficient-object-detection
Видео PR-217: EfficientDet: Scalable and Efficient Object Detection канала JinWon Lee
Показать
Комментарии отсутствуют
Информация о видео
Другие видео канала
PR-366: A ConvNet for the 2020s
PR-095: Modularity Matters: Learning Invariant Relational Reasoning Tasks
PR-406: Large Models are Parsimonious Learners: Activation Sparsity in Trained Transformers
PR-377: Scaling Up Your Kernels to 31x31: Revisiting Large Kernel Design in CNNs
PR-197: One ticket to win them all: generalizing lottery ticket initialization
PR-144: SqueezeNext: Hardware-Aware Neural Network Design
PR-085: In-Datacenter Performance Analysis of a Tensor Processing Unit
PR-304: Pretrained Transformers As Universal Computation Engines
PR-330: How To Train Your ViT? Data, Augmentation, and Regularization in Vision Transformers
PR-243: Designing Network Design Spaces
PR-317: MLP-Mixer: An all-MLP Architecture for Vision
PR-297: Training Data-efficient Image Transformers & Distillation through Attention (DeiT)
PR-231: A Simple Framework for Contrastive Learning of Visual Representations
PR-207: YOLOv3: An Incremental Improvement
PR-344: A Battle of Network Structures: An Empirical Study of CNN, Transformer, and MLP
PR-155: Exploring Randomly Wired Neural Networks for Image Recognition
PR-183: MixNet: Mixed Depthwise Convolutional Kernels
PR-284: End-to-End Object Detection with Transformers(DETR)
PR-270: PP-YOLO: An Effective and Efficient Implementation of Object Detector
PR-044: MobileNet
PR-355: Masked Autoencoders Are Scalable Vision Learners