Backbone
البنية الأساسية
الشبكة الالتفافية العميقة (مثل ResNet أو VGG) التي تستخلص خرائط السمات من الصورة الخام. تُشكّل المرحلة الأولى في خطوط أنابيب الرصد والتجزئة، وتُشارَك سماتها بين المهام المختلفة.
The deep convolutional network (e.g. ResNet or VGG) that extracts feature maps from the raw image. It forms the first stage of detection and segmentation pipelines, and its features are shared across different task heads.
Also translated asالعمود الفقري للشبكة، الشبكة الأساسية المستخلصة للسمات
First appears in this corpus in: Very Deep Convolutional Networks for Large-Scale Image Recognition (2014)
Appears in these papers
- ALIGN: Scaling Up Visual and Vision-Language Representation Learning with Noisy Text Supervision2021in the sky ✦
- Learning Fine-Grained Bimanual Manipulation with Low-Cost Hardware2023in the sky ✦
- Barlow Twins: Self-Supervised Learning via Redundancy Reduction2021in the sky ✦
- Barlow Twins: Self-Supervised Learning via Redundancy Reduction2021in the sky ✦
- BEiT: BERT Pre-Training of Image Transformers2021in the sky ✦
- Bootstrap Your Own Latent: A New Approach to Self-Supervised Learning2020in the sky ✦
- A ConvNet for the 2020s2022in the sky ✦
- A ConvNet for the 2020s2022in the sky ✦
- DeepLab: Semantic Image Segmentation with Deep Convolutional Nets, Atrous Convolution, and Fully Connected CRFs2017in the sky ✦
- Depth Anything: Unleashing the Power of Large-Scale Unlabeled Data2024in the sky ✦
- Depth Anything: Unleashing the Power of Large-Scale Unlabeled Data2024in the sky ✦
- End-to-End Object Detection with Transformers2020in the sky ✦
- Diffusion Policy: Visuomotor Policy Learning via Action Diffusion2023in the sky ✦
- Emerging Properties in Self-Supervised Vision Transformers2021in the sky ✦
- Emerging Properties in Self-Supervised Vision Transformers2021in the sky ✦
- DINOv2: Learning Robust Visual Features Without Supervision2023in the sky ✦
- DINOv2: Learning Robust Visual Features Without Supervision2023in the sky ✦
- Fast R-CNN2015in the sky ✦
- Faster R-CNN: Towards Real-Time Object Detection with Region Proposal Networks2015in the sky ✦
- Fully Convolutional Networks for Semantic Segmentation2015in the sky ✦
- Feature Pyramid Networks for Object Detection2017in the sky ✦
- Feature Pyramid Networks for Object Detection2017in the sky ✦
- Grounding DINO: Marrying DINO with Grounded Pre-Training for Open-Set Object Detection2023in the sky ✦
- Grounding DINO: Marrying DINO with Grounded Pre-Training for Open-Set Object Detection2023in the sky ✦
- Mask R-CNN2017in the sky ✦
- Open X-Embodiment: Robotic Learning Datasets and RT-X Models2024in the sky ✦
- Focal Loss for Dense Object Detection2017in the sky ✦
- Unsupervised Representation Learning by Predicting Image Rotations2018in the sky ✦
- Unsupervised Representation Learning by Predicting Image Rotations2018in the sky ✦
- RT-1: Robotics Transformer for Real-World Control at Scale2022in the sky ✦
- RT-1: Robotics Transformer for Real-World Control at Scale2022in the sky ✦
- SegFormer: Simple and Efficient Design for Semantic Segmentation with Transformers2021in the sky ✦
- Exploring Simple Siamese Representation Learning2021in the sky ✦
- Exploring Simple Siamese Representation Learning2021in the sky ✦
- SSD: Single Shot MultiBox Detector2016in the sky ✦
- SwAV: Unsupervised Learning of Visual Features by Contrasting Cluster Assignments2020in the sky ✦
- Swin Transformer: Hierarchical Vision Transformer Using Shifted Windows2021in the sky ✦
- Swin Transformer: Hierarchical Vision Transformer Using Shifted Windows2021in the sky ✦
- Universal Language Model Fine-Tuning for Text Classification2018in the sky ✦
- Very Deep Convolutional Networks for Large-Scale Image Recognition2014in the sky ✦
- VICReg: Variance-Invariance-Covariance Regularization for Self-Supervised Learning2021in the sky ✦
- YOLOv3: An Incremental Improvement2018in the sky ✦