Description
One-Shot Aggregation is an image model block that is an alternative to Dense Blocks, by aggregating intermediate features. It is proposed as part of the VoVNet architecture. Each convolution layer is connected by two-way connection. One way is connected to the subsequent layer to produce the feature with a larger receptive field while the other way is aggregated only once into the final output feature map. The difference with DenseNet is that the output of each layer is not routed to all subsequent intermediate layers which makes the input size of intermediate layers constant.
Papers Using This Method
A new method for optical steel rope non-destructive damage detection2024-02-06FedLPA: One-shot Federated Learning with Layer-Wise Posterior Aggregation2023-09-30RCS-YOLO: A Fast and High-Accuracy Object Detector for Brain Tumor Detection2023-07-31A Self-Supervised Miniature One-Shot Texture Segmentation (MOSTS) Model for Real-Time Robot Navigation and Embedded Applications2023-06-15BEVFormer v2: Adapting Modern Image Backbones to Bird's-Eye-View Recognition via Perspective Supervision2022-11-18Intelligent detect for substation insulator defects based on CenterMask2022-08-31TreeNet: A lightweight One-Shot Aggregation Convolutional Network2021-09-25Diverse Temporal Aggregation and Depthwise Spatiotemporal Factorization for Efficient Video Classification2020-12-01ACFD: Asymmetric Cartoon Face Detector2020-07-02CenterMask : Real-Time Anchor-Free Instance Segmentation2019-11-15An Energy and GPU-Computation Efficient Backbone Network for Real-Time Object Detection2019-04-22