Compact Sparse R-CNN: Speeding up sparse R-CNN by reducing iterative detection heads and simplifying feature pyramid network
Processing a large number of proposals usually takes a significant proportion of inference time in two-stage object detection methods. Sparse regions with CNN features (Sparse R-CNN) was proposed using a small number of learnable proposals to replace the proposals derived from anchors. To decrease t...
Main Authors: | Zihang He, Xiang Ye, Yong Li |
---|---|
Format: | Article |
Language: | English |
Published: |
AIP Publishing LLC
2023-05-01
|
Series: | AIP Advances |
Online Access: | http://dx.doi.org/10.1063/5.0146453 |
Similar Items
-
Optimization of Microarchitecture and Dataflow for Sparse Tensor CNN Acceleration
by: Ngoc-Son Pham, et al.
Published: (2023-01-01) -
Deep CNN sparse coding analysis: Towards average case
by: Murray, M, et al.
Published: (2018) -
SparseM: A Sparse Matrix Package for R *
by: Roger Koenker, et al.
Published: (2003-02-01) -
Deep CNN Sparse Coding for Real Time Inhaler Sounds Classification
by: Vaggelis Ntalianis, et al.
Published: (2020-04-01) -
Optimization of Scatter Network Architectures and Bank Allocations for Sparse CNN Accelerators
by: Sunwoo Kim, et al.
Published: (2022-01-01)