DPNET: Dual-Path Network for Efficient Object Detectioj with Lightweight Self-Attention

10/31/2021
by   Huimin Shi, et al.
0

Object detection often costs a considerable amount of computation to get satisfied performance, which is unfriendly to be deployed in edge devices. To address the trade-off between computational cost and detection accuracy, this paper presents a dual path network, named DPNet, for efficient object detection with lightweight self-attention. In backbone, a single input/output lightweight self-attention module (LSAM) is designed to encode global interactions between different positions. LSAM is also extended into a multiple-inputs version in feature pyramid network (FPN), which is employed to capture cross-resolution dependencies in two paths. Extensive experiments on the COCO dataset demonstrate that our method achieves state-of-the-art detection results. More specifically, DPNet obtains 29.0 and 2.27M model size for a 320x320 image.

READ FULL TEXT
research
09/28/2022

DPNet: Dual-Path Network for Real-time Object Detection with Lightweight Attention

The recent advances of compressing high-accuracy convolution neural netw...
research
07/29/2018

Tiny-DSOD: Lightweight Object Detection for Resource-Restricted Usages

Object detection has made great progress in the past few years along wit...
research
12/10/2022

CamoFormer: Masked Separable Attention for Camouflaged Object Detection

How to identify and segment camouflaged objects from the background is c...
research
06/24/2022

Excavating RoI Attention for Underwater Object Detection

Self-attention is one of the most successful designs in deep learning, w...
research
12/04/2018

Factorized Attention: Self-Attention with Linear Complexities

Recent works have been applying self-attention to various fields in comp...
research
10/31/2021

DRBANET: A Lightweight Dual-Resolution Network for Semantic Segmentation with Boundary Auxiliary

Due to the powerful ability to encode image details and semantics, many ...
research
11/04/2020

Covariance Self-Attention Dual Path UNet for Rectal Tumor Segmentation

Deep learning algorithms are preferable for rectal tumor segmentation. H...

Please sign up or login with your details

Forgot password? Click here to reset