DeepAI AI Chat
Log In Sign Up

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

by   Yuxi Li, et al.

Object detection has made great progress in the past few years along with the development of deep learning. However, most current object detection methods are resource hungry, which hinders their wide deployment to many resource restricted usages such as usages on always-on devices, battery-powered low-end devices, etc. This paper considers the resource and accuracy trade-off for resource-restricted usages during designing the whole object detection framework. Based on the deeply supervised object detection (DSOD) framework, we propose Tiny-DSOD dedicating to resource-restricted usages. Tiny-DSOD introduces two innovative and ultra-efficient architecture blocks: depthwise dense block (DDB) based backbone and depthwise feature-pyramid-network (D-FPN) based front-end. We conduct extensive experiments on three famous benchmarks (PASCAL VOC 2007, KITTI, and COCO), and compare Tiny-DSOD to the state-of-the-art ultra-efficient object detection solutions such as Tiny-YOLO, MobileNet-SSD (v1 & v2), SqueezeDet, Pelee, etc. Results show that Tiny-DSOD outperforms these solutions in all the three metrics (parameter-size, FLOPs, accuracy) in each comparison. For instance, Tiny-DSOD achieves 72.1 only 0.95M parameters and 1.06B FLOPs, which is by far the state-of-the-arts result with such a low resource requirement.


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

Object detection often costs a considerable amount of computation to get...

Light-Weight RetinaNet for Object Detection

Object detection has gained great progress driven by the development of ...

Single-Training Collaborative Object Detectors Adaptive to Bandwidth and Computation

In the past few years, mobile deep-learning deployment progressed by lea...

AdaCon: Adaptive Context-Aware Object Detection for Resource-Constrained Embedded Devices

Convolutional Neural Networks achieve state-of-the-art accuracy in objec...

GiraffeDet: A Heavy-Neck Paradigm for Object Detection

In conventional object detection frameworks, a backbone body inherited f...

Towards Precise Weakly Supervised Object Detection via Interactive Contrastive Learning of Context Information

Weakly supervised object detection (WSOD) aims at learning precise objec...

Efficient Scale-Permuted Backbone with Learned Resource Distribution

Recently, SpineNet has demonstrated promising results on object detectio...