DynamicDet: A Unified Dynamic Architecture for Object Detection

• URL: http://arxiv.org/abs/2304.05552v1
• Date: Wed, 12 Apr 2023 01:16:53 GMT
• Title: DynamicDet: A Unified Dynamic Architecture for Object Detection
• Authors: Zhihao Lin, Yongtao Wang, Jinhe Zhang, Xiaojie Chu
• Abstract summary: We propose a dynamic framework for object detection, named DynamicDet. We present a novel optimization strategy with an exiting criterion based on the detection losses for our dynamic detectors. Experiments conducted on the COCO benchmark demonstrate that the proposed DynamicDet achieves new state-of-the-art accuracy-speed trade-offs.
• Score: 9.719671347009827
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: Dynamic neural network is an emerging research topic in deep learning. With adaptive inference, dynamic models can achieve remarkable accuracy and computational efficiency. However, it is challenging to design a powerful dynamic detector, because of no suitable dynamic architecture and exiting criterion for object detection. To tackle these difficulties, we propose a dynamic framework for object detection, named DynamicDet. Firstly, we carefully design a dynamic architecture based on the nature of the object detection task. Then, we propose an adaptive router to analyze the multi-scale information and to decide the inference route automatically. We also present a novel optimization strategy with an exiting criterion based on the detection losses for our dynamic detectors. Last, we present a variable-speed inference strategy, which helps to realize a wide range of accuracy-speed trade-offs with only one dynamic detector. Extensive experiments conducted on the COCO benchmark demonstrate that the proposed DynamicDet achieves new state-of-the-art accuracy-speed trade-offs. For instance, with comparable accuracy, the inference speed of our dynamic detector Dy-YOLOv7-W6 surpasses YOLOv7-E6 by 12%, YOLOv7-D6 by 17%, and YOLOv7-E6E by 39%. The code is available at https://github.com/VDIGPKU/DynamicDet.

Related papers

• Deep Generic Dynamic Object Detection Based on Dynamic Grid Maps [39.58317527488534]
  This paper describes a method to detect generic dynamic objects for automated driving. A LiDAR-based dynamic grid is generated online to infer the presence of dynamic objects. Deep learning-based detector is trained on the dynamic grid to infer the presence of dynamic objects of any type.
  arXiv  Detail & Related papers  (2024-10-18T18:15:32Z)
• Learn to Memorize and to Forget: A Continual Learning Perspective of Dynamic SLAM [17.661231232206028]
  Simultaneous localization and mapping (SLAM) with implicit neural representations has received extensive attention. We propose a novel SLAM framework for dynamic environments.
  arXiv  Detail & Related papers  (2024-07-18T09:35:48Z)
• Neuromorphic Vision-based Motion Segmentation with Graph Transformer Neural Network [4.386534439007928]
  We propose a novel event-based motion segmentation algorithm using a Graph Transformer Neural Network, dubbed GTNN. Our proposed algorithm processes event streams as 3D graphs by a series nonlinear transformations to unveil local and global correlations between events. We show that GTNN outperforms state-of-the-art methods in the presence of dynamic background variations, motion patterns, and multiple dynamic objects with varying sizes and velocities.
  arXiv  Detail & Related papers  (2024-04-16T22:44:29Z)
• Dynamics-aware Adversarial Attack of Adaptive Neural Networks [75.50214601278455]
  We investigate the dynamics-aware adversarial attack problem of adaptive neural networks. We propose a Leaded Gradient Method (LGM) and show the significant effects of the lagged gradient. Our LGM achieves impressive adversarial attack performance compared with the dynamic-unaware attack methods.
  arXiv  Detail & Related papers  (2022-10-15T01:32:08Z)
• Using Detection, Tracking and Prediction in Visual SLAM to Achieve Real-time Semantic Mapping of Dynamic Scenarios [70.70421502784598]
  RDS-SLAM can build semantic maps at object level for dynamic scenarios in real time using only one commonly used Intel Core i7 CPU. We evaluate RDS-SLAM in TUM RGB-D dataset, and experimental results show that RDS-SLAM can run with 30.3 ms per frame in dynamic scenarios.
  arXiv  Detail & Related papers  (2022-10-10T11:03:32Z)
• Gradient-Based Trajectory Optimization With Learned Dynamics [80.41791191022139]
  We use machine learning techniques to learn a differentiable dynamics model of the system from data. We show that a neural network can model highly nonlinear behaviors accurately for large time horizons. In our hardware experiments, we demonstrate that our learned model can represent complex dynamics for both the Spot and Radio-controlled (RC) car.
  arXiv  Detail & Related papers  (2022-04-09T22:07:34Z)
• Learning to Generate Content-Aware Dynamic Detectors [62.74209921174237]
  We introduce a newpective of designing efficient detectors, which is automatically generating sample-adaptive model architecture. We introduce a course-to-fine strat-egy tailored for object detection to guide the learning of dynamic routing. Experiments on MS-COCO dataset demonstrate that CADDet achieves 1.8 higher mAP with 10% fewer FLOPs compared with vanilla routing.
  arXiv  Detail & Related papers  (2020-12-08T08:05:20Z)
• DOT: Dynamic Object Tracking for Visual SLAM [83.69544718120167]
  DOT combines instance segmentation and multi-view geometry to generate masks for dynamic objects. To determine which objects are actually moving, DOT segments first instances of potentially dynamic objects and then, with the estimated camera motion, tracks such objects by minimizing the photometric reprojection error. Our results show that our approach improves significantly the accuracy and robustness of ORB-SLAM 2, especially in highly dynamic scenes.
  arXiv  Detail & Related papers  (2020-09-30T18:36:28Z)
• A Progressive Sub-Network Searching Framework for Dynamic Inference [33.93841415140311]
  We propose a progressive sub-net searching framework, which is embedded with several effective techniques, including trainable noise ranking, channel group and fine-tuning threshold setting, sub-nets re-selection. Our proposed method achieves much better dynamic inference accuracy compared with prior popular Universally-Slimmable-Network by 4.4%-maximally and 2.3%-averagely in ImageNet dataset with the same model size.
  arXiv  Detail & Related papers  (2020-09-11T22:56:02Z)
• Dynamic R-CNN: Towards High Quality Object Detection via Dynamic Training [70.2914594796002]
  We propose Dynamic R-CNN to adjust the label assignment criteria and the shape of regression loss function. Our method improves upon ResNet-50-FPN baseline with 1.9% AP and 5.5% AP$_90$ on the MS dataset with no extra overhead.
  arXiv  Detail & Related papers  (2020-04-13T15:20:25Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.