RMOPP: Robust Multi-Objective Post-Processing for Effective Object Detection

• URL: http://arxiv.org/abs/2102.04582v1
• Date: Tue, 9 Feb 2021 00:02:38 GMT
• Title: RMOPP: Robust Multi-Objective Post-Processing for Effective Object Detection
• Authors: Mayuresh Savargaonkar, Abdallah Chehade and Samir Rawashdeh
• Abstract summary: RMOPP is a statistically driven, post-processing algorithm that allows for simultaneous optimization of precision and recall. We provide a compelling test case on YOLOv2 using the MS-COCO dataset.
• Score: 0.0
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: Over the last few decades, many architectures have been developed that harness the power of neural networks to detect objects in near real-time. Training such systems requires substantial time across multiple GPUs and massive labeled training datasets. Although the goal of these systems is generalizability, they are often impractical in real-life applications due to flexibility, robustness, or speed issues. This paper proposes RMOPP: A robust multi-objective post-processing algorithm to boost the performance of fast pre-trained object detectors with a negligible impact on their speed. Specifically, RMOPP is a statistically driven, post-processing algorithm that allows for simultaneous optimization of precision and recall. A unique feature of RMOPP is the Pareto frontier that identifies dominant possible post-processed detectors to optimize for both precision and recall. RMOPP explores the full potential of a pre-trained object detector and is deployable for near real-time predictions. We also provide a compelling test case on YOLOv2 using the MS-COCO dataset.

Related papers

• High-Speed Detector For Low-Powered Devices In Aerial Grasping [16.940649285960028]
  Fast Fruit Detector (FFD) is a resource-efficient, single-stage, and postprocessing-free object detector. FFD achieves 100FPS@FP32 precision on the latest 10W NVIDIA Jetson-NX embedded device.
  arXiv  Detail & Related papers  (2024-02-22T14:44:50Z)
• TimePillars: Temporally-Recurrent 3D LiDAR Object Detection [8.955064958311517]
  TimePillars is a temporally-recurrent object detection pipeline. It exploits the pillar representation of LiDAR data across time. We show how basic building blocks are enough to achieve robust and efficient results.
  arXiv  Detail & Related papers  (2023-12-22T10:25:27Z)
• SpikeMOT: Event-based Multi-Object Tracking with Sparse Motion Features [52.213656737672935]
  SpikeMOT is an event-based multi-object tracker. SpikeMOT uses spiking neural networks to extract sparsetemporal features from event streams associated with objects.
  arXiv  Detail & Related papers  (2023-09-29T05:13:43Z)
• Let's Roll: Synthetic Dataset Analysis for Pedestrian Detection Across Different Shutter Types [7.0441427250832644]
  This paper studies the impact of different shutter mechanisms on machine learning (ML) object detection models on a synthetic dataset. In particular, we train and evaluate mainstream detection models with our synthetically-generated paired GS and RS datasets.
  arXiv  Detail & Related papers  (2023-09-15T04:07:42Z)
• 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)
• Lightweight Jet Reconstruction and Identification as an Object Detection Task [5.071565475111431]
  We apply convolutional techniques to end-to-end jet identification and reconstruction tasks encountered at the CERN Large Hadron Collider. PFJet-SSD performs simultaneous localization, classification and regression tasks to cluster jets and reconstruct their features. We show that the ternary network closely matches the performance of its full-precision equivalent and outperforms the state-of-the-art rule-based algorithm.
  arXiv  Detail & Related papers  (2022-02-09T15:01:53Z)
• Real-Time GPU-Accelerated Machine Learning Based Multiuser Detection for 5G and Beyond [70.81551587109833]
  nonlinear beamforming filters can significantly outperform linear approaches in stationary scenarios with massive connectivity. One of the main challenges comes from the real-time implementation of these algorithms. This paper explores the acceleration of APSM-based algorithms through massive parallelization.
  arXiv  Detail & Related papers  (2022-01-13T15:20:45Z)
• Adaptive Anomaly Detection for Internet of Things in Hierarchical Edge Computing: A Contextual-Bandit Approach [81.5261621619557]
  We propose an adaptive anomaly detection scheme with hierarchical edge computing (HEC) We first construct multiple anomaly detection DNN models with increasing complexity, and associate each of them to a corresponding HEC layer. Then, we design an adaptive model selection scheme that is formulated as a contextual-bandit problem and solved by using a reinforcement learning policy network.
  arXiv  Detail & Related papers  (2021-08-09T08:45:47Z)
• Deep Cellular Recurrent Network for Efficient Analysis of Time-Series Data with Spatial Information [52.635997570873194]
  This work proposes a novel deep cellular recurrent neural network (DCRNN) architecture to process complex multi-dimensional time series data with spatial information. The proposed architecture achieves state-of-the-art performance while utilizing substantially less trainable parameters when compared to comparable methods in the literature.
  arXiv  Detail & Related papers  (2021-01-12T20:08:18Z)
• End-to-End Object Detection with Fully Convolutional Network [71.56728221604158]
  We introduce a Prediction-aware One-To-One (POTO) label assignment for classification to enable end-to-end detection. A simple 3D Max Filtering (3DMF) is proposed to utilize the multi-scale features and improve the discriminability of convolutions in the local region. Our end-to-end framework achieves competitive performance against many state-of-the-art detectors with NMS on COCO and CrowdHuman datasets.
  arXiv  Detail & Related papers  (2020-12-07T09:14:55Z)
• Fast Region Proposal Learning for Object Detection for Robotics [21.48920421574167]
  We propose an architecture that leverages on the powerful representation of deep learning descriptors, while permitting fast adaptation time. In this paper, we demonstrate that a further boost in accuracy can be obtained by adapting, in addition to the regions candidate generation on the task at hand.
  arXiv  Detail & Related papers  (2020-11-25T14:51:49Z)

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.