Object Detector based on Enhanced Multi-scale Feature Fusion Pyramid Network
4
Citation
16
Reference
10
Related Paper
Citation Trend
Abstract:
Constructing the pyramidal architecture for the feature is currently a very effective way to obtain feature information of objects at different scales. Although the feature pyramid can realize the recognition and detection of multi-scale objects in the object detection task well, it still has some limitations. Since the feature information of different levels is often not from the same layer of the network, it is difficult to obtain the feature of different objects information at a certain scale from a certain level feature map of the pyramid network. To solve this problem, we present a novel object detection architecture, named Enhanced Multi-scale Feature Fusion Pyramid Network (EMFFPNet). Our network consists of Enhanced Multi-scale Feature Fusion Module (EMFFM) and Predictor Optimization Module (POM). In EMFFM, Features at different levels can be fused into the Enhanced features as outputs, which are more representative and deterministic. In order to enable the enhanced features to play their respective roles in the pyramid network, we assign different weights to fusion features of different levels in POM. We perform the experiments on the COCO detection benchmark. The experimental results indicate that the performance of our model is much better than the state-of-the-art model.Keywords:
Pyramid (geometry)
Feature (linguistics)
Benchmark (surveying)
Benchmark is a method of measuring performance, and we can obtain continuous performance improvement of programming algorithm through Benchmark validation. In order to solve large-scale linear programming problems, this paper proposes an integrated Benchmark validation which integrates theoretical Benchmark analysis with advance language-based Benchmark. Through the integrated Benchmark validation, we can continuously improve an optimizing algorithm, and validate whether the new optimizing algorithm achieves the performance objectives. The results of experiments show the proposed integrated Benchmark validation is an effective method for developing large-scale linear programming algorithms.
Benchmark (surveying)
Cite
Citations (0)
Feature-based approaches have recently become very popular in computer vision and image analysis applications, and are becoming a promising direction in shape retrieval. SHREC'11 robust feature detection and description benchmark simulates the feature detection and description stages of feature-based shape retrieval algorithms. The benchmark tests the performance of shape feature detectors and descriptors under a wide variety of transformations. The benchmark allows evaluating how algorithms cope with certain classes of transformations and strength of the transformations that can be dealt with. The present paper is a report of the SHREC'11 robust feature detection and description benchmark results.
Benchmark (surveying)
Feature (linguistics)
Cite
Citations (210)
In this paper, we raise a new issue on Unidentified Foreground Object (UFO) detection in 3D point clouds, which is a crucial technology in autonomous driving in the wild. UFO detection is challenging in that existing 3D object detectors encounter extremely hard challenges in both 3D localization and Out-of-Distribution (OOD) detection. To tackle these challenges, we suggest a new UFO detection framework including three tasks: evaluation protocol, methodology, and benchmark. The evaluation includes a new approach to measure the performance on our goal, i.e. both localization and OOD detection of UFOs. The methodology includes practical techniques to enhance the performance of our goal. The benchmark is composed of the KITTI Misc benchmark and our additional synthetic benchmark for modeling a more diverse range of UFOs. The proposed framework consistently enhances performance by a large margin across all four baseline detectors: SECOND, PointPillars, PV-RCNN, and PartA2, giving insight for future work on UFO detection in the wild.
Benchmark (surveying)
Margin (machine learning)
Cite
Citations (0)
Benchmark consumers expect benchmark suites to be complete, accurate, and consistent, and benchmark scores serve as relative measures of performance. however, it is important to understand how benchmarks stress the processors that they aim to test. this study explores the stress points of the EEMBC embedded benchmark suite using the benchmark characterization technique.
Benchmark (surveying)
Test suite
Cite
Citations (208)
The safety of building worker is important in construction industry. In order to realize the worker intelligent management, a novel building worker detection based on cross feature pyramid network is proposed to come true the real-time detection of workers. The proposed cross feature pyramid network uses cross feature of different layers to obtain robust feature of workers. The extracted feature may include high-level and low-level features. Experimental results indicate that the proposed algorithm obtain better performance than the traditional feature pyramid network.
Pyramid (geometry)
Feature (linguistics)
Cite
Citations (0)
Benchmark (surveying)
Cite
Citations (0)
In the paper we discuss the problem of evaluating disc performance with benchmarks. In particular, we concentrate on assessing benchmark properties. For this purpose we have developed benchmark managing platform which allows us to enhance the benchmark execution process with monitoring performance counters. The developed methodology and tool do not need additional benchmark instrumentation and have a negligible impact on its execution. The usefulness of this approach has been illustrated with experimental results covering a representative set of benchmark programs.
Benchmark (surveying)
Instrumentation
Benchmarking
Cite
Citations (0)
In this paper, we propose and evaluate a novel object detection architecture called Cascaded Multi-Channel Feature Pyramid Network, or CM-FPN. The proposed network, which is based on Feature Pyramid Network by Lin et al., employs multi-stage cascaded top-down feature pyramid networks to extract more semantic multiresolution feature maps for object region proposal and object classification. Depths of the feature maps are adjusted so that the feature maps in the later stages of the cascades where they are more semantic have higher channel depths. Experimental evaluation of the proposed approach has shown that the proposed method produces higher object detection accuracy.
Feature (linguistics)
Pyramid (geometry)
Semantic feature
Cite
Citations (0)
The process of implementing monetary policy by the Central Bank is that of taking the advantage of the manipulative instruments to reach the goals of policy so the Central Bank should choose the manipulative instruments according to certain benchmark so as to reach its goals better. The benchmark of choosing instruments of monetary policy by the Central Bank include theoretical benchmark and empirical benchmark. The theoretical benchmark consist of external and internal benchmark. Internal benchmark are the most important benchmark for daily operation,which include initiative benchmark,fine-tuning benchmark,signal-functioning benchmark,timeliness benchmark,and operablity benchmark.
Benchmark (surveying)
Cite
Citations (0)
Results of the third benchmark are briefly described. The problem requires solution of a mulirate system. It is found that the benchmark is a difficult problem and many respondees have used it to expand and debug their facilities. A more complete paper on the solutions of this benchmark will be submitted to the Control System Magazine for further dissemination.
Benchmark (surveying)
Cite
Citations (3)