Zero Cost Improvements for General Object Detection Network
- URL: http://arxiv.org/abs/2011.07756v2
- Date: Mon, 15 Nov 2021 17:24:01 GMT
- Title: Zero Cost Improvements for General Object Detection Network
- Authors: Shaohua Wang, Yaping Dai
- Abstract summary: Two modules are proposed to improve detection precision with zero cost.
We employ the scale attention mechanism to efficiently fuse multi-level feature maps with less parameters.
Experiment results show that the networks with the two modules can surpass original networks by 1.1 AP and 0.8 AP with zero cost.
- Score: 6.072666305426913
- License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
- Abstract: Modern object detection networks pursuit higher precision on general object
detection datasets, at the same time the computation burden is also increasing
along with the improvement of precision. Nevertheless, the inference time and
precision are both critical to object detection system which needs to be
real-time. It is necessary to research precision improvement without extra
computation cost. In this work, two modules are proposed to improve detection
precision with zero cost, which are focus on FPN and detection head improvement
for general object detection networks. We employ the scale attention mechanism
to efficiently fuse multi-level feature maps with less parameters, which is
called SA-FPN module. Considering the correlation of classification head and
regression head, we use sequential head to take the place of widely-used
parallel head, which is called Seq-HEAD module. To evaluate the effectiveness,
we apply the two modules to some modern state-of-art object detection networks,
including anchor-based and anchor-free. Experiment results on coco dataset show
that the networks with the two modules can surpass original networks by 1.1 AP
and 0.8 AP with zero cost for anchor-based and anchor-free networks,
respectively. Code will be available at https://git.io/JTFGl.
Related papers
- Semi-Supervised and Long-Tailed Object Detection with CascadeMatch [91.86787064083012]
We propose a novel pseudo-labeling-based detector called CascadeMatch.
Our detector features a cascade network architecture, which has multi-stage detection heads with progressive confidence thresholds.
We show that CascadeMatch surpasses existing state-of-the-art semi-supervised approaches in handling long-tailed object detection.
arXiv Detail & Related papers (2023-05-24T07:09:25Z) - Rethinking the Detection Head Configuration for Traffic Object Detection [11.526701794026641]
We propose a lightweight traffic object detection network based on matching between detection head and object distribution.
The proposed model achieves more competitive performance than other models on BDD100K dataset and our proposed ETFOD-v2 dataset.
arXiv Detail & Related papers (2022-10-08T02:23:57Z) - CPFN: Cascaded Primitive Fitting Networks for High-Resolution Point
Clouds [51.47100091540298]
We present Cascaded Primitive Fitting Networks (CPFN) that relies on an adaptive patch sampling network to assemble detection results of global and local primitive detection networks.
CPFN improves the state-of-the-art SPFN performance by 13-14% on high-resolution point cloud datasets and specifically improves the detection of fine-scale primitives by 20-22%.
arXiv Detail & Related papers (2021-08-31T23:27:33Z) - Oriented R-CNN for Object Detection [61.78746189807462]
This work proposes an effective and simple oriented object detection framework, termed Oriented R-CNN.
In the first stage, we propose an oriented Region Proposal Network (oriented RPN) that directly generates high-quality oriented proposals in a nearly cost-free manner.
The second stage is oriented R-CNN head for refining oriented Regions of Interest (oriented RoIs) and recognizing them.
arXiv Detail & Related papers (2021-08-12T12:47:43Z) - AGSFCOS: Based on attention mechanism and Scale-Equalizing pyramid
network of object detection [10.824032219531095]
Our model has a certain improvement in accuracy compared with the current popular detection models on the COCO dataset.
Our optimal model can get 39.5% COCO AP under the background of ResNet50.
arXiv Detail & Related papers (2021-05-20T08:41:02Z) - Enhancing Object Detection for Autonomous Driving by Optimizing Anchor
Generation and Addressing Class Imbalance [0.0]
This study presents an enhanced 2D object detector based on Faster R-CNN that is better suited for the context of autonomous vehicles.
The proposed modifications over the Faster R-CNN do not increase computational cost and can easily be extended to optimize other anchor-based detection frameworks.
arXiv Detail & Related papers (2021-04-08T16:58:31Z) - Enabling certification of verification-agnostic networks via
memory-efficient semidefinite programming [97.40955121478716]
We propose a first-order dual SDP algorithm that requires memory only linear in the total number of network activations.
We significantly improve L-inf verified robust accuracy from 1% to 88% and 6% to 40% respectively.
We also demonstrate tight verification of a quadratic stability specification for the decoder of a variational autoencoder.
arXiv Detail & Related papers (2020-10-22T12:32:29Z) - Scope Head for Accurate Localization in Object Detection [135.9979405835606]
We propose a novel detector coined as ScopeNet, which models anchors of each location as a mutually dependent relationship.
With our concise and effective design, the proposed ScopeNet achieves state-of-the-art results on COCO.
arXiv Detail & Related papers (2020-05-11T04:00:09Z) - Depthwise Non-local Module for Fast Salient Object Detection Using a
Single Thread [136.2224792151324]
We propose a new deep learning algorithm for fast salient object detection.
The proposed algorithm achieves competitive accuracy and high inference efficiency simultaneously with a single CPU thread.
arXiv Detail & Related papers (2020-01-22T15:23:48Z) - Seeing without Looking: Contextual Rescoring of Object Detections for AP
Maximization [4.346179456029563]
We propose to incorporate context in object detection by post-processing the output of an arbitrary detector.
Rescoring is done by conditioning on contextual information from the entire set of detections.
We show that AP can be improved by simply reassigning the detection confidence values.
arXiv Detail & Related papers (2019-12-27T18:56:29Z)
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.