Probabilistic two-stage detection
- URL: http://arxiv.org/abs/2103.07461v1
- Date: Fri, 12 Mar 2021 18:56:17 GMT
- Title: Probabilistic two-stage detection
- Authors: Xingyi Zhou, Vladlen Koltun, Philipp Kr\"ahenb\"uhl
- Abstract summary: We show how to build a probabilistic two-stage detector from any state-of-the-art one-stage detector.
The resulting detectors are faster and more accurate than both their one- and two-stage precursors.
- Score: 83.9604523643406
- License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
- Abstract: We develop a probabilistic interpretation of two-stage object detection. We
show that this probabilistic interpretation motivates a number of common
empirical training practices. It also suggests changes to two-stage detection
pipelines. Specifically, the first stage should infer proper
object-vs-background likelihoods, which should then inform the overall score of
the detector. A standard region proposal network (RPN) cannot infer this
likelihood sufficiently well, but many one-stage detectors can. We show how to
build a probabilistic two-stage detector from any state-of-the-art one-stage
detector. The resulting detectors are faster and more accurate than both their
one- and two-stage precursors. Our detector achieves 56.4 mAP on COCO test-dev
with single-scale testing, outperforming all published results. Using a
lightweight backbone, our detector achieves 49.2 mAP on COCO at 33 fps on a
Titan Xp, outperforming the popular YOLOv4 model.
Related papers
- DF40: Toward Next-Generation Deepfake Detection [62.073997142001424]
Existing works identify top-notch detection algorithms and models by adhering to the common practice: training detectors on one specific dataset (e.g., FF++) and testing them on other prevalent deepfake datasets.
But can these stand-out "winners" be truly applied to tackle the myriad of realistic and diverse deepfakes lurking in the real world?
We construct a highly diverse and large-scale deepfake dataset called DF40, which comprises 40 distinct deepfake techniques.
We then conduct comprehensive evaluations using 4 standard evaluation protocols and 7 representative detectors, resulting in over 2,000 evaluations.
arXiv Detail & Related papers (2024-06-19T12:35:02Z) - Simplifying Two-Stage Detectors for On-Device Inference in Remote Sensing [0.7305342793164903]
We propose a model simplification method for two-stage object detectors.
Our method reduces computation costs upto 61.2% with the accuracy loss within 2.1% on the DOTAv1.5 dataset.
arXiv Detail & Related papers (2024-04-11T00:45:10Z) - COCO-O: A Benchmark for Object Detectors under Natural Distribution
Shifts [27.406639379618003]
COCO-O is a test dataset based on COCO with 6 types of natural distribution shifts.
COCO-O has a large distribution gap with training data and results in a significant 55.7% relative performance drop on a Faster R-CNN detector.
We study the robustness effect on recent breakthroughs of detector's architecture design, augmentation and pre-training techniques.
arXiv Detail & Related papers (2023-07-24T12:22:19Z) - 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) - PDNet: Towards Better One-stage Object Detection with Prediction
Decoupling [37.83405509385431]
We propose a prediction-target-decoupled detector named PDNet to establish a more flexible detection paradigm.
With a single ResNeXt-64x4d-101 as the backbone, our detector achieves 48.7 AP with single-scale testing.
arXiv Detail & Related papers (2021-04-28T16:48:04Z) - Object Detection Made Simpler by Eliminating Heuristic NMS [70.93004137521946]
We show a simple NMS-free, end-to-end object detection framework.
We attain on par or even improved detection accuracy compared with the original one-stage detector.
arXiv Detail & Related papers (2021-01-28T02:38:29Z) - MimicDet: Bridging the Gap Between One-Stage and Two-Stage Object
Detection [65.74032877197844]
One-stage detectors are more efficient owing to straightforward architectures, but the two-stage detectors still take the lead in accuracy.
We propose MimicDet, a novel framework to train a one-stage detector by directly mimicking the two-stage features.
Mimic methods have a shared backbone for one-stage and two-stage detectors, then it branches into two heads which are well designed to have compatible features for mimicking.
arXiv Detail & Related papers (2020-09-24T07:36:58Z) - Detection in Crowded Scenes: One Proposal, Multiple Predictions [79.28850977968833]
We propose a proposal-based object detector, aiming at detecting highly-overlapped instances in crowded scenes.
The key of our approach is to let each proposal predict a set of correlated instances rather than a single one in previous proposal-based frameworks.
Our detector can obtain 4.9% AP gains on challenging CrowdHuman dataset and 1.0% $textMR-2$ improvements on CityPersons dataset.
arXiv Detail & Related papers (2020-03-20T09:48:53Z)
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.