CPM R-CNN: Calibrating Point-guided Misalignment in Object Detection
- URL: http://arxiv.org/abs/2003.03570v2
- Date: Wed, 4 Nov 2020 09:12:36 GMT
- Title: CPM R-CNN: Calibrating Point-guided Misalignment in Object Detection
- Authors: Bin Zhu, Qing Song, Lu Yang, Zhihui Wang, Chun Liu, Mengjie Hu
- Abstract summary: CPM R-CNN contains three efficient modules to optimize anchor-based point-guided method.
Compared with Faster R-CNN and Grid R-CNN based on ResNet-101 with FPN, our approach can substantially improve detection mAP by 3.3% and 1.5% respectively.
- Score: 30.819685214855685
- License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
- Abstract: In object detection, offset-guided and point-guided regression dominate
anchor-based and anchor-free method separately. Recently, point-guided approach
is introduced to anchor-based method. However, we observe points predicted by
this way are misaligned with matched region of proposals and score of
localization, causing a notable gap in performance. In this paper, we propose
CPM R-CNN which contains three efficient modules to optimize anchor-based
point-guided method. According to sufficient evaluations on the COCO dataset,
CPM R-CNN is demonstrated efficient to improve the localization accuracy by
calibrating mentioned misalignment. Compared with Faster R-CNN and Grid R-CNN
based on ResNet-101 with FPN, our approach can substantially improve detection
mAP by 3.3% and 1.5% respectively without whistles and bells. Moreover, our
best model achieves improvement by a large margin to 49.9% on COCO test-dev.
Code and models will be publicly available.
Related papers
- SGCCNet: Single-Stage 3D Object Detector With Saliency-Guided Data Augmentation and Confidence Correction Mechanism [7.631190617438259]
Single-stage point-based 3D object detectors face challenges such as inadequate learning of low-quality objects (ILQ) and misalignment between localization accuracy and classification confidence (MLC)
For ILQ, SGCCNet adopts a Saliency-Guided Data Augmentation (SGDA) strategy to enhance the robustness of the model on low-quality objects.
For MLC, we design a Confidence Correction Mechanism ( CCM) specifically for point-based multi-class detectors.
arXiv Detail & Related papers (2024-07-01T12:36:01Z) - CPR++: Object Localization via Single Coarse Point Supervision [55.8671776333499]
coarse point refinement (CPR) is first attempt to alleviate semantic variance from an algorithmic perspective.
CPR reduces semantic variance by selecting a semantic centre point in a neighbourhood region to replace the initial annotated point.
CPR++ can obtain scale information and further reduce the semantic variance in a global region.
arXiv Detail & Related papers (2024-01-30T17:38:48Z) - Accurate and Reliable Methods for 5G UAV Jamming Identification With
Calibrated Uncertainty [3.4208659698673127]
Only increasing accuracy without considering uncertainty may negatively impact Deep Neural Network (DNN) decision-making.
This paper proposes five combined preprocessing and post-processing methods for time-series binary classification problems.
arXiv Detail & Related papers (2022-11-05T15:04:45Z) - Learning to Register Unbalanced Point Pairs [10.369750912567714]
Recent 3D registration methods can effectively handle large-scale or partially overlapping point pairs.
We present a novel 3D registration method, called UPPNet, for the unbalanced point pairs.
arXiv Detail & Related papers (2022-07-09T08:03:59Z) - Object Localization under Single Coarse Point Supervision [107.46800858130658]
We propose a POL method using coarse point annotations, relaxing the supervision signals from accurate key points to freely spotted points.
CPR constructs point bags, selects semantic-correlated points, and produces semantic center points through multiple instance learning (MIL)
In this way, CPR defines a weakly supervised evolution procedure, which ensures training high-performance object localizer under coarse point supervision.
arXiv Detail & Related papers (2022-03-17T14:14:11Z) - Boost Neural Networks by Checkpoints [9.411567653599358]
We propose a novel method to ensemble the checkpoints of deep neural networks (DNNs)
With the same training budget, our method achieves 4.16% lower error on Cifar-100 and 6.96% on Tiny-ImageNet with ResNet-110 architecture.
arXiv Detail & Related papers (2021-10-03T09:14:15Z) - Adaptive Nearest Neighbor Machine Translation [60.97183408140499]
kNN-MT combines pre-trained neural machine translation with token-level k-nearest-neighbor retrieval.
Traditional kNN algorithm simply retrieves a same number of nearest neighbors for each target token.
We propose Adaptive kNN-MT to dynamically determine the number of k for each target token.
arXiv Detail & Related papers (2021-05-27T09:27:42Z) - Making Affine Correspondences Work in Camera Geometry Computation [62.7633180470428]
Local features provide region-to-region rather than point-to-point correspondences.
We propose guidelines for effective use of region-to-region matches in the course of a full model estimation pipeline.
Experiments show that affine solvers can achieve accuracy comparable to point-based solvers at faster run-times.
arXiv Detail & Related papers (2020-07-20T12:07:48Z) - Calibrating Deep Neural Network Classifiers on Out-of-Distribution
Datasets [20.456742449675904]
CCAC (Confidence with an Auxiliary Class) is a new post-hoc confidence calibration method for deep neural network (DNN)
Key novelty of CCAC is an auxiliary class in the calibration model which separates mis-classified samples from correctly classified ones.
Our experiments on different DNN models, datasets and applications show that CCAC can consistently outperform the prior post-hoc calibration methods.
arXiv Detail & Related papers (2020-06-16T04:06:21Z) - 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) - Robust 6D Object Pose Estimation by Learning RGB-D Features [59.580366107770764]
We propose a novel discrete-continuous formulation for rotation regression to resolve this local-optimum problem.
We uniformly sample rotation anchors in SO(3), and predict a constrained deviation from each anchor to the target, as well as uncertainty scores for selecting the best prediction.
Experiments on two benchmarks: LINEMOD and YCB-Video, show that the proposed method outperforms state-of-the-art approaches.
arXiv Detail & Related papers (2020-02-29T06:24:55Z)
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.