Robust Object Detection With Inaccurate Bounding Boxes
- URL: http://arxiv.org/abs/2207.09697v1
- Date: Wed, 20 Jul 2022 06:57:30 GMT
- Title: Robust Object Detection With Inaccurate Bounding Boxes
- Authors: Chengxin Liu, Kewei Wang, Hao Lu, Zhiguo Cao, and Ziming Zhang
- Abstract summary: Learning accurate object detectors often requires large-scale training data with precise object bounding boxes.
In this work, we aim to address the challenge of learning robust object detectors with inaccurate bounding boxes.
By treating an object as a bag of instances, we introduce an Object-Aware Multiple Instance Learning approach.
- Score: 27.664730859319707
- License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
- Abstract: Learning accurate object detectors often requires large-scale training data
with precise object bounding boxes. However, labeling such data is expensive
and time-consuming. As the crowd-sourcing labeling process and the ambiguities
of the objects may raise noisy bounding box annotations, the object detectors
will suffer from the degenerated training data. In this work, we aim to address
the challenge of learning robust object detectors with inaccurate bounding
boxes. Inspired by the fact that localization precision suffers significantly
from inaccurate bounding boxes while classification accuracy is less affected,
we propose leveraging classification as a guidance signal for refining
localization results. Specifically, by treating an object as a bag of
instances, we introduce an Object-Aware Multiple Instance Learning approach
(OA-MIL), featured with object-aware instance selection and object-aware
instance extension. The former aims to select accurate instances for training,
instead of directly using inaccurate box annotations. The latter focuses on
generating high-quality instances for selection. Extensive experiments on
synthetic noisy datasets (i.e., noisy PASCAL VOC and MS-COCO) and a real noisy
wheat head dataset demonstrate the effectiveness of our OA-MIL. Code is
available at https://github.com/cxliu0/OA-MIL.
Related papers
- Bayesian Detector Combination for Object Detection with Crowdsourced Annotations [49.43709660948812]
Acquiring fine-grained object detection annotations in unconstrained images is time-consuming, expensive, and prone to noise.
We propose a novel Bayesian Detector Combination (BDC) framework to more effectively train object detectors with noisy crowdsourced annotations.
BDC is model-agnostic, requires no prior knowledge of the annotators' skill level, and seamlessly integrates with existing object detection models.
arXiv Detail & Related papers (2024-07-10T18:00:54Z) - Robust Tiny Object Detection in Aerial Images amidst Label Noise [50.257696872021164]
This study addresses the issue of tiny object detection under noisy label supervision.
We propose a DeNoising Tiny Object Detector (DN-TOD), which incorporates a Class-aware Label Correction scheme.
Our method can be seamlessly integrated into both one-stage and two-stage object detection pipelines.
arXiv Detail & Related papers (2024-01-16T02:14:33Z) - SalienDet: A Saliency-based Feature Enhancement Algorithm for Object
Detection for Autonomous Driving [160.57870373052577]
We propose a saliency-based OD algorithm (SalienDet) to detect unknown objects.
Our SalienDet utilizes a saliency-based algorithm to enhance image features for object proposal generation.
We design a dataset relabeling approach to differentiate the unknown objects from all objects in training sample set to achieve Open-World Detection.
arXiv Detail & Related papers (2023-05-11T16:19:44Z) - MuRAL: Multi-Scale Region-based Active Learning for Object Detection [20.478741635006116]
We propose a novel approach called Multi-scale Region-based Active Learning (MuRAL) for object detection.
MuRAL identifies informative regions of various scales to reduce annotation costs for well-learned objects.
Our proposed method surpasses all existing coarse-grained and fine-grained baselines on Cityscapes and MS COCO datasets.
arXiv Detail & Related papers (2023-03-29T12:52:27Z) - Robust Object Detection in Remote Sensing Imagery with Noisy and Sparse
Geo-Annotations (Full Version) [4.493174773769076]
In this paper, we present a novel approach for training object detectors with extremely noisy and incomplete annotations.
Our method is based on a teacher-student learning framework and a correction module accounting for imprecise and missing annotations.
We demonstrate that our approach improves standard detectors by 37.1% $AP_50$ on a noisy real-world remote-sensing dataset.
arXiv Detail & Related papers (2022-10-24T07:25:31Z) - Scaling Novel Object Detection with Weakly Supervised Detection
Transformers [21.219817483091166]
We propose the Weakly Supervised Detection Transformer, which enables efficient knowledge transfer from a large-scale pretraining dataset to WSOD finetuning.
Our experiments show that our approach outperforms previous state-of-the-art models on large-scale novel object detection datasets.
arXiv Detail & Related papers (2022-07-11T21:45:54Z) - Semi-supervised Object Detection via Virtual Category Learning [68.26956850996976]
This paper proposes to use confusing samples proactively without label correction.
Specifically, a virtual category (VC) is assigned to each confusing sample.
It is attributed to specifying the embedding distance between the training sample and the virtual category.
arXiv Detail & Related papers (2022-07-07T16:59:53Z) - Discovery-and-Selection: Towards Optimal Multiple Instance Learning for
Weakly Supervised Object Detection [86.86602297364826]
We propose a discoveryand-selection approach fused with multiple instance learning (DS-MIL)
Our proposed DS-MIL approach can consistently improve the baselines, reporting state-of-the-art performance.
arXiv Detail & Related papers (2021-10-18T07:06:57Z) - Labels Are Not Perfect: Inferring Spatial Uncertainty in Object
Detection [26.008419879970365]
In this work, we infer the uncertainty in bounding box labels from LiDAR point clouds based on a generative model.
Comprehensive experiments show that the proposed model reflects complex environmental noises in LiDAR perception and the label quality.
We propose Jaccard IoU as a new evaluation metric that extends IoU by incorporating label uncertainty.
arXiv Detail & Related papers (2020-12-18T09:11:44Z) - Towards Noise-resistant Object Detection with Noisy Annotations [119.63458519946691]
Training deep object detectors requires significant amount of human-annotated images with accurate object labels and bounding box coordinates.
Noisy annotations are much more easily accessible, but they could be detrimental for learning.
We address the challenging problem of training object detectors with noisy annotations, where the noise contains a mixture of label noise and bounding box noise.
arXiv Detail & Related papers (2020-03-03T01:32:16Z)
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.