Active Learning for Object Detection with Non-Redundant Informative
Sampling
- URL: http://arxiv.org/abs/2307.08414v1
- Date: Mon, 17 Jul 2023 11:55:20 GMT
- Title: Active Learning for Object Detection with Non-Redundant Informative
Sampling
- Authors: Aral Hekimoglu, Adrian Brucker, Alper Kagan Kayali, Michael Schmidt,
Alvaro Marcos-Ramiro
- Abstract summary: Our strategy integrates uncertainty and diversity-based selection principles into a joint selection objective.
Our proposed NORIS algorithm quantifies the impact of training with a sample on the informativeness of other similar samples.
Our strategy achieves a 20% and 30% reduction in labeling costs compared to random selection for PASCAL-VOC and KITTI.
- Score: 1.7602289331729377
- License: http://creativecommons.org/licenses/by-sa/4.0/
- Abstract: Curating an informative and representative dataset is essential for enhancing
the performance of 2D object detectors. We present a novel active learning
sampling strategy that addresses both the informativeness and diversity of the
selections. Our strategy integrates uncertainty and diversity-based selection
principles into a joint selection objective by measuring the collective
information score of the selected samples. Specifically, our proposed NORIS
algorithm quantifies the impact of training with a sample on the
informativeness of other similar samples. By exclusively selecting samples that
are simultaneously informative and distant from other highly informative
samples, we effectively avoid redundancy while maintaining a high level of
informativeness. Moreover, instead of utilizing whole image features to
calculate distances between samples, we leverage features extracted from
detected object regions within images to define object features. This allows us
to construct a dataset encompassing diverse object types, shapes, and angles.
Extensive experiments on object detection and image classification tasks
demonstrate the effectiveness of our strategy over the state-of-the-art
baselines. Specifically, our selection strategy achieves a 20% and 30%
reduction in labeling costs compared to random selection for PASCAL-VOC and
KITTI, respectively.
Related papers
- On-the-Fly Object-aware Representative Point Selection in Point Cloud [21.55830632188697]
We propose a representative point selection framework for point cloud downsampling.<n>We show that our method consistently outperforms state-of-the-art baselines in both efficiency and effectiveness.<n>As a model-agnostic solution, our approach integrates seamlessly with diverse downstream models.
arXiv Detail & Related papers (2025-08-04T01:39:09Z) - Extending Dataset Pruning to Object Detection: A Variance-based Approach [0.0]
We present the first extension of classification pruning techniques to the object detection domain.<n>We propose tailored solutions, including a novel scoring method called Variance-based Prediction Score (VPS)<n>Our work bridges dataset pruning and object detection, paving the way for dataset pruning in complex vision tasks.
arXiv Detail & Related papers (2025-05-22T19:46:51Z) - MAFE R-CNN: Selecting More Samples to Learn Category-aware Features for Small Object Detection [21.402560040693558]
Small object detection in intricate environments has consistently represented a major challenge in the field of object detection.<n>In this paper, we identify that this difficulty stems from the detectors' inability to effectively learn discriminative features for objects of small size.<n>We propose the Multi-Clue Assignment and Feature Enhancement R-CNN, which integrates two pivotal components.
arXiv Detail & Related papers (2025-05-22T09:30:09Z) - TSceneJAL: Joint Active Learning of Traffic Scenes for 3D Object Detection [26.059907173437114]
TSceneJAL framework can efficiently sample the balanced, diverse, and complex traffic scenes from both labeled and unlabeled data.
Our approach outperforms existing state-of-the-art methods on 3D object detection tasks with up to 12% improvements.
arXiv Detail & Related papers (2024-12-25T11:07:04Z) - Oriented Tiny Object Detection: A Dataset, Benchmark, and Dynamic Unbiased Learning [51.170479006249195]
We introduce a new dataset, benchmark, and a dynamic coarse-to-fine learning scheme in this study.
Our proposed dataset, AI-TOD-R, features the smallest object sizes among all oriented object detection datasets.
We present a benchmark spanning a broad range of detection paradigms, including both fully-supervised and label-efficient approaches.
arXiv Detail & Related papers (2024-12-16T09:14:32Z) - Downstream-Pretext Domain Knowledge Traceback for Active Learning [138.02530777915362]
We propose a downstream-pretext domain knowledge traceback (DOKT) method that traces the data interactions of downstream knowledge and pre-training guidance.
DOKT consists of a traceback diversity indicator and a domain-based uncertainty estimator.
Experiments conducted on ten datasets show that our model outperforms other state-of-the-art methods.
arXiv Detail & Related papers (2024-07-20T01:34:13Z) - Annotation-Efficient Polyp Segmentation via Active Learning [45.59503015577479]
We propose a deep active learning framework for annotation-efficient polyp segmentation.
In practice, we measure the uncertainty of each sample by examining the similarity between features masked by the prediction map of the polyp and the background area.
We show that our proposed method achieved state-of-the-art performance compared to other competitors on both a public dataset and a large-scale in-house dataset.
arXiv Detail & Related papers (2024-03-21T12:25:17Z) - Metric-aligned Sample Selection and Critical Feature Sampling for
Oriented Object Detection [4.677438149607058]
We introduce affine transformation to evaluate the quality of samples and propose a distance-based label assignment strategy.
The proposed metric-aligned selection (MAS) strategy can dynamically select samples according to the shape and rotation characteristic of objects.
The results show the state-of-the-art accuracy of the proposed detector.
arXiv Detail & Related papers (2023-06-29T06:36:46Z) - infoVerse: A Universal Framework for Dataset Characterization with
Multidimensional Meta-information [68.76707843019886]
infoVerse is a universal framework for dataset characterization.
infoVerse captures multidimensional characteristics of datasets by incorporating various model-driven meta-information.
In three real-world applications (data pruning, active learning, and data annotation), the samples chosen on infoVerse space consistently outperform strong baselines.
arXiv Detail & Related papers (2023-05-30T18:12:48Z) - 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) - Uncertainty Aware Active Learning for Reconfiguration of Pre-trained
Deep Object-Detection Networks for New Target Domains [0.0]
Object detection is one of the most important and fundamental aspects of computer vision tasks.
To obtain training data for object detection model efficiently, many datasets opt to obtain their unannotated data in video format.
Annotating every frame from a video is costly and inefficient since many frames contain very similar information for the model to learn from.
In this paper, we proposed a novel active learning algorithm for object detection models to tackle this problem.
arXiv Detail & Related papers (2023-03-22T17:14:10Z) - Exploring Active 3D Object Detection from a Generalization Perspective [58.597942380989245]
Uncertainty-based active learning policies fail to balance the trade-off between point cloud informativeness and box-level annotation costs.
We propose textscCrb, which hierarchically filters out the point clouds of redundant 3D bounding box labels.
Experiments show that the proposed approach outperforms existing active learning strategies.
arXiv Detail & Related papers (2023-01-23T02:43:03Z) - Exploiting Diversity of Unlabeled Data for Label-Efficient
Semi-Supervised Active Learning [57.436224561482966]
Active learning is a research area that addresses the issues of expensive labeling by selecting the most important samples for labeling.
We introduce a new diversity-based initial dataset selection algorithm to select the most informative set of samples for initial labeling in the active learning setting.
Also, we propose a novel active learning query strategy, which uses diversity-based sampling on consistency-based embeddings.
arXiv Detail & Related papers (2022-07-25T16:11:55Z) - ALLSH: Active Learning Guided by Local Sensitivity and Hardness [98.61023158378407]
We propose to retrieve unlabeled samples with a local sensitivity and hardness-aware acquisition function.
Our method achieves consistent gains over the commonly used active learning strategies in various classification tasks.
arXiv Detail & Related papers (2022-05-10T15:39:11Z) - Budget-aware Few-shot Learning via Graph Convolutional Network [56.41899553037247]
This paper tackles the problem of few-shot learning, which aims to learn new visual concepts from a few examples.
A common problem setting in few-shot classification assumes random sampling strategy in acquiring data labels.
We introduce a new budget-aware few-shot learning problem that aims to learn novel object categories.
arXiv Detail & Related papers (2022-01-07T02:46:35Z) - Active Learning for Deep Object Detection via Probabilistic Modeling [27.195742892250916]
We propose a novel deep active learning approach for object detection.
Our approach relies on mixture density networks that estimate a probabilistic distribution for each localization and classification head's output.
Our method uses a scoring function that aggregates these two types of uncertainties for both heads to obtain every image's informativeness score.
arXiv Detail & Related papers (2021-03-30T07:37:11Z)
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.