MuRAL: Multi-Scale Region-based Active Learning for Object Detection
- URL: http://arxiv.org/abs/2303.16637v1
- Date: Wed, 29 Mar 2023 12:52:27 GMT
- Title: MuRAL: Multi-Scale Region-based Active Learning for Object Detection
- Authors: Yi-Syuan Liou, Tsung-Han Wu, Jia-Fong Yeh, Wen-Chin Chen, Winston H.
Hsu
- Abstract summary: 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.
- Score: 20.478741635006116
- License: http://creativecommons.org/licenses/by-nc-nd/4.0/
- Abstract: Obtaining large-scale labeled object detection dataset can be costly and
time-consuming, as it involves annotating images with bounding boxes and class
labels. Thus, some specialized active learning methods have been proposed to
reduce the cost by selecting either coarse-grained samples or fine-grained
instances from unlabeled data for labeling. However, the former approaches
suffer from redundant labeling, while the latter methods generally lead to
training instability and sampling bias. To address these challenges, 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 and improve training
performance. The informative region score is designed to consider both the
predicted confidence of instances and the distribution of each object category,
enabling our method to focus more on difficult-to-detect classes. Moreover,
MuRAL employs a scale-aware selection strategy that ensures diverse regions are
selected from different scales for labeling and downstream finetuning, which
enhances training stability. Our proposed method surpasses all existing
coarse-grained and fine-grained baselines on Cityscapes and MS COCO datasets,
and demonstrates significant improvement in difficult category performance.
Related papers
- 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) - Virtual Category Learning: A Semi-Supervised Learning Method for Dense
Prediction with Extremely Limited Labels [63.16824565919966]
This paper proposes to use confusing samples proactively without label correction.
A Virtual Category (VC) is assigned to each confusing sample in such a way that it can safely contribute to the model optimisation.
Our intriguing findings highlight the usage of VC learning in dense vision tasks.
arXiv Detail & Related papers (2023-12-02T16:23:52Z) - MUS-CDB: Mixed Uncertainty Sampling with Class Distribution Balancing
for Active Annotation in Aerial Object Detection [40.94800050576902]
Recent aerial object detection models rely on a large amount of labeled training data.
Active learning effectively reduces the data labeling cost by selectively querying the informative and representative unlabelled samples.
We propose a novel active learning method for cost-effective aerial object detection.
arXiv Detail & Related papers (2022-12-06T07:50:00Z) - In Defense of Core-set: A Density-aware Core-set Selection for Active
Learning [3.6753274024067593]
In a real-world active learning scenario, considering the diversity of the selected samples is crucial.
In this work, we analyze the feature space through the lens of the density and propose a density-aware core-set (DACS)
The strategy is to estimate the density of the unlabeled samples and select diverse samples mainly from sparse regions.
arXiv Detail & Related papers (2022-06-10T01:47:49Z) - Self-supervised Assisted Active Learning for Skin Lesion Segmentation [18.78959113954792]
Label scarcity has been a long-standing issue for biomedical image segmentation, due to high annotation costs and professional requirements.
We propose a novel self-supervised assisted active learning framework in the cold-start setting, in which the segmentation model is first warmed up with self-supervised learning.
Our approach is capable of achieving promising performance with substantial improvements over existing baselines.
arXiv Detail & Related papers (2022-05-14T09:40:18Z) - 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) - Data-Uncertainty Guided Multi-Phase Learning for Semi-Supervised Object
Detection [66.10057490293981]
We propose a data-uncertainty guided multi-phase learning method for semi-supervised object detection.
Our method behaves extraordinarily compared to baseline approaches and outperforms them by a large margin.
arXiv Detail & Related papers (2021-03-29T09:27:23Z) - Minimax Active Learning [61.729667575374606]
Active learning aims to develop label-efficient algorithms by querying the most representative samples to be labeled by a human annotator.
Current active learning techniques either rely on model uncertainty to select the most uncertain samples or use clustering or reconstruction to choose the most diverse set of unlabeled examples.
We develop a semi-supervised minimax entropy-based active learning algorithm that leverages both uncertainty and diversity in an adversarial manner.
arXiv Detail & Related papers (2020-12-18T19:03:40Z) - SPL-MLL: Selecting Predictable Landmarks for Multi-Label Learning [87.27700889147144]
We propose to select a small subset of labels as landmarks which are easy to predict according to input (predictable) and can well recover the other possible labels (representative)
We employ the Alternating Direction Method (ADM) to solve our problem. Empirical studies on real-world datasets show that our method achieves superior classification performance over other state-of-the-art methods.
arXiv Detail & Related papers (2020-08-16T11:07:44Z) - Towards Cross-Granularity Few-Shot Learning: Coarse-to-Fine
Pseudo-Labeling with Visual-Semantic Meta-Embedding [13.063136901934865]
Few-shot learning aims at rapidly adapting to novel categories with only a handful of samples at test time.
In this paper, we advance the few-shot classification paradigm towards a more challenging scenario, i.e., cross-granularity few-shot classification.
We approximate the fine-grained data distribution by greedy clustering of each coarse-class into pseudo-fine-classes according to the similarity of image embeddings.
arXiv Detail & Related papers (2020-07-11T03:44:21Z)
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.