Active Learning for Deep Object Detection

Brust, Clemens-Alexander; Käding, Christoph; Denzler, Joachim

doi:10.48550/arxiv.1809.09875

Cited by 18 publications

(29 citation statements)

References 0 publications

Supporting

Mentioning

Contrasting

Unclassified

Order By: Relevance

“…First, we contrast OLALA with image-level AL methods to analyze the modeling accuracy improvements from conducting object-level labeling. We find Brust, Käding, and Denzler (2018) the most appropriate comparison target for imagelevel AL. As their method calculates image scores based on aggregating object-level scores, the comparison can reveal the benefits of conducting ranking and selection at the object-level as opposed to the image-level.…”

Section: Methodsmentioning

confidence: 94%

“…AL for object detection has also attracted attention recently in the context of deep learning. Brust, Käding, and Denzler (2018) generate marginal scores for candidate boxes and aggregate them to imagelevel scores for active selection, while Roy, Unmesh, and Namboodiri (2018) apply the query by committee (Seung, Opper, and Sompolinsky 1992) method within convolution outputs to generate these scores. Aghdam et al (2019) propose a pixel level scoring method using convolution backbones and aggregate them to informativeness scores for image ranking.…”

Section: Related Workmentioning

confidence: 99%

“…High scores may imply larger information gains if the sample is selected for training, and an AL agent usually prioritizes labeling for such instances. It is designed to select the most informative samples for models (Aghdam et al 2019), or samples with the most ambiguous model predictions (Brust, Käding, and Denzler 2018). This image-level selection schema perfectly aligns with the typical AL framework for tasks like image classification, yet the user needs to create all objects labels Ȳi = Y i for the images in M t .…”

Section: Problem Formulationmentioning

confidence: 99%

“…Active learning (AL) provides powerful tools that can optimize object detection tasks by identifying the most important samples to label (Aghdam et al 2019;Haussmann et al 2020;Brust, Käding, and Denzler 2018;Roy, Unmesh, and Namboodiri 2018). However, while the end goal is to annotate individual objects within an image, these AL methods typically score and select samples at the image level, rather than at the object level.…”

Section: Introductionmentioning

confidence: 99%

See 3 more Smart Citations

OLALA: Object-Level Active Learning for Efficient Document Layout Annotation

Shen,

Zhao,

Dell

et al. 2020

Preprint

View full text Add to dashboard Cite

In layout object detection problems, the ground-truth datasets are constructed by annotating object instances individually. Yet active learning for object detection is typically conducted at the image level, not at the object level. Because objects appear with different frequencies across images, image-level active learning may be subject to over-exposure to common objects. This reduces the efficiency of human labeling. This work introduces an Object-Level Active Learning Layout Annotation framework, OLALA, which includes an object scoring method and a prediction correction algorithm. The object scoring method estimates the object prediction informativeness considering both the object category and the location. It selects only the most ambiguous object prediction regions within an image for annotators to label, optimizing the use of the annotation budget. For the unselected model predictions, we propose a correction algorithm to rectify two types of potential errors with minor supervision from ground-truths. The human annotated and model predicted objects are then merged as new image annotations for training the object detection models. In simulated labeling experiments, we show that OLALA helps to create the dataset more efficiently and report strong accuracy improvements of the trained models compared to image-level active learning baselines. The code is available at https://github.com/ lolipopshock/Detectron2 AL.

show abstract

Section: Methodsmentioning

confidence: 94%

Section: Related Workmentioning

confidence: 99%

Section: Problem Formulationmentioning

confidence: 99%

Section: Introductionmentioning

confidence: 99%

See 2 more Smart Citations

OLALA: Object-Level Active Learning for Efficient Document Layout Annotation

Shen,

Zhao,

Dell

et al. 2020

Preprint

View full text Add to dashboard Cite

show abstract

“…Furthermore, some data points are more informative than others. Active learning methods [17,134] could help efficiently generate new (either synthetic or real) samples that help intrinsic decomposition methods improve their generalization capabilities.…”

Section: Enhancing Generalizationmentioning

confidence: 99%

A Survey on Intrinsic Images: Delving Deep Into Lambert and Beyond

Garcés¹,

Rodríguez-Pardo²,

Casas³

et al. 2021

Preprint

View full text Add to dashboard Cite

Intrinsic imaging or intrinsic image decomposition has traditionally been described as the problem of decomposing an image into two layers: a reflectance, the albedo invariant color of the material; and a shading, produced by the interaction between light and geometry. Deep learning techniques have been broadly applied in recent years to increase the accuracy of those separations. In this survey, we overview those results in context of well-known intrinsic image data sets and relevant metrics used in the literature, discussing their suitability to predict a desirable intrinsic image decomposition. Although the Lambertian assumption is still a foundational basis for many methods, we show that there is increasing awareness on the potential of more sophisticated physicallyprincipled components of the image formation process, that is, optically accurate material models and geometry, and more complete inverse light transport estimations. We classify these methods in terms of the type of decomposition, considering the priors and models used, as well as the learning architecture and methodology driving the decomposition process. We also provide insights about future directions for research, given the recent advances in neural, inverse and differentiable rendering techniques.

show abstract

Mask-guided sample selection for semi-supervised instance segmentation

Bellver

Salvador

Torres

et al. 2020

Multimed Tools Appl

View full text Add to dashboard Cite

Image segmentation methods are usually trained with pixel-level annotations, which require significant human effort to collect. The most common solution to address this constraint is to implement weakly-supervised pipelines trained with lower forms of supervision, such as bounding boxes or scribbles. Another option are semi-supervised methods, which leverage a large amount of unlabeled data and a limited number of strongly-labeled samples. In this second setup, samples to be strongly-annotated can be selected randomly or with an active learning mechanism that chooses the ones that will maximize the model performance. In this work, we propose a sample selection approach to decide which samples to annotate for semi-supervised instance segmentation. Our method consists in first predicting pseudo-masks for the unlabeled pool of samples, together with a score predicting the quality of the mask. This score is an estimate of the Intersection Over Union (IoU) of the segment with the ground truth mask. We study which samples are better to annotate given the quality score, and show how our approach outperforms a random selection, leading to improved performance for semi-supervised instance segmentation with low annotation budgets.

show abstract

Active Learning for Deep Object Detection

Cited by 18 publications

References 0 publications

OLALA: Object-Level Active Learning for Efficient Document Layout Annotation

OLALA: Object-Level Active Learning for Efficient Document Layout Annotation

A Survey on Intrinsic Images: Delving Deep Into Lambert and Beyond

Mask-guided sample selection for semi-supervised instance segmentation

Contact Info

Product

Resources

About