Object Discovery From a Single Unlabeled Image by Mining Frequent Itemsets With Multi-Scale Features

Zhang, Runsheng; Huang, Yaping; Pu, Mengyang; Zhang, Jian; Guan, Qingji; Zou, Qi; Ling, Haibin

doi:10.1109/tip.2020.3015543

Cited by 24 publications

(19 citation statements)

References 82 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…However, if that is not the case, single-object images can be extracted from large scale images prior to using ALMI fully automatic. Some methods are proposed in [14][15][16] where the method proposed in [16] expects images from fixed cameras. The other two methods can be applied to any kind of dataset, e.g., image from OFOSs, FUOs, or semi-mobile platforms such as pan/tilt units.…”

Section: Discussionmentioning

confidence: 99%

“…else (15) denote the labels that are used to train the classifier. Third, to take the strong data imbalance and the dominating abundance of images with no objects (see Figure 2 top right) into account, the performance measurement had to be adapted.…”

Section: Evaluation On the Data Set LVmentioning

confidence: 99%

“…In almost all works published, these images are in fact image patches, marked by domain experts in large images showing an underwater scenery containing multiple objects. The detection and extraction of these patches showing single objects can be done by experts, sometimes supported by computational methods that often employ unsupervised learning [14][15][16] or even citizen scientists [17]. However, one task that cannot be supported straightforwardly with computational methods or non-experts is the final classification of objects to taxonomic categories or morphotypes, and this task is addressed in this work.…”

Section: Introductionmentioning

confidence: 99%

See 2 more Smart Citations

ALMI—A Generic Active Learning System for Computational Object Classification in Marine Observation Images

Möller

Nattkemper

2021

Sensors

View full text Add to dashboard Cite

In recent years, an increasing number of cabled Fixed Underwater Observatories (FUOs) have been deployed, many of them equipped with digital cameras recording high-resolution digital image time series for a given period. The manual extraction of quantitative information from these data regarding resident species is necessary to link the image time series information to data from other sensors but requires computational support to overcome the bottleneck problem in manual analysis. As a priori knowledge about the objects of interest in the images is almost never available, computational methods are required that are not dependent on the posterior availability of a large training data set of annotated images. In this paper, we propose a new strategy for collecting and using training data for machine learning-based observatory image interpretation much more efficiently. The method combines the training efficiency of a special active learning procedure with the advantages of deep learning feature representations. The method is tested on two highly disparate data sets. In our experiments, we can show that the proposed method ALMI achieves on one data set a classification accuracy A > 90% with less than N = 258 data samples and A > 80% after N = 150 iterations, i.e., training samples, on the other data set outperforming the reference method regarding accuracy and training data required.

show abstract

Section: Discussionmentioning

confidence: 99%

Section: Evaluation On the Data Set LVmentioning

confidence: 99%

Section: Introductionmentioning

confidence: 99%

See 1 more Smart Citation

ALMI—A Generic Active Learning System for Computational Object Classification in Marine Observation Images

Möller

Nattkemper

2021

Sensors

View full text Add to dashboard Cite

show abstract

“…Camera motion and object motion can both result in optical flow, therefore these methods can not be aware of the objects in the scene. In high-level vision, object tracking and object discovery in videos have been well-studied [3][4][5][6][7][8], especially with the introduction of unsupervised challenge of the DAVIS dataset [9]. However, the unsupervising in that challenge only means that the supervision information is not required for the test phase, but it is still required for the training phase.…”

Section: Introductionmentioning

confidence: 99%

“…However, the unsupervising in that challenge only means that the supervision information is not required for the test phase, but it is still required for the training phase. Despite remarkable performance, these approaches benefit either from object labels [5,7], or from pre-trained models in order to generate proposals [3,10]. In this paper, we define that an unsupervised video learning module should not use any manual annotation or pre-trained models on the manual annotation.…”

Section: Introductionmentioning

confidence: 99%

Unsupervised Learning from Videos for Object Discovery in Single Images

Zhao

Ding

et al. 2020

Symmetry

View full text Add to dashboard Cite

This paper proposes a method for discovering the primary objects in single images by learning from videos in a purely unsupervised manner—the learning process is based on videos, but the generated network is able to discover objects from a single input image. The rough idea is that an image typically consists of multiple object instances (like the foreground and background) that have spatial transformations across video frames and they can be sparsely represented. By exploring the sparsity representation of a video with a neural network, one may learn the features of each object instance without any labels, which can be used to discover, recognize, or distinguish object instances from a single image. In this paper, we consider a relatively simple scenario, where each image roughly consists of a foreground and a background. Our proposed method is based on encoder-decoder structures to sparsely represent the foreground, background, and segmentation mask, which further reconstruct the original images. We apply the feed-forward network trained from videos for object discovery in single images, which is different from the previous co-segmentation methods that require videos or collections of images as the input for inference. The experimental results on various object segmentation benchmarks demonstrate that the proposed method extracts primary objects accurately and robustly, which suggests that unsupervised image learning tasks can benefit from the sparsity of images and the inter-frame structure of videos.

show abstract

Object representation enhancement for self‐supervised colocalization

Jin

et al. 2022

Int J of Intelligent Sys

View full text Add to dashboard Cite

show abstract

Object Discovery From a Single Unlabeled Image by Mining Frequent Itemsets With Multi-Scale Features

Cited by 24 publications

References 82 publications

ALMI—A Generic Active Learning System for Computational Object Classification in Marine Observation Images

ALMI—A Generic Active Learning System for Computational Object Classification in Marine Observation Images

Unsupervised Learning from Videos for Object Discovery in Single Images

Object representation enhancement for self‐supervised colocalization

Contact Info

Product

Resources

About