• Journal of Broadcast Engineering
• /
• v.26 no.1
• /
• pp.70-78
• /
• 2021

Estimating 3D information from a single image is one of the essential problems in numerous applications. Since a 2D image inherently might originate from an infinite number of different 3D scenes, thus 3D reconstruction from a single image is notoriously challenging. This challenge has been overcame by the advent of recent deep convolutional neural networks (CNNs), by modeling the mapping function between 2D image and 3D information. However, to train such deep CNNs, a massive training data is demanded, but such data is difficult to achieve or even impossible to build. Recent trends thus aim to present deep learning techniques that can be trained in a weakly-supervised manner, with a meta-data without relying on the ground-truth depth data. In this article, we introduce recent developments of weakly-supervised deep learning technique, especially categorized as scene 3D reconstruction and object 3D reconstruction, and discuss limitations and further directions.

• The Journal of the Institute of Internet, Broadcasting and Communication
• /
• v.19 no.6
• /
• pp.227-233
• /
• 2019

Recently, along with the recent development of deep learning technique, neural networks are achieving success in computer vision filed. Convolutional neural network have shown outstanding performance in not only for a simple image classification task, but also for tasks with high difficulty such as object segmentation and detection. However many such deep learning models are based on supervised-learning, which requires more annotation labels than image-level label. Especially image semantic segmentation model requires pixel-level annotations for training, which is very. To solve these problems, this paper proposes a weakly-supervised semantic segmentation method which requires only image level label to train network. Existing weakly-supervised learning methods have limitations in detecting only specific area of object. In this paper, on the other hand, we use multi-classifier deep learning architecture so that our model recognizes more different parts of objects. The proposed method is evaluated using VOC 2012 validation dataset.

• Proceedings of the Korean Society of Broadcast Engineers Conference
• /
• 2022.11a
• /
• pp.171-174
• /
• 2022

Weakly-supervised learning is a widely adopted approach in video anomaly detection whereby only video labels are utilized instead of expensive frame-level annotations. Since the success of multi-instance learning (MIL), almost all recent approaches are based on maximizing the margin between the set of abnormal video snippets and those of normal video snippets. In this work, we present a simple contrastive approach for weakly supervised video anomaly detection (WS-VAD) with aims to enhance the performance of existing models. The method is generic in nature and introduces a loss function to encourage attraction of output features from the same video class and repel those from different video classes. Experimental results demonstrate our method can be applied to existing algorithms to improve detection accuracy in public video anomaly dataset.

• Journal of the Korea Institute of Information and Communication Engineering
• /
• v.24 no.2
• /
• pp.204-211
• /
• 2020

In this paper, we propose an optimal deep learning network architecture for main object location detection through weak supervised learning. The proposed network adds convolution blocks for improving the localization accuracy of the main object through weakly-supervised learning. The additional deep learning network consists of five additional blocks that add a composite product layer based on VGG-16. And the proposed network was trained by the method of weakly-supervised learning that does not require real location information for objects. In addition, Grad-CAM to compensate for the weakness of GAP in CAM, which is one of weak supervised learning methods, was used. The proposed network was tested through the CUB-200-2011 data set, we could obtain 50.13% in top-1 localization error. Also, the proposed network shows higher accuracy in detecting the main object than the existing method.

• The Journal of the Acoustical Society of Korea
• /
• v.40 no.2
• /
• pp.139-147
• /
• 2021

This paper introduces and implements a Sound Event Detection (SED) system based on weakly-supervised learning where only part of the data is labeled, and analyzes the effect of parameters. The SED system estimates the classes and onset/offset times of events in the acoustic signal. In order to train the model, all information on the event class and onset/offset times must be provided. Unfortunately, the onset/offset times are hard to be labeled exactly. Therefore, in the weakly-supervised task, the SED model is trained by "strongly labeled data" including the event class and activations, "weakly labeled data" including the event class, and "unlabeled data" without any label. Recently, the SED systems using the mean-teacher model are widely used for the task with several parameters. These parameters should be chosen carefully because they may affect the performance. In this paper, performance analysis was performed on parameters, such as the feature, moving average parameter, weight of the consistency cost function, ramp-up length, and maximum learning rate, using the data of DCASE 2020 Task 4. Effects and the optimal values of the parameters were discussed.

• KSII Transactions on Internet and Information Systems (TIIS)
• /
• v.16 no.7
• /
• pp.2359-2376
• /
• 2022

With the exponential growth of medical image big data represented by high-resolution CT images(CTI), the high-resolution CTI data is of great importance for clinical research and diagnosis. The paper takes lung CTI as an example to study. Retrieving answer CTIs similar to the input one from the large-scale lung CTI database can effectively assist physicians to diagnose. Compared with the conventional content-based image retrieval(CBIR) methods, the CBIR for lung CTIs demands higher retrieval accuracy in both the contour shape and the internal details of the organ. In traditional supervised deep learning networks, the learning of the network relies on the labeling of CTIs which is a very time-consuming task. To address this issue, the paper proposes a Weakly Supervised Similarity Evaluation Network (WSSENet) for efficiently support similarity analysis of lung CTIs. We conducted extensive experiments to verify the effectiveness of the WSSENet based on which the CBIR is performed.

• Journal of Drive and Control
• /
• v.20 no.2
• /
• pp.15-23
• /
• 2023

In this study, two-dimensional location of crops for auto weeding was detected using deep learning. To construct a dataset for soybean detection, an image-capturing system was developed using a mono camera and single-board computer and the system was mounted on a weeding robot to collect soybean images. A dataset was constructed by extracting RoI (region of interest) from the raw image and each sample was labeled with soybean and the background for classification learning. The deep learning model consisted of four convolutional layers and was trained with a weakly supervised learning method that can provide object localization only using image-level labeling. Localization of the soybean area can be visualized via CAM and the two-dimensional position of the soybean was estimated by clustering the pixels associated with the soybean area and transforming the pixel coordinates to world coordinates. The actual position, which is determined manually as pixel coordinates in the image was evaluated and performances were 6.6(X-axis), 5.1(Y-axis) and 1.2(X-axis), 2.2(Y-axis) for MSE and RMSE about world coordinates, respectively. From the results, we confirmed that the center position of the soybean area derived through deep learning was sufficient for use in automatic weeding systems.

• KIPS Transactions on Software and Data Engineering
• /
• v.10 no.9
• /
• pp.349-358
• /
• 2021

Recently, a method of finding the attention area or localization area for an object of an image using CAM (Class Activation Map)[1] has been variously carried out as a study of WSOL (Weakly Supervised Object Localization). The attention area extraction from the object heat map using CAM has a disadvantage in that it cannot find the entire area of the object by focusing mainly on the part where the features are most concentrated in the object. To improve this, using CAM and Selective Search[6] together, we first expand the attention area in the heat map, and a Gaussian smoothing is applied to the extended area to generate retraining data. Finally we train the data to expand the attention area of the objects. The proposed method requires retraining only once, and the search time to find an localization area is greatly reduced since the selective search is not needed in this stage. Through the experiment, the attention area was expanded from the existing CAM heat maps, and in the calculation of IOU (Intersection of Union) with the ground truth for the bounding box of the expanded attention area, about 58% was improved compared to the existing CAM.

• Journal of the Korea Institute of Information and Communication Engineering
• /
• v.24 no.10
• /
• pp.1271-1279
• /
• 2020

Text region detection is a technology that detects text area in handwriting or printed documents. The detected text areas are digitized through a recognition step, which is used in various fields depending on the purpose of use. However, the detection result of the small text unit is not suitable for the industrial field. In addition, the border of tables in the document that it causes miss-detected results, which has an adverse effect on the recognition step. To solve the issues, we propose a method for detecting text region using the border information of the table. In order to utilize the border information of the table, the proposed method adjusts the flow of two decoders. Experimentally, we show improved performance using the table border pseudo label based on weak supervised learning.

• Proceedings of the Korean Society of Broadcast Engineers Conference
• /
• 2022.11a
• /
• pp.145-148
• /
• 2022

준지도학습 기반의 동영상 이상행동감지는 구하기 어려운 프레임 단위 레이블이 필요하지 않아 더 많은 동영상을 학습에 활용 가능한 장점이 있어 관련 연구가 활발히 진행되고 있다. 최근 제안된 기법들은 주로 UCF-Crime 이라는 실제 CCTV 동영상 데이터셋을 활용하고 있는데, 본 데이터셋은 학습 영상과 테스트 영상에서 이상행동 클래스 별 분포도가 균등하지 않다. 본 연구에서는 해당 불균형으로 인해 학습 모델이 특정 행동 클래스에 과적합될 수 있음을 보이며, 이러한 불균형을 해결하기 위해 Class-Balanced Multiple Instance Learning Loss 를 제안한다. 이를 통해 기존에 특정 클래스에 편중되었던 모델이 이상행동 종류에 좀 더 균등한 성능을 낼 수 있음을 보여준다. 특히 단순히 클래스별 정확도가 제로섬(zero sum)으로 증감하는 것이 아니라 전체적인 이상행동 판별 정확도 또한 향상됨을 실험 결과를 통해 확인할 수 있다.