• International Journal of Computer Science & Network Security
• /
• 제21권7호
• /
• pp.182-190
• /
• 2021

Deep learning is an advanced technology for large-scale data analysis, with numerous promising cases like image processing, object detection and significantly more. It becomes customarily to use transfer learning and fine-tune a pre-trained CNN model for most image recognition tasks. Having people taking photos and tag themselves provides a valuable resource of in-data. However, these tags and labels might be noisy as people who annotate these images might not be experts. This paper aims to explore the impact of noisy labels on fine-tuning pre-trained CNN models. Such effect is measured on a food recognition task using Food101 as a benchmark. Four pre-trained CNN models are included in this study: InceptionV3, VGG19, MobileNetV2 and DenseNet121. Symmetric label noise will be added with different ratios. In all cases, models based on DenseNet121 outperformed the other models. When noisy labels were introduced to the data, the performance of all models degraded almost linearly with the amount of added noise.

• 한국멀티미디어학회논문지
• /
• 제23권11호
• /
• pp.1349-1360
• /
• 2020

In recent years, Convolutional Neural Networks (CNNs) have been successfully implemented in different tasks of computer vision. Since CNN models are the representatives of supervised learning algorithms, they demand large amount of data in order to train the classifiers. Thus, obtaining data with correct labels is imperative to attain the state-of-the-art performance of the CNN models. However, labelling datasets is quite tedious and expensive process, therefore real-life datasets often exhibit incorrect labels. Although the issue of poorly labelled datasets has been studied before, we have noticed that the methods are very complex and hard to reproduce. Therefore, in this research work, we propose Deep CleanNet - a considerably simple system that achieves competitive results when compared to the existing methods. We use K-means clustering algorithm for selecting data with correct labels and train the new dataset using a deep CNN model. The technique achieves competitive results in both training and validation stages. We conducted experiments using MNIST database of handwritten digits with 50% corrupted labels and achieved up to 10 and 20% increase in training and validation sets accuracy scores, respectively.

• KSII Transactions on Internet and Information Systems (TIIS)
• /
• 제11권5호
• /
• pp.2523-2538
• /
• 2017

In most of the existing literature, the definition of the class label has the following characteristics. First, the class label of the samples from the same object has an absolutely fixed value. Second, the difference between class labels of the samples from different objects should be maximized. However, the appearance of a face varies greatly due to the variations of the illumination, pose, and expression. Therefore, the previous definition of class label is not quite reasonable. Inspired by discriminative least squares regression algorithm (DLSR), a noisy label based discriminative least squares regression algorithm (NLDLSR) is presented in this paper. In our algorithm, the maximization difference between the class labels of the samples from different objects should be satisfied. Meanwhile, the class label of the different samples from the same object is allowed to have small difference, which is consistent with the fact that the different samples from the same object have some differences. In addition, the proposed NLDLSR is expanded to the kernel space, and we further propose a novel kernel noisy label based discriminative least squares regression algorithm (KNLDLSR). A large number of experiments show that our proposed algorithms can achieve very good performance.

• International Journal of Fuzzy Logic and Intelligent Systems
• /
• 제14권1호
• /
• pp.8-16
• /
• 2014

We consider the visual barcode recognition problem in a noisy video data setup. Unlike most existing single-frame recognizers that require considerable user effort to acquire clean, motionless and blur-free barcode signals, we eliminate such extra human efforts by proposing a robust video-based barcode recognition algorithm. We deal with a sequence of noisy blurred barcode image frames by posing it as an online filtering problem. In the proposed dynamic recognition model, at each frame we infer the blur level of the frame as well as the digit class label. In contrast to a frame-by-frame based approach with heuristic majority voting scheme, the class labels and frame-wise noise levels are propagated along the frame sequences in our model, and hence we exploit all cues from noisy frames that are potentially useful for predicting the barcode label in a probabilistically reasonable sense. We also suggest a visual barcode tracking approach that efficiently localizes barcode areas in video frames. The effectiveness of the proposed approaches is demonstrated empirically on both synthetic and real data setup.

• Journal of Communications and Networks
• /
• 제5권2호
• /
• pp.157-166
• /
• 2003

This paper deals with the problem of channel identification for Single Input Multiple Output (SIMO) slow fading channels using clustering algorithms. Due to the intrinsic memory of the discrete-time model of the channel, over short observation periods, the received data vectors of the SIMO model are spread in clusters because of the AWGN noise. Each cluster is practically centered around the ideal channel output labels without noise and the noisy received vectors are distributed according to a multivariate Gaussian distribution. Starting from the Markov SIMO channel model, simultaneous maximum ikelihood estimation of the input vector and the channel coefficients reduce to one of obtaining the values of this pair that minimizes the sum of the Euclidean norms between the received and the estimated output vectors. Viterbi algorithm can be used for this purpose provided the trellis diagram of the Markov model can be labeled with the noiseless channel outputs. The problem of identification of the ideal channel outputs, which is the focus of this paper, is then equivalent to designing a Vector Quantizer (VQ) from a training set corresponding to the observed noisy channel outputs. The Linde-Buzo-Gray (LBG)-type clustering algorithms [1] could be used to obtain the noiseless channel output labels from the noisy received vectors. One problem with the use of such algorithms for blind time-varying channel identification is the codebook initialization. This paper looks at two critical issues with regards to the use of VQ for channel identification. The first has to deal with the applicability of this technique in general; we present theoretical results for the conditions under which the technique may be applicable. The second aims at overcoming the codebook initialization problem by proposing a novel approach which attempts to make the first phase of the channel estimation faster than the classical codebook initialization methods. Sample simulation results are provided confirming the effectiveness of the proposed initialization technique.

• 한국정보통신학회:학술대회논문집
• /
• 한국정보통신학회 2021년도 춘계학술대회
• /
• pp.607-610
• /
• 2021

지도학습에서 모델을 학습함에 있어 입력 데이터와 해당 데이터의 라벨이 필요하다. 하지만 신뢰성 있는 라벨링은 비용과 시간적인 면에서 많이 소요되며 이를 자동화할 경우 라벨이 언제나 맞는다는 보장이 없어 노이즈가 들어가게 된다. 이러한 라벨 노이즈 환경에서 지도학습을 진행할 경우 모델은 학습 초기에는 정확도가 올라가지만, 어느 정도 학습 후 정확도가 크게 감소되는 경향을 보인다. 라벨 노이즈 문제를 해결하기 위해 다양한 방법이 있지만, 대다수의 경우 모델이 예측한 확률을 수도라벨로 사용해 이용하는 경우가 많다. 여기에 대해서 우리는 모델이 예측한 확률을 정제하여 좀 더 빠르게 참 라벨을 예측하는 방법을 제시한다. 기존의 논문 중 모델이 예측한 확률을 사용하는 방법에 우리가 제안하는 방법을 적용하여 같은 환경, 데이터셋에 대해 실험을 진행한 결과 성능개선과 더 빠르게 수렴하는 것을 확인할 수 있었다. 이를 통해 기존 연구들 중 모델이 예측하는 확률분포를 사용하는 방법들에 적용할 수 있고 같은 환경에서도 더 빠르게 수렴시킬 수 있기에 학습 소요시간을 줄일 수 있다.

• KSII Transactions on Internet and Information Systems (TIIS)
• /
• 제14권12호
• /
• pp.4776-4794
• /
• 2020

We propose a rapid adaptive learning framework for streaming object detection, called EER-ASSL. The method combines the expected error reduction (EER) dependent rollback learning and the active semi-supervised learning (ASSL) for a rapid adaptive CNN detector. Most CNN object detectors are built on the assumption of static data distribution. However, images are often noisy and biased, and the data distribution is imbalanced in a real world environment. The proposed method consists of collaborative sampling and EER-ASSL. The EER-ASSL utilizes the active learning (AL) and rollback based semi-supervised learning (SSL). The AL allows us to select more informative and representative samples measuring uncertainty and diversity. The SSL divides the selected streaming image samples into the bins and each bin repeatedly transfers the discriminative knowledge of the EER and CNN models to the next bin until convergence and incorporation with the EER rollback learning algorithm is achieved. The EER models provide a rapid short-term myopic adaptation and the CNN models an incremental long-term performance improvement. EER-ASSL can overcome noisy and biased labels in varying data distribution. Extensive experiments shows that EER-ASSL obtained 70.9 mAP compared to state-of-the-art technology such as Faster RCNN, SSD300, and YOLOv2.

• 한국음향학회지
• /
• 제40권5호
• /
• pp.479-487
• /
• 2021

본 논문에서는 잡음 학생 모델 기반의 자가 학습을 활용한 음향 사건 검지 기법을 제안한다. 제안된 음향 사건 검지 모델은 두 단계로 구성된다. 첫 번째 단계에서는 잔차 합성곱 순환 신경망(Residual Convolutional Recurrent Neural Network, RCRNN)을 훈련하여 레이블이 지정되지 않은 비표기 데이터셋의 레이블 예측에 활용한다. 두 번째 단계에서는 세 가지 잡음 종류를 적용한 잡음 학생 모델을 자가학습 기법으로 반복하여 학습한다. 여기서 잡음 학생 모델은 SpecAugment, Mixup, 시간-주파수 이동을 활용한 특징 잡음, 드롭아웃을 활용한 모델 잡음, 그리고 semi-supervised loss function을 적용한 레이블 잡음을 활용하여 학습된다. 제안된 음향 사건 검지 모델의 성능은 Detection and Classification of Acoustic Scenes and Events(DCASE) 2020 Challenge Task 4의 validation set으로 평가하였다. DCASE 2020 챌린지 데이터셋의 baseline 및 최상위 랭크된 모델과 이벤트 단위 F1 점수 성능을 비교한 결과, 제안된 음향 사건 검지 모델이 단일 모델과 앙상블 모델에서 최상위 모델 대비 F1 점수를 각각 4.6 %와 3.4 % 향상시켰다.

• Journal of Information Processing Systems
• /
• 제11권4호
• /
• pp.528-537
• /
• 2015

Text in images is one of the most important cues for understanding a scene. In this paper, we propose a novel approach based on interest points to localize text in natural scene images. The main ideas of this approach are as follows: first we used interest point detection techniques, which extract the corner points of characters and center points of edge connected components, to select candidate regions. Second, these candidate regions were verified by using tensor voting, which is capable of extracting perceptual structures from noisy data. Finally, area, orientation, and aspect ratio were used to filter out non-text regions. The proposed method was tested on the ICDAR 2003 dataset and images of wine labels. The experiment results show the validity of this approach.

• 정보과학회 논문지
• /
• 제44권9호
• /
• pp.887-892
• /
• 2017

뇌-컴퓨터 인터페이스는 정신 작업 동안 다채널에서 생성된 뇌파의 신호를 측정, 분석하여 컴퓨터를 제어하거나 의사를 전달하는 기술이다. 이때 최적의 뇌파 채널 선택은 뇌-컴퓨터 인터페이스의 편의성과 속도뿐만 아니라 정확도 향상을 위해 필요하다. 최적의 채널은 중복 채널들 또는 노이즈 채널들을 제거함으로써 얻는다. 이 논문에서는 최적 뇌파 채널을 선택하기 위해 이중 filter-기반의 채널 선택 방법을 제안한다. 제안한 방법은 먼저 채널들 간의 중복성을 제거하기 위해 spearman's rank correlation을 사용하여 중복 채널들을 제거한다. 그 뒤, F score를 이용하여 채널과 클래스 라벨 간의 적합성을 측정하여 상위 m개의 채널들만을 선택한다. 제안한 방법은 클래스 라벨과 관련되고 중복이 없는 채널들을 사용함으로써 좋은 분류 정확도를 이끌어 낼 수 있다. 제안한 채널 선택 방법은 채널의 수를 상당히 줄임과 동시에 평균 분류 정확도를 향상시켰다.