Justification of STL-10 dataset using a competent CNN model trained on CIFAR-10

Singh, Hardik; Swagatika, Sweta; Venkat, Raavi Sai; Saxena, Sanjay

doi:10.1109/iceca.2019.8821870

Cited by 6 publications

(3 citation statements)

References 6 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…To address this issue, we propose to modify the skip-connection for capturing multi-scale information from local fea-tures. Experimental results show that our method outperforms state-of-the-art anomaly detection methods on datasets such as CIFAR10 [11], and STL10 [22] on outer-class task, LBOT [12] and MVTecAD [3] considering inter-class task, additionally. The main contributions of this paper are summarized as follows:…”

Section: Introductionmentioning

confidence: 91%

See 1 more Smart Citation

A Transformer-Based GAN for Anomaly Detection

Yang¹,

Lan²,

Huang³

et al. 2022

Lecture Notes in Computer Science

View full text Add to dashboard Cite

Anomaly detection is the task of detecting outliers from normal data. Numerous methods have been proposed to address this problem, including recent methods based on generative adversarial network (GAN). However, these methods are limited in capturing the long-range information in data due to the limited receptive field obtained by the convolution operation. The long-range information is crucial for producing distinctive representation for normal data belonging to different classes, while the local information is important for distinguishing normal data from abnormal data, if they belong to the same class. In this paper, we propose a novel Transformer-based architecture for anomaly detection which has advantages in extracting features with global information representing different classes as well as the local details useful for capturing anomalies. In our design, we introduce self-attention mechanism into the generator of GAN to extract global semantic information, and also modify the skip-connection to capture local details in multi-scale from input data. The experiments on CIFAR10 and STL10 show that our method provides better performance on representing different classes as compared with the state-of-the-art CNN-based GAN methods. Experiments performed on MVTecAD and LBOT datasets show that the proposed method offers state-of-the-art results, outperforming the baseline method SAGAN by over 3% in terms of the AUC metric.

show abstract

Section: Introductionmentioning

confidence: 91%

“…We evaluate our model 1 in a way of leave-one-class-out anomaly detection, with datasets CIFAR10 [11], STL10 [22], LBOT [12] and MVTecAD [3]. We use SAGAN 2 and Skip-Anomaly as baseline methods in our comparison.…”

Section: Inferencementioning

confidence: 99%

A Transformer-Based GAN for Anomaly Detection

Yang¹,

Lan²,

Huang³

et al. 2022

Lecture Notes in Computer Science

View full text Add to dashboard Cite

show abstract

“…Training a deep CNN 42 is the main idea behind it. From the training, the model starts learning about the pattern of data.…”

Section: Convolutional Neural Networkmentioning

confidence: 99%

Convolutional neural network and its pretrained models for image classification and object detection: A survey

Jena

Nayak

Saxena

2021

Concurrency and Computation

Self Cite

View full text Add to dashboard Cite

At present, in the age of computers and automation of services, deep learning (DL) technology, mainly the subset of machine learning (ML) and artificial intelligence (AI), is expressively used in innumerable domains of computer vision such as data analysis, image recognition, classification, natural language processing, and many more. It has become the foremost choice of researchers as of its effectiveness in producing decent results. This paper presents detailed and analytical literature starting from the very elementary level to the recent trends of this trending technology while focusing on the most used DL model, that is, convolutional neural network and its pretrained models for image classification and object detection. It also reviews diverse existing current literature based on this. Further, a brief introduction of AI, ML, and DL has also been presented, making the foundation for the readers. As pretrained models continuously give an upper edge to DL over ML and other technologies, 23 most popular pretrained models with their architectural diagrams have also been presented. This paper aims to summarize and analyze all the concepts used to formulate DL and its models. Also, we have emphasized more on the GoogleNet models and the entire Inception modules in detail. Finally, the fascinating applications and discussion on integral components of DL have been presented. This paper will definitely draw the attention of the students and researchers working in the area of DL and its models.

show abstract