On the Performance of GoogLeNet and AlexNet Applied to Sketches

Ballester, Pedro; Araújo, Ricardo M.

doi:10.1609/aaai.v30i1.10171

Cited by 225 publications

(49 citation statements)

References 13 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…This section provides a review of state-of-the-art work that investigated the CNN textural bias phenomenon on natural images. In 2016, Ballester and Araujo [11] tested pre-trained GoogLeNet and AlexNet on crowd-sourced sketches. Their aim was to investigate what CNNs could learn, as well as their limitations.…”

Section: Background a Textural Bias In Deep Convolutional Neural Networkmentioning

confidence: 99%

Reducing CNN Textural Bias With k-Space Artifacts Improves Robustness

Cabrera

Fetit

2022

IEEE Access

View full text Add to dashboard Cite

Convolutional neural networks (CNNs) have become the de facto algorithms of choice for semantic segmentation tasks in biomedical image processing. Yet, models based on CNNs remain susceptible to the domain shift problem, where a mismatch between source and target distributions could lead to a drop in performance. CNNs were recently shown to exhibit a textural bias when processing natural images, and recent studies suggest that this bias also extends to the context of biomedical imaging. In this paper, we focus on Magnetic Resonance Images (MRI) and investigate textural bias in the context of k-space artifacts (Gibbs, spike, and wraparound artifacts), which naturally manifest in clinical MRI scans. We show that carefully introducing such artifacts at training time can help reduce textural bias, and consequently lead to CNN models that are more robust to acquisition noise and out-of-distribution inference, including scans from hospitals not seen during training. We also present Gibbs ResUnet; a novel, end-to-end framework that automatically finds an optimal combination of Gibbs k-space stylizations and segmentation model weights. We illustrate our findings on multimodal and multi-institutional clinical MRI datasets obtained retrospectively from the Medical Segmentation Decathlon (n = 750) and The Cancer Imaging Archive (n = 243).INDEX TERMS Texture, bias, artifacts, robustness, MRI, CNNs.

show abstract

Section: Background a Textural Bias In Deep Convolutional Neural Networkmentioning

confidence: 99%

Reducing CNN Textural Bias With k-Space Artifacts Improves Robustness

Cabrera

Fetit

2022

IEEE Access

View full text Add to dashboard Cite

show abstract

“…Convolutional Neural Networks are mostly utilized in the ImageNet Challenge with various combinations of datasets of sketches [11].On image datasets, few studies have shown a comparison between the detection abilities of a human subject and a trained network . The comparison results showed that person corresponds to a 73.1% accuracy rate on the dataset whereas the outcomes of a trained network show a 64% accuracy rate [12]. Similarly, when Convolutional Neural Networks was applied to the identical dataset it yielded an accuracy of 74.9%, hence outperforming the accuracy rate of humans [13].…”

Section: IIImentioning

confidence: 99%

“…The used methods mostly make use of the strokes' order to achieve a much better accuracy rate. There are studies happening that aim at understanding Deep Neural Network's behavior in diverse situations [12]. These studies present how small changes made to a picture can severely change the results of grouping.…”

Section: IIImentioning

confidence: 99%

“…These studies present how small changes made to a picture can severely change the results of grouping. within the work also, presents images that are fully unrecognized by human's beings but are classified with high accuracy rates by the trained networks [12]. There has been a lot of progress in the field of feature detectors and descriptors, and various algorithms and strategies for object and scene categorization have been created.…”

Section: IIImentioning

confidence: 99%

See 1 more Smart Citation

Image Classification using Deep Learning and Tensorflow

Yadav¹,

Rais²,

Kumar³

et al. 2022

IJRASET

View full text Add to dashboard Cite

The image classification is one of the most classical problem of image processing. This research paper about image classification by using deep neural network(DNN) or also known as Deep learning by using framework Tensorflow. Python is used as a programming language because it comes together with Tensorflow framework. Image Classification nowdays is used to narrow the gap between the computer vision and human vision so that the images can be identify by the machine in the same way as human can do. It handle the assigning task for image class. So we are proposing a system called Image Classification using Deep Learning that classifies given images using classifiers such as Neural Network. The system will be built using Python as a programming language and Tensorflow to create neural networks. Keywords: Image classification, Deep Learning, Tensorflow

show abstract

“…There are various existing models that perform well and achieve good results. One of them is AlexNet (Ballester and de Araújo, 2016). It is one of the first networks that has introduced a method for solving the problem of overfitting and has used the dropout method.…”

Section: Background and Related Workmentioning

confidence: 99%

Incremental approach for multi-modal face expression recognition system using deep neural networks

Handa

Agarwal

Kohli

2021

IJCVR

View full text Add to dashboard Cite

Facial expression recognition (FER) is still one of the most challenging tasks. Convolutional neural network (CNN) and deep convolutional neural network (DCNN) has evolved as an efficient tool for FER models, but they differ significantly in terms of their network configuration and architecture. There exists a variety of bottlenecks in existing FER systems, such as they lack in generalising their algorithms. In this paper, we propose a model based on DCNN to overcome these challenges. Firstly, the proposed model focuses on the selection of an appropriate activation function depending on its accuracy and training loss over a database. Secondly, an incremental strategy is used in which deeper models are developed simultaneously from shallower networks to increase the accuracy with less training loss. Lastly, by an ensemble of CNN and DCNNs, the model achieves an accuracy of 74.15% for FER2013, 96.20% for CK+, and 98.25% for JAFFE databases, outperforming previous work.

show abstract

On the Performance of GoogLeNet and AlexNet Applied to Sketches

Cited by 225 publications

References 13 publications

Reducing CNN Textural Bias With k-Space Artifacts Improves Robustness

Reducing CNN Textural Bias With k-Space Artifacts Improves Robustness

Image Classification using Deep Learning and Tensorflow

Incremental approach for multi-modal face expression recognition system using deep neural networks

Contact Info

Product

Resources

About