Learning Deep Features for Discriminative Localization

Zhou, Bolei; Khosla, Aditya; Lapedriza, Àgata; Oliva, Aude; Torralba, Antonio

doi:10.48550/arxiv.1512.04150

Cited by 130 publications

(127 citation statements)

References 17 publications

Supporting

Mentioning

126

Contrasting

Order By: Relevance

“…We have built the architecture of CNEEP, which allows us to directly reflect the spatial importance of EP, inspired by the visual interpretation techniques of CNNs [60,61]. The CNEEP has been firstly applied to the bead-spring model to demonstrate its performance, and the results have shown that the CNEEP precisely captures how much EP occurs in different areas of images along a single movie as well as the ensemble average.…”

Section: Discussionmentioning

confidence: 99%

Attaining entropy production and dissipation maps from Brownian movies via neural networks

Bae,

Kim,

Jeong

2021

Preprint

View full text Add to dashboard Cite

Quantifying entropy production (EP) is essential to understand stochastic systems at mesoscopic scales, such as living organisms or biological assemblies. However, without tracking the relevant variables, it is challenging to figure out where and to what extent EP occurs from recorded time-series image data from experiments. Here, applying a convolutional neural network (CNN), a powerful tool for image processing, we develop an estimation method for EP through an unsupervised learning algorithm that calculates only from movies. Together with an attention map of the CNN's last layer, our method can not only quantify stochastic EP but also produce the spatiotemporal pattern of the EP (dissipation map). We show that our method accurately measures the EP and creates a dissipation map in two nonequilibrium systems, the bead-spring model and a network of elastic filaments. We further confirm high performance even with noisy, low spatial resolution data, and partially observed situations. Our method will provide a practical way to obtain dissipation maps and ultimately contribute to uncovering the nonequilibrium nature of complex systems.

show abstract

Section: Discussionmentioning

confidence: 99%

Attaining entropy production and dissipation maps from Brownian movies via neural networks

Bae,

Kim,

Jeong

2021

Preprint

View full text Add to dashboard Cite

show abstract

“…CNNs also contain another important layer known as a pooling layer. These layers are used to down sample feature maps (Zhou et al 2015). For this work, we use MaxPooling.…”

Section: Convolutional Neural Networkmentioning

confidence: 99%

Morphological classification of galaxies with deep learning: comparing 3-way and 4-way CNNs

Cavanagh,

Bekki,

Groves

2021

Preprint

View full text Add to dashboard Cite

Classifying the morphologies of galaxies is an important step in understanding their physical properties and evolutionary histories. The advent of large-scale surveys has hastened the need to develop techniques for automated morphological classification. We train and test several convolutional neural network architectures to classify the morphologies of galaxies in both a 3-class (elliptical, lenticular, spiral) and 4-class (+irregular/miscellaneous) schema with a dataset of 14034 visually-classified SDSS images. We develop a new CNN architecture that outperforms existing models in both 3 and 4-way classification, with overall classification accuracies of 83% and 81% respectively. We also compare the accuracies of 2-way / binary classifications between all four classes, showing that ellipticals and spirals are most easily distinguished (>98% accuracy), while spirals and irregulars are hardest to differentiate (78% accuracy). Through an analysis of all classified samples, we find tentative evidence that misclassifications are physically meaningful, with lenticulars misclassified as ellipticals tending to be more massive, among other trends. We further combine our binary CNN classifiers to perform a hierarchical classification of samples, obtaining comparable accuracies (81%) to the direct 3-class CNN, but considerably worse accuracies in the 4-way case (65%). As an additional verification, we apply our networks to a small sample of Galaxy Zoo images, obtaining accuracies of 92%, 82% and 77% for the binary, 3-way and 4-way classifications respectively.

show abstract

“…In this paper, GradCam and SmoothGrad are used to visualize class activation and saliency maps respectively. Saliency Maps such as SmoothGrad and vanilla saliency [25] uses the gradients of the output layer with respect to input image which tells us how the output value changes with a change in input value whereas class activation maps [24] such as GradCAM, ScoreCAM, and many more, didn't use gradients instead they use penultimate layer (pre-dense) to get spatial information which gets lost in dense layers. tf-keras-vis [42] visualization toolkit was used for visualization of these maps.…”

Section: Attention Visualizationmentioning

confidence: 99%

Prediction of lung and colon cancer through analysis of histopathological images by utilizing Pre-trained CNN models with visualization of class activation and saliency maps

Garg

2020

2020 3rd Artificial Intelligence and Cloud Computing Conference

View full text Add to dashboard Cite

Colon and Lung cancer is one of the most perilous and dangerous ailments that individuals are enduring worldwide and has become a general medical problem. To lessen the risk of death, a legitimate and early finding is particularly required. In any case, it is a truly troublesome task that depends on the experience of histopathologists. If a histologist is under-prepared it may even hazard the life of a patient. As of late, deep learning has picked up energy, and it is being valued in the analysis of Medical Imaging. This paper intends to utilize and alter the current pre-trained CNN-based model to identify lung and colon cancer utilizing histopathological images with better augmentation techniques. In this paper, eight distinctive Pre-trained CNN models, VGG16, NASNetMobile, InceptionV3, InceptionResNetV2, ResNet50, Xception, MobileNet, and DenseNet169 are trained on LC25000 dataset. The model performances are assessed on precision, recall, f1score, accuracy, and auroc score. The results exhibit that all eight models accomplished noteworthy results ranging from 96% to 100% accuracy. Subsequently, GradCAM and SmoothGrad are also used to picture the attention images of Pre-trained CNN models classifying malignant and benign images. CCS Concepts: • Computing methodologies → Supervised learning by classification; Neural networks; Computer vision; • Applied computing → Health care information systems.

show abstract

Learning Deep Features for Discriminative Localization

Cited by 130 publications

References 17 publications

Attaining entropy production and dissipation maps from Brownian movies via neural networks

Attaining entropy production and dissipation maps from Brownian movies via neural networks

Morphological classification of galaxies with deep learning: comparing 3-way and 4-way CNNs

Prediction of lung and colon cancer through analysis of histopathological images by utilizing Pre-trained CNN models with visualization of class activation and saliency maps

Contact Info

Product

Resources

About