Where's Wally Now? Deep Generative and Discriminative Embeddings for Novelty Detection

Burlina, Philippe; Joshi, Neil; Wang, I-Jeng

doi:10.1109/cvpr.2019.01177

Cited by 37 publications

(35 citation statements)

References 21 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Although KDGAN-3 achieves the second-best results on MNIST and FMNIST, it shows the worst performance on CIFAR-10 dataset. KDGAN- 4 obtains the second-best results on CIFAR-10, but it is about 0.5% lower than the best result. In addition, KDGAN-d (KDGAN- 4 ) illustrated in Figure 6(c) is inferior in accuracy and training stability compared to P-KDGAN-II.…”

Section: E Evaluation Of P-kdgan Methodsmentioning

confidence: 88%

P-KDGAN: Progressive Knowledge Distillation with GANs for One-class Novelty Detection

Zhang

Chen

Sun

2020

Proceedings of the Twenty-Ninth International Joint Conference on Artificial Intelligence

View full text Add to dashboard Cite

One-class novelty detection is to identify anomalous instances that do not conform to the expected normal instances. In this paper, the Generative Adversarial Networks (GANs) based on encoder-decoder-encoder pipeline are used for detection and achieve state-of-the-art performance. However, deep neural networks are too over-parameterized to deploy on resource-limited devices. Therefore, Progressive Knowledge Distillation with GANs (P-KDGAN) is proposed to learn compact and fast novelty detection networks. The P-KDGAN is a novel attempt to connect two standard GANs by the designed distillation loss for transferring knowledge from the teacher to the student. The progressive learning of knowledge distillation is a two-step approach that continuously improves the performance of the student GAN and achieves better performance than single step methods. In the first step, the student GAN learns the basic knowledge totally from the teacher via guiding of the pre-trained teacher GAN with fixed weights. In the second step, joint fine-training is adopted for the knowledgeable teacher and student GANs to further improve the performance and stability. The experimental results on CIFAR-10, MNIST, and FMNIST show that our method improves the performance of the student GAN by 2.44%, 1.77%, and 1.73% when compressing the computation at ratios of 24.45:1, 311.11:1, and 700:1, respectively.

show abstract

Section: E Evaluation Of P-kdgan Methodsmentioning

confidence: 88%

P-KDGAN: Progressive Knowledge Distillation with GANs for One-class Novelty Detection

Zhang

Chen

Sun

2020

Proceedings of the Twenty-Ninth International Joint Conference on Artificial Intelligence

View full text Add to dashboard Cite

show abstract

“…1 ). The original method in Burlina et al 14 is used to start with synthetic images with markers of DR, and perform latent space manipulation on those images, via gradient descent, to generate new images that included the desired markers for subpopulations of darker-skin individuals.…”

Section: Methodsmentioning

confidence: 99%

“…To accomplish this, first, a StyleGAN model was trained as in Burlina et al 14 using the same training dataset used by the baseline DLS. Pairs of (latent space vector w , and image I ), were then generated by using the trained StyleGAN model, in inference mode (about 120,000 [w, I] tuples).…”

Section: Methodsmentioning

confidence: 99%

“…This study addresses this situation and considers algorithmic debiasing approaches. Algorithmic solutions to bias due to imbalance may include simple approaches, such as using reweighting of the training loss function or more complex ones such as: using DLSs that requires less training data (so called “low-shot method”) 11 , 12 ; using anomaly detectors 13 , 14 that work by detecting distributional inliers versus outliers; or using adversarial approaches that try to mask information about protected attributes of the individual. 7 , 15 Some of the aforementioned strategies have inherent limitations.…”

Section: Introductionmentioning

confidence: 99%

See 1 more Smart Citation

Addressing Artificial Intelligence Bias in Retinal Diagnostics

Burlina

Joshi

Paul

et al. 2021

Trans. Vis. Sci. Tech.

Self Cite

View full text Add to dashboard Cite

Purpose This study evaluated generative methods to potentially mitigate artificial intelligence (AI) bias when diagnosing diabetic retinopathy (DR) resulting from training data imbalance or domain generalization, which occurs when deep learning systems (DLSs) face concepts at test/inference time they were not initially trained on. Methods The public domain Kaggle EyePACS dataset (88,692 fundi and 44,346 individuals, originally diverse for ethnicity) was modified by adding clinician-annotated labels and constructing an artificial scenario of data imbalance and domain generalization by disallowing training (but not testing) exemplars for images of retinas with DR warranting referral (DR-referable) from darker-skin individuals, who presumably have greater concentration of melanin within uveal melanocytes, on average, contributing to retinal image pigmentation. A traditional/baseline diagnostic DLS was compared against new DLSs that would use training data augmented via generative models for debiasing. Results Accuracy (95% confidence intervals [CIs]) of the baseline diagnostics DLS for fundus images of lighter-skin individuals was 73.0% (66.9% to 79.2%) versus darker-skin of 60.5% (53.5% to 67.3%), demonstrating bias/disparity (delta = 12.5%; Welch t -test t = 2.670, P = 0.008) in AI performance across protected subpopulations. Using novel generative methods for addressing missing subpopulation training data (DR-referable darker-skin) achieved instead accuracy, for lighter-skin, of 72.0% (65.8% to 78.2%), and for darker-skin, of 71.5% (65.2% to 77.8%), demonstrating closer parity (delta = 0.5%) in accuracy across subpopulations (Welch t -test t = 0.111, P = 0.912). Conclusions Findings illustrate how data imbalance and domain generalization can lead to disparity of accuracy across subpopulations, and show that novel generative methods of synthetic fundus images may play a role for debiasing AI. Translational Relevance New AI methods have possible applications to address potential AI bias in DR diagnostics from fundus pigmentation, and potentially other ophthalmic DLSs too.

show abstract

“…The most prominent examples are MNIST (LeCun et al 1998), CIFAR10 (Krizhevsky and Hinton 2009), and ImageNet (Krizhevsky et al 2012). A popular approach is to select an arbitrary subset of classes, re-label them as outliers, and train a novelty detection system solely on the remaining inlier classes (An and Cho 2015;Chalapathy et al 2018;Ruff et al 2018;Burlina et al 2019). During the testing phase, it is checked whether the trained model is able to correctly predict that a test sample belongs to one of the inlier classes.…”

Section: Classification Of Anomalous Imagesmentioning

confidence: 99%

The MVTec Anomaly Detection Dataset: A Comprehensive Real-World Dataset for Unsupervised Anomaly Detection

et al. 2021

View full text Add to dashboard Cite

The detection of anomalous structures in natural image data is of utmost importance for numerous tasks in the field of computer vision. The development of methods for unsupervised anomaly detection requires data on which to train and evaluate new approaches and ideas. We introduce the MVTec anomaly detection dataset containing 5354 high-resolution color images of different object and texture categories. It contains normal, i.e., defect-free images intended for training and images with anomalies intended for testing. The anomalies manifest themselves in the form of over 70 different types of defects such as scratches, dents, contaminations, and various structural changes. In addition, we provide pixel-precise ground truth annotations for all anomalies. We conduct a thorough evaluation of current state-of-the-art unsupervised anomaly detection methods based on deep architectures such as convolutional autoencoders, generative adversarial networks, and feature descriptors using pretrained convolutional neural networks, as well as classical computer vision methods. We highlight the advantages and disadvantages of multiple performance metrics as well as threshold estimation techniques. This benchmark indicates that methods that leverage descriptors of pretrained networks outperform all other approaches and deep-learning-based generative models show considerable room for improvement.

show abstract

Where's Wally Now? Deep Generative and Discriminative Embeddings for Novelty Detection

Cited by 37 publications

References 21 publications

P-KDGAN: Progressive Knowledge Distillation with GANs for One-class Novelty Detection

P-KDGAN: Progressive Knowledge Distillation with GANs for One-class Novelty Detection

Addressing Artificial Intelligence Bias in Retinal Diagnostics

The MVTec Anomaly Detection Dataset: A Comprehensive Real-World Dataset for Unsupervised Anomaly Detection

Contact Info

Product

Resources

About