Search Results for author:
Found 15 papers, 5 papers with code
Constricting Normal Latent Space for Anomaly Detection with Normal-only Training Data
During test time, since AE is not trained using real anomalies, it is expected to poorly reconstruct the anomalous data.
LAA-Net: Localized Artifact Attention Network for High-Quality Deepfakes Detection
Second, an Enhanced Feature Pyramid Network (E-FPN) is proposed as a simple and effective mechanism for spreading discriminative low-level features into the final feature output, with the advantage of limiting redundancy.
PseudoBound: Limiting the anomaly reconstruction capability of one-class classifiers using pseudo anomalies
Typically in OCC, an autoencoder (AE) is trained to reconstruct the normal only training data with the expectation that, in test time, it can poorly reconstruct the anomalous data.
Stabilizing Adversarially Learned One-Class Novelty Detection Using Pseudo Anomalies
In the current study, we propose a robust anomaly detection framework that overcomes such instability by transforming the fundamental role of the discriminator from identifying real vs. fake data to distinguishing good vs. bad quality reconstructions.
Clustering Aided Weakly Supervised Training to Detect Anomalous Events in Surveillance Videos
Formulating learning systems for the detection of real-world anomalous events using only video-level labels is a challenging task mainly due to the presence of noisy labels as well as the rare occurrence of anomalous events in the training data.
Learning Not to Reconstruct Anomalies
Typically, to tackle this problem, an autoencoder (AE) is trained to reconstruct the input with training set consisting only of normal data.
Ranked #19 on
Anomaly Detection
on CUHK Avenue
Synthetic Temporal Anomaly Guided End-to-End Video Anomaly Detection
A popular way to tackle this problem is by utilizing an autoencoder (AE) trained only on normal data.
Deep Visual Anomaly detection with Negative Learning
However, these are trained with only normal data and at the test time, given abnormal data as input, may often generate normal-looking output.
Cleaning Label Noise with Clusters for Minimally Supervised Anomaly Detection
Learning to detect real-world anomalous events using video-level annotations is a difficult task mainly because of the noise present in labels.
CLAWS: Clustering Assisted Weakly Supervised Learning with Normalcy Suppression for Anomalous Event Detection
The proposed method obtains83. 03% and 89. 67% frame-level AUC performance on the UCF Crime and ShanghaiTech datasets respectively, demonstrating its superiority over the existing state-of-the-art algorithms.
SmoothMix: A Simple Yet Effective Data Augmentation to Train Robust Classifiers
Data augmentation has been proven effective which, by preventing overfitting, can not only enhances the performance of a deep neural network but also leads to a better generalization even with limited dataset.
Old is Gold: Redefining the Adversarially Learned One-Class Classifier Training Paradigm
Another possible approach is to use both generator and discriminator for anomaly detection.
Ranked #1 on
Anomaly Detection
on MNIST-test
Small Object Detection using Context and Attention
We propose an object detection method using context for improving accuracy of detecting small objects.
Rank Selection of CP-decomposed Convolutional Layers with Variational Bayesian Matrix Factorization
One of the method to compress CNNs is compressing the layers iteratively, i. e. by layer-by-layer compression and fine-tuning, with CP-decomposition in convolutional layers.
CP-decomposition with Tensor Power Method for Convolutional Neural Networks Compression
Convolutional Neural Networks (CNNs) has shown a great success in many areas including complex image classification tasks.
