Search Results for author:
Found 51 papers, 19 papers with code
Crane: Context-Guided Prompt Learning and Attention Refinement for Zero-Shot Anomaly Detections
Anomaly Detection (AD) involves identifying deviations from normal data distributions and is critical in fields such as medical diagnostics and industrial defect detection.
Scanning Trojaned Models Using Out-of-Distribution Samples
TRODO leverages the concept of "blind spots"--regions where trojaned classifiers erroneously identify out-of-distribution (OOD) samples as in-distribution (ID).
A Contrastive Teacher-Student Framework for Novelty Detection under Style Shifts
There have been several efforts to improve Novelty Detection (ND) performance.
Mitigating Spurious Negative Pairs for Robust Industrial Anomaly Detection
Then, we demonstrate that adversarial training with contrastive loss could serve as an ideal objective function, as it creates both inter- and intra-group perturbations.
Killing it with Zero-Shot: Adversarially Robust Novelty Detection
By incorporating robust pretrained features into the k-NN algorithm, we establish a new standard for performance and robustness in the field of robust ND.
Leveraging Graph-RAG and Prompt Engineering to Enhance LLM-Based Automated Requirement Traceability and Compliance Checks
Ensuring that Software Requirements Specifications (SRS) align with higher-level organizational or national requirements is vital, particularly in regulated environments such as finance and aerospace.
Continual Learning: Less Forgetting, More OOD Generalization via Adaptive Contrastive Replay
In this paper, we highlight this issue and propose a simple yet effective strategy inspired by contrastive learning and data-centric principles to address it.
Universal Novelty Detection Through Adaptive Contrastive Learning
More precisely, for novelty detection, distribution shifts may occur in the training set or the test set.
Enhancing Anomaly Detection Generalization through Knowledge Exposure: The Dual Effects of Augmentation
Despite advancements in these benchmarks, contemporary anomaly detection methods often struggle with out-of-distribution generalization, particularly in classifying samples with subtle transformations during testing.
Class-Adaptive Sampling Policy for Efficient Continual Learning
Continual learning (CL) aims to acquire new knowledge while preserving information from previous experiences without forgetting.
Explainability of Vision Transformers: A Comprehensive Review and New Perspectives
Transformers have had a significant impact on natural language processing and have recently demonstrated their potential in computer vision.
Mitigating Bias: Enhancing Image Classification by Improving Model Explanations
In this paper, we propose a novel approach to address this issue and improve the learning of main concepts by image classifiers.
Adversarial Backdoor Attack by Naturalistic Data Poisoning on Trajectory Prediction in Autonomous Driving
In autonomous driving, behavior prediction is fundamental for safe motion planning, hence the security and robustness of prediction models against adversarial attacks are of paramount importance.
Global-Local Processing in Convolutional Neural Networks
We devise a simple module called Global Advantage Stream (GAS) to learn and capture the holistic features of input samples (i. e., the global features).
Revealing Model Biases: Assessing Deep Neural Networks via Recovered Sample Analysis
While a generalization test is one way to evaluate a trained model's performance, it can be costly and may not cover all scenarios to ensure that the model has learned the primary concepts.
A Unified Concept-Based System for Local, Global, and Misclassification Explanations
Explainability of Deep Neural Networks (DNNs) has been garnering increasing attention in recent years.
Quantifying Overfitting: Evaluating Neural Network Performance through Analysis of Null Space
To achieve this, we analyze the null space in the last layer of neural networks, which enables us to quantify overfitting without access to training data or knowledge of the accuracy of those data.
Towards Realistic Out-of-Distribution Detection: A Novel Evaluation Framework for Improving Generalization in OOD Detection
This paper presents a novel evaluation framework for Out-of-Distribution (OOD) detection that aims to assess the performance of machine learning models in more realistic settings.
Out-of-Distribution Detection
Out of Distribution (OOD) Detection
MobileDenseNet: A new approach to object detection on mobile devices
We also developed a light neck FCPNLite for mobile devices that will aid with the detection of small objects.
Fake It Till You Make It: Towards Accurate Near-Distribution Novelty Detection
Effectiveness of our method for both the near-distribution and standard novelty detection is assessed through extensive experiments on datasets in diverse applications such as medical images, object classification, and quality control.
Ranked #3 on
Anomaly Detection
on One-class CIFAR-10
(using extra training data)
Deep-Disaster: Unsupervised Disaster Detection and Localization Using Visual Data
In this paper, inspired by the success of Knowledge Distillation (KD) methods, we propose an unsupervised deep neural network to detect and localize damages in social media images.
All You Need In Sign Language Production
To make an easy and mutual communication between the hearing-impaired and the hearing communities, building a robust system capable of translating the spoken language into sign language and vice versa is fundamental.
A Unified Survey on Anomaly, Novelty, Open-Set, and Out-of-Distribution Detection: Solutions and Future Challenges
To date, several research domains tackle the problem of detecting unfamiliar samples, including anomaly detection, novelty detection, one-class learning, open set recognition, and out-of-distribution detection.
Looking Back on Learned Experiences For Class/task Incremental Learning
In this paper, we shed light on an on-call transfer set to provide past experiences whenever a new task arises in the data stream.
Multi-Modal Zero-Shot Sign Language Recognition
Zero-Shot Learning (ZSL) has rapidly advanced in recent years.
ClaRe: Practical Class Incremental Learning By Remembering Previous Class Representations
Learning new knowledge in the absence of data instances from previous classes or even imbalance samples of both old and new classes makes CIL an ongoing challenging problem.
Sign Language Production: A Review
Sign Language is the dominant yet non-primary form of communication language used in the deaf and hearing-impaired community.
ZS-IL: Looking Back on Learned ExperiencesFor Zero-Shot Incremental Learning
In this paper, we shed light on an on-call transfer set to provide past experiences whenever a new class arises in the data stream.
Ano-Graph: Learning Normal Scene Contextual Graphs to Detect Video Anomalies
Video anomaly detection has proved to be a challenging task owing to its unsupervised training procedure and high spatio-temporal complexity existing in real-world scenarios.
Image/Video Deep Anomaly Detection: A Survey
AD strongly correlates with the important computer vision and image processing tasks such as image/video anomaly, irregularity and sudden event detection.
Robustification of Segmentation Models Against Adversarial Perturbations In Medical Imaging
This paper presents a novel yet efficient defense framework for segmentation models against adversarial attacks in medical imaging.
G2D: Generate to Detect Anomaly
Previous researches solve this problem as a One-Class Classification (OCC) task where they train a reference model on all of the available samples.
Deep-HR: Fast Heart Rate Estimation from Face Video Under Realistic Conditions
In this paper, we propose a simple yet efficient approach to benefit the advantages of the Deep Neural Network (DNN) by simplifying HR estimation from a complex task to learning from very correlated representation to HR.
Code-Bridged Classifier (CBC): A Low or Negative Overhead Defense for Making a CNN Classifier Robust Against Adversarial Attacks
In this paper, we propose Code-Bridged Classifier (CBC), a framework for making a Convolutional Neural Network (CNNs) robust against adversarial attacks without increasing or even by decreasing the overall models' computational complexity.
AutoIDS: Auto-encoder Based Method for Intrusion Detection System
These detectors are two encoder-decoder neural networks that are forced to provide a compressed and a sparse representation from the normal flows.
Self-Supervised Representation Learning via Neighborhood-Relational Encoding
Conventional unsupervised learning methods only focused on training deep networks to understand the primitive characteristics of the visual data, mainly to be able to reconstruct the data from a latent space.
AVD: Adversarial Video Distillation
The key idea is to represent videos by compressing them in the form of realistic images, which can be used in a variety of video-based scene analysis applications.
End-to-End Adversarial Learning for Intrusion Detection in Computer Networks
Inspired by the successes of Generative Adversarial Networks (GANs) for training deep models in semi-unsupervised setting, we have proposed an end-to-end deep architecture for IDS.
Online Signature Verification using Deep Representation: A new Descriptor
To deal with these difficulties and modeling the signatures efficiently, we propose a method that a one-class classifier per each user is built on discriminative features.
Semantic Video Segmentation: A Review on Recent Approaches
This paper gives an overview on semantic segmentation consists of an explanation of this field, it's status and relation with other vision fundamental tasks, different datasets and common evaluation parameters that have been used by researchers.
AVID: Adversarial Visual Irregularity Detection
Real-time detection of irregularities in visual data is very invaluable and useful in many prospective applications including surveillance, patient monitoring systems, etc.
Adversarially Learned One-Class Classifier for Novelty Detection
Our architecture is composed of two deep networks, each of which trained by competing with each other while collaborating to understand the underlying concept in the target class, and then classify the testing samples.
Towards Principled Design of Deep Convolutional Networks: Introducing SimpNet
SimpNet outperforms the deeper and more complex architectures such as VGGNet, ResNet, WideResidualNet \etc, on several well-known benchmarks, while having 2 to 25 times fewer number of parameters and operations.
Ranked #118 on
Image Classification
on CIFAR-10
Deep-Anomaly: Fully Convolutional Neural Network for Fast Anomaly Detection in Crowded Scenes
The detection of abnormal behaviours in crowded scenes has to deal with many challenges.
Lets keep it simple, Using simple architectures to outperform deeper and more complex architectures
Our simple 13-layer architecture outperforms most of the deeper and complex architectures to date such as VGGNet, ResNet, and GoogleNet on several well-known benchmarks while having 2 to 25 times fewer number of parameters and operations.
Ranked #11 on
Image Classification
on MNIST
STFCN: Spatio-Temporal FCN for Semantic Video Segmentation
Current work on convolutional neural networks(CNNs) has shown that CNNs provide advanced spatial features supporting a very good performance of solutions for both image and video analysis, especially for the semantic segmentation task.
Real-Time Anomaly Detection and Localization in Crowded Scenes
In this paper, we propose a method for real-time anomaly detection and localization in crowded scenes.
Real-Time Anomalous Behavior Detection and Localization in Crowded Scenes
We propose a fusion strategy to combine the two descriptors as the output of our system.
A Novel Approach For Finger Vein Verification Based on Self-Taught Learning
In this paper, we propose a method for user Finger Vein Authentication (FVA) as a biometric system.
IDSA: Intelligent Distributed Sensor Activation Algorithm For Target Tracking With Wireless Sensor Network
One important application of the Wireless Sensor Network(WSN) is target tracking, the aim of this application is converging to an event or object in an area.
Feature Representation for Online Signature Verification
Biometrics systems have been used in a wide range of applications and have improved people authentication.
