Search Results for author:
Found 16 papers, 6 papers with code
Road Surface Defect Detection -- From Image-based to Non-image-based: A Survey
As a result, there has been a growing interest in the literature on the subject, leading to the development of various road surface defect detection methods.
Multi-class Road Defect Detection and Segmentation using Spatial and Channel-wise Attention for Autonomous Road Repairing
To demonstrate the effectiveness of our framework, we conducted various ablation studies and comparisons with prior methods on a newly collected dataset annotated with nine road defect classes.
Adversarial Denoising Diffusion Model for Unsupervised Anomaly Detection
With the addition of explicit adversarial learning on data samples, ADDM can learn the semantic characteristics of the data more robustly during training, which achieves a similar data sampling performance with much fewer sampling steps than DDPM.
Active anomaly detection based on deep one-class classification
In an active learning framework, a model queries samples to be labeled by experts and re-trains the model with the labeled data samples.
An Iterative Method for Unsupervised Robust Anomaly Detection Under Data Contamination
Therefore, it has been a common practice to learn normality under the assumption that anomalous data are absent in a training dataset, which we call normality assumption.
Unsupervised Deep One-Class Classification with Adaptive Threshold based on Training Dynamics
One-class classification has been a prevailing method in building deep anomaly detection models under the assumption that a dataset consisting of normal samples is available.
Normality-Calibrated Autoencoder for Unsupervised Anomaly Detection on Data Contamination
In this paper, we propose Normality-Calibrated Autoencoder (NCAE), which can boost anomaly detection performance on the contaminated datasets without any prior information or explicit abnormal samples in the training phase.
Camera-Tracklet-Aware Contrastive Learning for Unsupervised Vehicle Re-Identification
However, this achievement requires large-scale and well-annotated datasets.
Unsupervised Person Re-identification via Multi-Label Prediction and Classification based on Graph-Structural Insight
The proposed GSMLP and SMLC boost the performance of unsupervised person Re-ID without any pre-labelled dataset.
Unsupervised Vehicle Re-Identification via Self-supervised Metric Learning using Feature Dictionary
The results of DPLM are applied to dictionary-based triplet loss (DTL) to improve the discriminativeness of learnt features and to refine the quality of the results of DPLM progressively.
Context-Aware Multi-Task Learning for Traffic Scene Recognition in Autonomous Vehicles
Specifically, we present a lower bound for the mutual information constraint between shared feature embedding and input that is considered to be able to extract common contextual information across tasks while preserving essential information of each task jointly.
Predictively Encoded Graph Convolutional Network for Noise-Robust Skeleton-based Action Recognition
In this work, we propose a skeleton-based action recognition method which is robust to noise information of given skeleton features.
Unsupervised Pixel-level Road Defect Detection via Adversarial Image-to-Frequency Transform
To end this, we propose an unsupervised approach to detecting road defects, using Adversarial Image-to-Frequency Transform (AIFT).
Drivers Drowsiness Detection using Condition-Adaptive Representation Learning Framework
The proposed framework consists of four models: spatio-temporal representation learning, scene condition understanding, feature fusion, and drowsiness detection.
Boosting Mapping Functionality of Neural Networks via Latent Feature Generation based on Reversible Learning
This paper addresses a boosting method for mapping functionality of neural networks in visual recognition such as image classification and face recognition.
Boosting Network Weight Separability via Feed-Backward Reconstruction
To this end, we propose an evaluation metric for weight separability based on semi-orthogonality of a matrix and Frobenius distance, and the feed-backward reconstruction loss which explicitly encourages weight separability between the column vectors in the weight matrix.
