Related papers: Unsupervised Pixel-level Road Defect Detection via…
Defect detection in the manufacturing industry is of utmost importance for product quality inspection. Recently, optical defect detection has been investigated as an anomaly detection using different deep learning methods. However, the…
Graph contrastive learning is the state-of-the-art unsupervised graph representation learning framework and has shown comparable performance with supervised approaches. However, evaluating whether the graph contrastive learning is robust to…
Previous advances in object tracking mostly reported on favorable illumination circumstances while neglecting performance at nighttime, which significantly impeded the development of related aerial robot applications. This work instead…
We propose a completely unsupervised pixel-wise anomaly detection method for hyperspectral images. The proposed method consists of three steps called data preparation, reconstruction, and detection. In the data preparation step, we apply a…
As the Internet grows in popularity, more and more classification jobs, such as IoT, finance industry and healthcare field, rely on mobile edge computing to advance machine learning. In the medical industry, however, good diagnostic…
Training an object detector on a data-rich domain and applying it to a data-poor one with limited performance drop is highly attractive in industry, because it saves huge annotation cost. Recent research on unsupervised domain adaptive…
Automated fiber placement (AFP) is an advanced manufacturing technology that increases the rate of production of composite materials. At the same time, the need for adaptable and fast inline control methods of such parts raises. Existing…
We propose a novel end-to-end semi-supervised adversarial framework to generate photorealistic face images of new identities with wide ranges of expressions, poses, and illuminations conditioned by a 3D morphable model. Previous adversarial…
This paper introduces LAFT, a novel feature transformation method designed to incorporate user knowledge and preferences into anomaly detection using natural language. Accurately modeling the boundary of normality is crucial for…
Current approaches of Reinforcement Learning (RL) applied in urban Autonomous Driving (AD) focus on decoupling the perception training from the driving policy training. The main reason is to avoid training a convolution encoder alongside a…
Recent AI-generated image (AIGI) detectors achieve impressive accuracy under clean condition. In view of antiforensics, it is significant to develop advanced adversarial attacks for evaluating the security of such detectors, which remains…
Neural networks have revolutionized various domains, exhibiting remarkable accuracy in tasks like natural language processing and computer vision. However, their vulnerability to slight alterations in input samples poses challenges,…
Autonomous driving is the key technology of intelligent logistics in Industrial Internet of Things (IIoT). In autonomous driving, the appearance of incomplete point clouds losing geometric and semantic information is inevitable owing to…
The long-tailed distribution is a common phenomenon in the real world. Extracted large scale image datasets inevitably demonstrate the long-tailed property and models trained with imbalanced data can obtain high performance for the…
It's useful to automatically transform an image from its original form to some synthetic form (style, partial contents, etc.), while keeping the original structure or semantics. We define this requirement as the "image-to-image translation"…
Bias in classifiers is a severe issue of modern deep learning methods, especially for their application in safety- and security-critical areas. Often, the bias of a classifier is a direct consequence of a bias in the training dataset,…
Estimating correspondences between pairs of non-rigid deformable 3D shapes remains a significant challenge in computer vision and graphics. While deep functional map methods have become the go-to solution for addressing this problem, they…
Deep learning-based image fusion approaches have obtained wide attention in recent years, achieving promising performance in terms of visual perception. However, the fusion module in the current deep learning-based methods suffers from two…
Local feature extraction is a standard approach in computer vision for tackling important tasks such as image matching and retrieval. The core assumption of most methods is that images undergo affine transformations, disregarding more…
The existing generative adversarial fusion methods generally concatenate source images and extract local features through convolution operation, without considering their global characteristics, which tends to produce an unbalanced result…