Computer Vision
Making images unlearnable through imperceptible perturbations is to prevent unauthorized image scraping from training deep neural networks (DNNs). Most existing methods for breaking these unlearnable data focus on applying image transformation techniques to disrupt the added perturbations, with limited attention given to modifying the classification tasks (target classes) of DNNs as an alternative approach. In this paper, we explore the vulnerabilities of unlearnable data, focusing mainly on modifying the classification tasks rather than applying image transformation techniques.
- Categories:
10 Views
Digital microfluidics are a unique technique for operation of nano-to-micro liter droplets based on electrowetting on dielectric. It has great application potential in the field on clinic diagnosis, life science and environment monitoring. Due to the fast droplet moving speed and high degree of freedom for droplet manipulation, it is urgent to develop automated and intelligent approaches for droplet monitoring and control.
- Categories:
18 Views
Introduction
Welcome to the new challenging event-based multi-object tracking dataset (DSEC-MOT) repository. Our goal is to provide a challenging and diverse event-based MOT dataset with various real-world scenarios to facilitate the objective and comphrehensive evaluation of event-based multi-object tracking algorithms. This dataset, built upon DSEC, contains a variety of traffic entities and complex scenarios, aiming to address the current lack of event-based MOT datasets.
- Categories:
38 Views
This study utilizes the open-source datasets FAIR1M and HRSC2016 as foundational resources to construct an optical remote sensing image dataset for rotated ship target detection. The dataset encompasses nine ship categories: Dry-Cargo-Ship, Engineering-Ship, Fishing-Boat, Motorboat, Tugboat, Passenger-Ship, Warship, Liquid-Cargo-Ship, and Other-Ship.
- Categories:
22 Views
Attached Image data set from combined OCT-SLO is used to train AI models and identify features to maximize quality of data set to adjust MZI reference arm, PMT Voltage of Liquid Lens and location of object. Why adjustment is needed is explained below:
- Categories:
140 Views
The NEU-DET dataset is a set of images characterized by surface defects on hot rolled steel strip. These defects are classified into six categories: cracks (cr), inclusions (in), patches (pa), pitted surfaces (ps), rolled scales (rs) and scratches (sc). The dataset contains 300 grayscale images for each category, for a total of 1800 images, each of which is 200×200 pixels in size.
- Categories:
27 Views
The painting style data sets were constructed by searching, selecting and collecting the public painting works on the internet, treating the painting style and artists' names as keywords. The data set collected 750 painting works in all, including five kinds of styles. They were receptively Cubism, Op Art, Color Field Painting, Post Impressionism and Rococo.
- Categories:
13 Views
This is a subset of the underwater video-level multi-task learning dataset UVMulti that we created for the paper submission. The complete dataset will be released when the paper is accepted. The file sequence represents the original video sequence, sequence_enh represents the corresponding underwater image enhancement annotation, mask represents the corresponding semantic segmentation annotation, depth represents the sparse depth annotation, and dense_depth represents the dense depth annotation.
- Categories:
26 Views
ElecsDataset is a specialized 3D semantic segmentation dataset designed for substation environments. It addresses the shortage of domain-specific annotated data in the field of substation 3D semantic segmentation. This dataset offers high-resolution, meticulously annotated point clouds that capture complex equipment structures and real-world occlusions. It consists of data collected from three substations of varying scales. The dataset is systematically partitioned into 6 distinct spatial regions with heterogeneous dimensions.
- Categories:
120 ViewsElecsDataset is a specialized 3D semantic segmentation dataset designed for substation environments. It addresses the shortage of domain-specific annotated data in the field of substation 3D semantic segmentation. This dataset offers high-resolution, meticulously annotated point clouds that capture complex equipment structures and real-world occlusions. It consists of data collected from three substations of varying scales. The dataset is systematically partitioned into 6 distinct spatial regions with heterogeneous dimensions.
- Categories:
Views