Related papers: Knowledge Distillation for Feature Extraction in U…
Detecting 3D objects from multi-view images is a fundamental problem in 3D computer vision. Recently, significant breakthrough has been made in multi-view 3D detection tasks. However, the unprecedented detection performance of these vision…
We present DistillFlow, a knowledge distillation approach to learning optical flow. DistillFlow trains multiple teacher models and a student model, where challenging transformations are applied to the input of the student model to generate…
Visual Simultaneous Localization and Mapping (vSLAM) is a widely used technique in robotics and computer vision that enables a robot to create a map of an unfamiliar environment using a camera sensor while simultaneously tracking its…
Both accuracy and efficiency are of significant importance to the task of semantic segmentation. Existing deep FCNs suffer from heavy computations due to a series of high-resolution feature maps for preserving the detailed knowledge in…
Owing to refraction, absorption, and scattering of light by suspended particles in water, raw underwater images suffer from low contrast, blurred details, and color distortion. These characteristics can significantly interfere with the…
Underwater diving assistance and safety support robots acquire real-time diver information through onboard underwater cameras. This study introduces a breath bubble detection algorithm that utilizes unsupervised K-means clustering, thereby…
Researchers have long tried to minimize training costs in deep learning while maintaining strong generalization across diverse datasets. Emerging research on dataset distillation aims to reduce training costs by creating a small synthetic…
Autonomous Underwater Vehicles (AUVs) and Remotely Operated Vehicles (ROVs) demand robust spatial perception capabilities, including Simultaneous Localization and Mapping (SLAM), to support both remote and autonomous tasks. Vision-based…
Background: Underwater images, in general, suffer from low contrast and high color distortions due to the non-uniform attenuation of the light as it propagates through the water. In addition, the degree of attenuation varies with the…
Classic vision-based navigation solutions, which are utilized in algorithms such as Simultaneous Localization and Mapping (SLAM), usually fail to work underwater when the water is murky and the quality of the recorded images is low. That is…
In recent years, coordinate-based neural implicit representations have shown promising results for the task of Simultaneous Localization and Mapping (SLAM). While achieving impressive performance on small synthetic scenes, these methods…
The recent success of pre-trained 2D vision models is mostly attributable to learning from large-scale datasets. However, compared with 2D image datasets, the current pre-training data of 3D point cloud is limited. To overcome this…
Surface defect detection is one of the most essential processes for industrial quality inspection. Deep learning-based surface defect detection methods have shown great potential. However, the well-performed models usually require large…
Color correction for underwater images has received increasing interests, due to its critical role in facilitating available mature vision algorithms for underwater scenarios. Inspired by the stunning success of deep convolutional neural…
Feature maps contain rich information about image intensity and spatial correlation. However, previous online knowledge distillation methods only utilize the class probabilities. Thus in this paper, we propose an online knowledge…
The purpose of this paper is to explore the use of underwater image enhancement techniques to improve keypoint detection and matching. By applying advanced deep learning models, including generative adversarial networks and convolutional…
Underwater image suffer from color cast, low contrast and hazy effect due to light absorption, refraction and scattering, which degraded the high-level application, e.g, object detection and object tracking. Recent learning-based methods…
As a promising approach in model compression, knowledge distillation improves the performance of a compact model by transferring the knowledge from a cumbersome one. The kind of knowledge used to guide the training of the student is…
Knowledge distillation is an effective method for training small and efficient deep learning models. However, the efficacy of a single method can degenerate when transferring to other tasks, modalities, or even other architectures. To…
Robust object recognition systems usually rely on powerful feature extraction mechanisms from a large number of real images. However, in many realistic applications, collecting sufficient images for ever-growing new classes is unattainable.…