相关论文: Squeezed Deep 6DoF Object Detection Using Knowledg…

The task of 6DoF object pose estimation is one of the fundamental problems of 3D vision with many practical applications such as industrial automation. Traditional deep learning approaches for this task often require extensive training data…

This paper tackles the problem of semi-supervised video object segmentation on resource-constrained devices, such as mobile phones. We formulate this problem as a distillation task, whereby we demonstrate that small space-time-memory…

We present a learning-based method for 6 DoF pose estimation of rigid objects in point cloud data. Many recent learning-based approaches use primarily RGB information for detecting objects, in some cases with an added refinement step using…

Defocus Blur Detection(DBD) aims to separate in-focus and out-of-focus regions from a single image pixel-wisely. This task has been paid much attention since bokeh effects are widely used in digital cameras and smartphone photography.…

Motivated by the stringent requirements of unstructured real-world where a plethora of unknown objects reside in arbitrary locations of the surface, we propose a voxel-based deep 3D Convolutional Neural Network (3D CNN) that generates…

In a real-world setting, object instances from new classes can be continuously encountered by object detectors. When existing object detectors are applied to such scenarios, their performance on old classes deteriorates significantly. A few…

Deep convolutional neural networks (CNN) has become the most promising method for object recognition, repeatedly demonstrating record breaking results for image classification and object detection in recent years. However, a very deep CNN…

In the era of AI at the edge, self-driving cars, and climate change, the need for energy-efficient, small, embedded AI is growing. Spiking Neural Networks (SNNs) are a promising approach to address this challenge, with their event-driven…

In the past few years, transformers have achieved promising performances on various computer vision tasks. Unfortunately, the immense inference overhead of most existing vision transformers withholds their from being deployed on edge…

Real-time visual localization often utilizes online computing, for which query images or videos are transmitted to remote servers for visual place recognition (VPR). However, limited network bandwidth necessitates image-quality reduction…

Single-domain generalization is essential for object detection, particularly when training models on a single source domain and evaluating them on unseen target domains. Domain shifts, such as changes in weather, lighting, or scene…

The goal of this work is to replace objects in an RGB-D scene with corresponding 3D models from a library. We approach this problem by first detecting and segmenting object instances in the scene using the approach from Gupta et al. [13].…

Knowledge distillation which learns a lightweight student model by distilling knowledge from a cumbersome teacher model is an attractive approach for learning compact deep neural networks (DNNs). Recent works further improve student network…

Deep learning networks have achieved state-of-the-art accuracies on computer vision workloads like image classification and object detection. The performant systems, however, typically involve big models with numerous parameters. Once…

The existing solutions for object detection distillation rely on the availability of both a teacher model and ground-truth labels. We propose a new perspective to relax this constraint. In our framework, a student is first trained with…

Deep neural networks based methods have been proved to achieve outstanding performance on object detection and classification tasks. Despite significant performance improvement, due to the deep structures, they still require prohibitive…

Deep convolutional Neural Networks (CNN) are the state-of-the-art performers for object detection task. It is well known that object detection requires more computation and memory than image classification. Thus the consolidation of a…

Knowledge distillation is a widely adopted technique for model lightening. However, the performance of most knowledge distillation methods in the domain of object detection is not satisfactory. Typically, knowledge distillation approaches…

Image matching and classification methods, as well as synchronous location and mapping, are widely used on embedded and mobile devices. Their most resource-intensive part is the detection and description of the key points of the images. And…

Detecting objects and their 6D poses from only RGB images is an important task for many robotic applications. While deep learning methods have made significant progress in visual object detection and segmentation, the object pose estimation…