相关论文: Creating Lightweight Object Detectors with Model C…

Object detection is a major challenge in computer vision, involving both object classification and object localization within a scene. While deep neural networks have been shown in recent years to yield very powerful techniques for tackling…

Despite the recent success of video object detection on Desktop GPUs, its architecture is still far too heavy for mobiles. It is also unclear whether the key principles of sparse feature propagation and multi-frame feature aggregation apply…

It is usually infeasible to fit and train an entire large deep neural network (DNN) model using a single edge device due to the limited resources. To facilitate intelligent applications across edge devices, researchers have proposed…

We propose an object detection method that improves the accuracy of the conventional SSD (Single Shot Multibox Detector), which is one of the top object detection algorithms in both aspects of accuracy and speed. The performance of a deep…

Camouflaged Object Detection (COD) aims to detect objects with similar patterns (e.g., texture, intensity, colour, etc) to their surroundings, and recently has attracted growing research interest. As camouflaged objects often present very…

Recent advances in Artificial Intelligence (AI) on the Internet of Things (IoT)-enabled network edge has realized edge intelligence in several applications such as smart agriculture, smart hospitals, and smart factories by enabling…

This paper presents a novel method of landslide detection by exploiting the Mask R-CNN capability of identifying an object layout by using a pixel-based segmentation, along with transfer learning used to train the proposed model. A data set…

Small targets are particularly difficult to detect due to their low pixel count, complex backgrounds, and varying shooting angles, which make it hard for models to extract effective features. While some large-scale models offer high…

We present a filter pruning approach for deep model compression, using a multitask network. Our approach is based on learning a a pruner network to prune a pre-trained target network. The pruner is essentially a multitask deep neural…

Compression of a neural network can help in speeding up both the training and the inference of the network. In this research, we study applying compression using low rank decomposition on network layers. Our research demonstrates that to…

As one of the basic tasks of computer vision, object detection has been widely used in many intelligent applications. However, object detection algorithms are usually heavyweight in computation, hindering their implementations on…

We present an improved version of PointRCNN for 3D object detection, in which a multi-branch backbone network is adopted to handle the non-uniform density of point clouds. An uncertainty-based sampling policy is proposed to deal with the…

Compressing neural networks without retraining is vital for deployment at scale. We study calibration-free compression through the lens of projection geometry: structured pruning is an axis-aligned projection, whereas model folding performs…

Previous research in $2D$ object detection focuses on various tasks, including detecting objects in generic and camouflaged images. These works are regarded as passive works for object detection as they take the input image as is. However,…

Achieving a balance between computational efficiency and detection accuracy in the realm of rotated bounding box object detection within aerial imagery is a significant challenge. While prior research has aimed at creating lightweight…

Training and deploying deepfake detection models on edge devices offers the advantage of maintaining data privacy and confidentiality by processing it close to its source. However, this approach is constrained by the limited computational…

Besides accuracy, the model size of convolutional neural networks (CNN) models is another important factor considering limited hardware resources in practical applications. For example, employing deep neural networks on mobile systems…

Deploying object detection on microcontrollers (MCUs) enables intelligent edge devices but current models cannot learn new object categories after deployment. Existing continual learning methods require storing raw images far exceeding MCU…

Salient object detection models often demand a considerable amount of computation cost to make precise prediction for each pixel, making them hardly applicable on low-power devices. In this paper, we aim to relieve the contradiction between…

We present a novel approach for oriented object detection, named TricubeNet, which localizes oriented objects using visual cues ($i.e.,$ heatmap) instead of oriented box offsets regression. We represent each object as a 2D Tricube kernel…