Related papers: YOLO-Master: MOE-Accelerated with Specialized Tran…

Aiming at the problems of missed detection, false detection and low detection efficiency in transmission line foreign object detection under railway environment, we proposed an improved algorithm MRS-YOLO based on YOLO11. Firstly, a…

One-stage object detection, particularly the YOLO series, strikes a favorable balance between accuracy and efficiency. However, existing YOLO detectors lack explicit modeling of heterogeneous object responses within shared feature channels,…

Ensuring safety in both autonomous driving and advanced driver-assistance systems (ADAS) depends critically on the efficient deployment of traffic sign recognition technology. While current methods show effectiveness, they often compromise…

Object detection is an important topic in computer vision, with post-processing, an essential part of the typical object detection pipeline, posing a significant bottleneck affecting the performance of traditional object detection models.…

Within the field of robotics, computer vision remains a significant barrier to progress, with many tasks hindered by inefficient vision systems. This research proposes a generalized vision module leveraging YOLOv9, a state-of-the-art…

Mixture-of-Experts (MoE) models scale large language models efficiently by sparsely activating experts, but once an expert is selected, it is executed fully. Hence, the trade-off between accuracy and computation in an MoE model typically…

Despite the rapid advancement of object detection algorithms, processing high-resolution images on embedded devices remains a significant challenge. Theoretically, the fully convolutional network architecture used in current real-time…

Mirrors can degrade the performance of computer vision models, but research into detecting them is in the preliminary phase. YOLOv4 achieves phenomenal results in terms of object detection accuracy and speed, but it still fails in detecting…

The proliferation of large language models (LLMs) has led to the adoption of Mixture-of-Experts (MoE) architectures that dynamically leverage specialized subnetworks for improved efficiency and performance. Despite their benefits, MoE…

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…

The sparsely activated mixture of experts (MoE) model presents a promising alternative to traditional densely activated (dense) models, enhancing both quality and computational efficiency. However, training MoE models from scratch demands…

Mixture-of-Experts (MoE) architectures are widely used in modern large language models and multimodal models. However, inference efficiency is often limited by highly dynamic and skewed expert workloads across different modalities. During…

The You Only Look Once (YOLO) series of detectors have established themselves as efficient and practical tools. However, their reliance on predefined and trained object categories limits their applicability in open scenarios. Addressing…

Existing detection methods for insulator defect identification from unmanned aerial vehicles (UAV) struggle with complex background scenes and small objects, leading to suboptimal accuracy and a high number of false positives detection.…

Accurate vehicle detection is essential for the development of intelligent transportation systems, autonomous driving, and traffic monitoring. This paper presents a detailed analysis of YOLO11, the latest advancement in the YOLO series of…

We introduce YOLO-pose, a novel heatmap-free approach for joint detection, and 2D multi-person pose estimation in an image based on the popular YOLO object detection framework. Existing heatmap based two-stage approaches are sub-optimal as…

Semi-Supervised Object Detection (SSOD) has been successful in improving the performance of both R-CNN series and anchor-free detectors. However, one-stage anchor-based detectors lack the structure to generate high-quality or flexible…

Efficient and accurate annotation of datasets remains a significant challenge for deploying object detection models such as You Only Look Once (YOLO) in real-world applications, particularly in agriculture where rapid decision-making is…

Drone-based target detection presents inherent challenges, such as the high density and overlap of targets in drone-based images, as well as the blurriness of targets under varying lighting conditions, which complicates identification.…

Sparse Mixture-of-Experts (MoE) architectures have emerged as a promising approach to decoupling model capacity from computational cost. At the core of the MoE model is the router, which learns the underlying clustering structure of the…