Related papers: REQ-YOLO: A Resource-Aware, Efficient Quantization…

The deployment of deep neural networks on resource-constrained devices necessitates effective model com- pression strategies that judiciously balance the reduction of model size with the preservation of performance. This study introduces a…

Autonomous driving has harsh requirements of small model size and energy efficiency, in order to enable the embedded system to achieve real-time on-board object detection. Recent deep convolutional neural network based object detectors have…

Deploying deep learning models on embedded systems has been challenging due to limited computing resources. The majority of existing work focuses on accelerating image classification, while other fundamental vision problems, such as object…

Model quantization is a widely used technique to compress and accelerate deep neural network (DNN) inference. Emergent DNN hardware accelerators begin to support mixed precision (1-8 bits) to further improve the computation efficiency,…

Deep Neural Networks (DNNs) typically require massive amount of computation resource in inference tasks for computer vision applications. Quantization can significantly reduce DNN computation and storage by decreasing the bitwidth of…

In recent years Deep Neural Networks (DNNs) have been rapidly developed in various applications, together with increasingly complex architectures. The performance gain of these DNNs generally comes with high computational costs and large…

Demand for efficient onboard object detection is increasing due to its key role in autonomous navigation. However, deploying object detection models such as YOLO on resource constrained edge devices is challenging due to the high…

As it requires a huge number of parameters when exposed to high dimensional inputs in video detection and classification, there is a grand challenge to develop a compact yet accurate video comprehension at terminal devices. Current works…

Object detection in civil engineering applications is constrained by limited annotated data in specialized domains. We introduce DINO-YOLO, a hybrid architecture combining YOLOv12 with DINOv3 self-supervised vision transformers for…

Region-based Convolutional Neural Networks (R-CNNs) have achieved great success in the field of object detection. The existing R-CNNs usually divide a Region-of-Interest (ROI) into grids, and then localize objects by utilizing the spatial…

Most neural network quantization methods apply uniform bit precision across spatial regions, disregarding the heterogeneous complexity inherent in visual data. This paper introduces MCAQ-YOLO, a practical framework for tile-wise spatial…

Low-bit quantization of network weights and activations can drastically reduce the memory footprint, complexity, energy consumption and latency of Deep Neural Networks (DNNs). However, low-bit quantization can also cause a considerable drop…

Due to object detection's close relationship with video analysis and image understanding, it has attracted much research attention in recent years. Traditional object detection methods are built on handcrafted features and shallow trainable…

We introduce Hyper-YOLO, a new object detection method that integrates hypergraph computations to capture the complex high-order correlations among visual features. Traditional YOLO models, while powerful, have limitations in their neck…

Surface defect detection in industrial scenarios is both crucial and technically demanding due to the wide variability in defect types, irregular shapes and sizes, fine-grained requirements, and complex material textures. Although recent…

Post-training quantization (PTQ) is crucial for deploying efficient object detection models, like YOLO, on resource-constrained devices. However, the impact of reduced precision on model robustness to real-world input degradations such as…

Combinatorial optimization (CO) aims to efficiently find the best solution to NP-hard problems ranging from statistical physics to social media marketing. A wide range of CO applications can benefit from local search methods because they…

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…

DQN (Deep Q-Network) is a method to perform Q-learning for reinforcement learning using deep neural networks. DQNs require a large buffer and batch processing for an experience replay and rely on a backpropagation based iterative…

Recent years have seen impressive progress in visual recognition on many benchmarks, however, generalization to the real-world in out-of-distribution setting remains a significant challenge. A state-of-the-art method for robust visual…