中文
相关论文

相关论文: Exploring Model Quantization in GenAI-based Image …

200 篇论文

Generative Artificial Intelligence (GenAI) features such as image editing, object removal, and prompt-guided image transformation are increasingly integrated into mobile applications. However, deploying Large Vision Models (LVMs) for such…

计算机视觉与模式识别 · 计算机科学 2026-04-01 Sowmya Vajrala , Aakash Parmar , Prasanna R , Sravanth Kodavanti , Manjunath Arveti , Srinivas Soumitri Miriyala , Ashok Senapati

Synthetic images are increasingly used to augment object-detection training sets, but reliably evaluating a synthetic dataset before training remains difficult: standard global generative metrics (e.g., FID) often do not predict downstream…

计算机视觉与模式识别 · 计算机科学 2026-02-24 Vasile Marian , Yong-Bin Kang , Alexander Buddery

Recent object detectors have achieved impressive accuracy in identifying objects seen during training. However, real-world deployment often introduces novel and unexpected objects, referred to as out-of-distribution (OOD) objects, posing…

In recent years, deep learning has vastly improved the identification and diagnosis of various diseases in plants. In this report, we investigate the problem of pathology classification using images of a single leaf. We explore the use of…

计算机视觉与模式识别 · 计算机科学 2020-12-02 Sedrick Scott Keh

For safety-critical applications such as autonomous driving, CNNs have to be robust with respect to unavoidable image corruptions, such as image noise. While previous works addressed the task of robust prediction in the context of…

计算机视觉与模式识别 · 计算机科学 2020-11-11 Christoph Kamann , Burkhard Güssefeld , Robin Hutmacher , Jan Hendrik Metzen , Carsten Rother

The number of leaves a plant has is one of the key traits (phenotypes) describing its development and growth. Here, we propose an automated, deep learning based approach for counting leaves in model rosette plants. While state-of-the-art…

计算机视觉与模式识别 · 计算机科学 2017-09-06 Andrei Dobrescu , Mario Valerio Giuffrida , Sotirios A Tsaftaris

Diffusion models have gained popularity for generating images from textual descriptions. Nonetheless, the substantial need for computational resources continues to present a noteworthy challenge, contributing to time-consuming processes.…

计算机视觉与模式识别 · 计算机科学 2023-11-30 Hanwen Chang , Haihao Shen , Yiyang Cai , Xinyu Ye , Zhenzhong Xu , Wenhua Cheng , Kaokao Lv , Weiwei Zhang , Yintong Lu , Heng Guo

Plant phenotyping refers to a quantitative description of the plants properties, however in image-based phenotyping analysis, our focus is primarily on the plants anatomical, ontogenetical and physiological properties.This technique…

计算机视觉与模式识别 · 计算机科学 2022-10-25 Petros N. Tamvakis , Chairi Kiourt , Alexandra D. Solomou , George Ioannakis , Nestoras C. Tsirliganis

Recent GAN-based image inpainting approaches adopt an average strategy to discriminate the generated image and output a scalar, which inevitably lose the position information of visual artifacts. Moreover, the adversarial loss and…

计算机视觉与模式识别 · 计算机科学 2020-11-18 Ruisong Zhang , Weize Quan , Baoyuan Wu , Zhifeng Li , Dong-Ming Yan

Precision agriculture relies heavily on effective weed management to ensure robust crop yields. This study presents RoWeeder, an innovative framework for unsupervised weed mapping that combines crop-row detection with a noise-resilient deep…

计算机视觉与模式识别 · 计算机科学 2024-10-10 Pasquale De Marinis , Gennaro Vessio , Giovanna Castellano

Early identification of drought stress in crops is vital for implementing effective mitigation measures and reducing yield loss. Non-invasive imaging techniques hold immense potential by capturing subtle physiological changes in plants…

计算机视觉与模式识别 · 计算机科学 2025-01-14 Aswini Kumar Patra , Lingaraj Sahoo

To enable robotic weed control, we develop algorithms to detect nutsedge weed from bermudagrass turf. Due to the similarity between the weed and the background turf, manual data labeling is expensive and error-prone. Consequently, directly…

计算机视觉与模式识别 · 计算机科学 2021-06-17 Shuangyu Xie , Chengsong Hu , Muthukumar Bagavathiannan , Dezhen Song

This paper explores the application of knowledge distillation technology in target detection tasks, especially the impact of different distillation temperatures on the performance of student models. By using YOLOv5l as the teacher network…

计算机视觉与模式识别 · 计算机科学 2024-10-17 Guanming Huang , Aoran Shen , Yuxiang Hu , Junliang Du , Jiacheng Hu , Yingbin Liang

This study, our main topic is to devlop a new deep-learning approachs for plant leaf disease identification and detection using leaf image datasets. We also discussed the challenges facing current methods of leaf disease detection and how…

机器学习 · 计算机科学 2025-01-03 El Houcine El Fatimi

Active learning aims to reduce labeling costs by selecting only the most informative samples on a dataset. Few existing works have addressed active learning for object detection. Most of these methods are based on multiple models or are…

计算机视觉与模式识别 · 计算机科学 2021-08-24 Jiwoong Choi , Ismail Elezi , Hyuk-Jae Lee , Clement Farabet , Jose M. Alvarez

Deep model-based reinforcement learning methods offer a conceptually simple approach to the decision-making and control problem: use learning for the purpose of estimating an approximate dynamics model, and offload the rest of the work to…

机器学习 · 计算机科学 2023-07-13 Michael Janner

Generic image inpainting aims to complete a corrupted image by borrowing surrounding information, which barely generates novel content. By contrast, multi-modal inpainting provides more flexible and useful controls on the inpainted content,…

计算机视觉与模式识别 · 计算机科学 2023-03-07 Shaoan Xie , Zhifei Zhang , Zhe Lin , Tobias Hinz , Kun Zhang

Visual detection of Unmanned Aerial Vehicles (UAVs) is a critical task in surveillance systems due to their small physical size and environmental challenges. Although deep learning models have achieved significant progress, deploying them…

计算机视觉与模式识别 · 计算机科学 2026-04-23 Amir Zamani , Zeinab Abedini

Object Detection has been a significant topic in computer vision. As the continuous development of Deep Learning, many advanced academic and industrial outcomes are established on localising and classifying the target objects, such as…

计算机视觉与模式识别 · 计算机科学 2019-07-31 Yingwei Zhou

The Kondinin region in Western Australia faces significant agricultural challenges due to pervasive weed infestations, causing economic losses and ecological impacts. This study constructs a tailored multispectral remote sensing dataset and…

计算机视觉与模式识别 · 计算机科学 2025-02-14 Haitian Wang , Muhammad Ibrahim , Yumeng Miao , D ustin Severtson , Atif Mansoor , Ajmal S. Mian