检索结果-内蒙古大学图书馆

APSeg: Auto-Prompt Network for Cross-Domain Few-Shot Semantic Segmentation

学校读者我要写书评

暂无评论

arXiv 2024年

作者： He, Weizhao Zhang, Yang Zhuo, Wei Shen, Linlin Yang, Jiaqi Deng, Songhe Sun, Liang Computer Vision Institute School of Computer Science & Software Engineering Shenzhen University China Shenzhen Institute of Artificial Intelligence and Robotics for Society China National Engineering Laboratory for Big Data System Computing Technology Shenzhen University China School of Computer Science University of Nottingham China

Few-shot semantic segmentation (FSS) endeavors to segment unseen classes with only a few labeled samples. Current FSS methods are commonly built on the assumption that their training and application scenarios share similar domains, and their performances degrade significantly while applied to a distinct domain. To this end, we propose to leverage the cutting-edge foundation model, the Segment Anything Model (SAM), for generalization enhancement. The SAM however performs unsatisfactorily on domains that are distinct from its training data, which primarily comprise natural scene images, and it does not support automatic segmentation of specific semantics due to its interactive prompting mechanism. In our work, we introduce APSeg, a novel auto-prompt network for cross-domain few-shot semantic segmentation (CD-FSS), which is designed to be auto-prompted for guiding cross-domain segmentation. Specifically, we propose a Dual Prototype Anchor Transformation (DPAT) module that fuses pseudo query prototypes extracted based on cycle-consistency with support prototypes, allowing features to be transformed into a more stable domain-agnostic space. Additionally, a Meta Prompt Generator (MPG) module is introduced to automatically generate prompt embeddings, eliminating the need for manual visual prompts. We build an efficient model which can be applied directly to target domains without fine-tuning. Extensive experiments on four cross-domain datasets show that our model outperforms the state-of-the-art CD-FSS method by 5.24% and 3.10% in average accuracy on 1-shot and 5-shot settings, respectively. Copyright © 2024, The Authors. All rights reserved.

关键词： Semantic Segmentation

Fingerprint Presentation Attack Detector Using Global-Local Model

学校读者我要写书评

暂无评论

arXiv 2024年

作者： Liu, Haozhe Zhang, Wentian Liu, Feng Wu, Haoqian Shen, Linlin The Computer Vision Institute College of Computer Science and Software Engineering SZU Branch Shenzhen Institute of Artificial Intelligence and Robotics for Society The National Engineering Laboratory for Big Data System Computing Technology The Guangdong Key Laboratory of Intelligent Information Processing Shenzhen University Shenzhen518060 China

The vulnerability of automated fingerprint recognition systems (AFRSs) to presentation attacks (PAs) promotes the vigorous development of PA detection (PAD) technology. However, PAD methods have been limited by information loss and poor generalization ability, resulting in new PA materials and fingerprint sensors. This paper thus proposes a global-local model-based PAD (RTK-PAD) method to overcome those limitations to some extent. The proposed method consists of three modules, called: 1) the global module;2) the local module;and 3) the rethinking module. By adopting the cut-out-based global module, a global spoofness score predicted from nonlocal features of the entire fingerprint images can be achieved. While by using the texture in-painting-based local module, a local spoofness score predicted from fingerprint patches is obtained. The two modules are not independent but connected through our proposed rethinking module by localizing two discriminative patches for the local module based on the global spoofness score. Finally, the fusion spoofness score by averaging the global and local spoofness scores is used for PAD. Our experimental results evaluated on LivDet 2017 show that the proposed RTK-PAD can achieve an average classification error (ACE) of 2.28% and a true detection rate (TDR) of 91.19% when the false detection rate (FDR) equals 1.0%, which significantly outperformed the state-of-the-art methods by ∼10% in terms of TDR (91.19% versus 80.74%). Copyright © 2024, The Authors. All rights reserved.

关键词： Supervised learning

Color-Difference Correntropy Guided Convolution Network for Point Cloud Semantic Segmentation

学校读者我要写书评

暂无评论

Color-Difference Correntropy Guided Convolution Network for ...

International Joint Conference on Neural Networks (IJCNN)

作者： Zhou Jiang Jing Yang Chunyu Xuan Dong Zhang Shaoyi Du School of Software Engineering Xi'an Jiaotong University Xi'an China School of Automation Science and Engineering Xi'an Jiaotong University Xi'an China Institute of Artificial Intelligence and Robotics Xi'an Jiaotong University Xi'an China

With the development of data acquisition technology, RGB color information is widely collected to strengthen the 3D point cloud. To some extent, RGB color information contains the prior relation about the spatial position of objects. However, the existing point cloud segmentation networks based on deep learning do not pay much attention to it. To remedy the lack in this area, we propose a color-difference correntropy guided convolution network, which introduces correntropy to optimize the measurement of color-difference. Meanwhile, we select points in the local neighborhood via the color-difference guided module, and construct an ordered sequence of points with correlation information, which not only facilitates the feature extraction by directly applying the convolution but also fully studies the correlation between the color information and spatial position of the point cloud. Moreover, we fuse the sequence features extracted by convolution with the geometric features acquired by MLP to get new features with more abundant semantic information, thus improving the segmentation performance. On both indoor and outdoor datasets, the experimental results demonstrate the effectiveness and superiority of the proposed method by the comparison experiments and ablation experiments.

关键词：

Unsupervised Alignment of Traffic Elements for Domain Adaptive Semantic Segmentation

学校读者我要写书评

暂无评论

Unsupervised Alignment of Traffic Elements for Domain Adapti...

International Conference on Intelligent Transportation

作者： Yuan Gao Yaochen Li Tengwen Zhang Chao Qiu Yuehu Liu School of Software Engineering Xi'an Jiaotong University Xi'an Shaanxi Province P.R. China Institute of Artificial Intelligence and Robotics Xi'an Jiaotong University Xi'an Shaanxi Province P.R. China

ISBN: (数字)9798331505929

ISBN: (纸本)9798331505936

Unsupervised domain adaptation has been used to reduce the domain shift, which would improve the performance of semantic segmentation on unlabeled real-world data. How-ever, existing methods do not cater to the specific characteristics of traffic scene elements, leading to suboptimal alignment outcomes. In this paper, we propose a novel domain adaptation method for semantic segmentation of road scenes via unsu-pervised alignment of traffic elements. Firstly, a self-training framework is developed, which distinguishes the differential features between dynamic and static traffic elements, providing more accurate alignment training. Then, we designed a dynamic and static traffic elements alignment module to achieve cross-domain feature matching between the source and the target domain images. The cosine similarity maximization is applied to the alignment of dynamic traffic elements, while the prototype learning is utilized for the static traffic elements. Furthermore, the element alignment loss functions for dynamic and static traffic elements are designed to optimize the alignment modules. The experimental results demonstrate that the proposed method is superior to the existing methods on G TAS→Cityscapes task, which is applicable to semantic segmentation of road scenes.

关键词： Training Accuracy Semantic segmentation Roads Semantics Prototypes Intelligent transportation systems

Exploration and Coverage Path Planning of Unknown Environment using Multi-Robot System

学校读者我要写书评

暂无评论

Exploration and Coverage Path Planning of Unknown Environmen...

IEEE International Conference on Electronics, Computing and Communication Technologies (CONECCT)

作者： Glace Varghese T Sreeja Kochuvila Navin Kumar Ajay Paul Varma Divya R Samar Shailendra Dept. of ECE Amrita Vishwa Vidyapeetham Bengaluru India Robotics – SX/PJ1-EM Bosch Global Software Technologies Bengaluru India Department of IT and Engineering Melbourne Institute of Technology Melbourne Australia

ISBN: (数字)9798350385922

ISBN: (纸本)9798350385939

This research paper delves into the intricacies of efficient environment exploration and coverage path planning using multi-robot systems. With a focus on unknown environments, the study addresses the mapping of the environment in 2D, distributing coverage tasks among robots, and coordinating their movements for comprehensive coverage. Various strategies are explored, including Simultaneous localization and mapping (SLAM) using G-mapping, dynamic task distribution, waypoint generation, and coordination mechanisms. Leveraging the collective intelligence of multiple robots, this work aims to optimize coverage while minimizing redundancy and resource consumption. Through simulations and analysis, the effectiveness of the proposed methodology is demonstrated with a coverage efficiency of 98.9%, highlighting the potential of multi-robot system in revolutionizing exploration and coverage path planning in diverse real-world applications.

关键词： Technological innovation Simultaneous localization and mapping Robot kinematics Redundancy Collaboration Collective intelligence Dynamic scheduling

Video Self-Supervised Cross-Pathway Training Based on Slow and Fast Pathways

学校读者我要写书评

暂无评论

Video Self-Supervised Cross-Pathway Training Based on Slow a...

IEEE International Conference on Systems, Man and Cybernetics

作者： Jie Li Jing Yang Zhou Jiang Yuehai Chen Shaoyi Du School of Automation Science and Engineering Xi'an Jiaotong University Xi'an China School of Software Engineering Xi'an Jiaotong University Xi'an China Institute of Artificial Intelligence and Robotics Xi'an Jiaotong University Xi'an China

In the field of video self-supervised learning, contrastive instance learning methods suffer from a lack of semantic information, resulting in inadequate generalization in downstream tasks. Although optical flow can provide some semantic information, it requires significant computational cost prior to training. To address this, we propose a Video self-supervised Cross-pathway training model based on Slow and Fast pathways (VCSF). This model separately extracts temporal and spatial features from pure RGB video frames, and uses the complementary representations of the two pathways to conduct cross-pathway training. Additionally, we propose a motion perception module in the low-frame-rate space to enhance the network's ability to perceive rapidly changing human motion. We conducted extensive experiments in downstream missions of UCF101 and HMDB51, and obtained state-of-the-art results in models using the UCF101 data set for self-supervised pre-training, including motion recognition and nearest neighbor retrieval.

关键词：

Multi-scale Dynamic and Hierarchical Relationship Modeling for Facial Action Units Recognition

学校读者我要写书评

暂无评论

arXiv 2024年

作者： Wang, Zihan Song, Siyang Luo, Cheng Deng, Songhe Xie, Weicheng Shen, Linlin Computer Vision Institute School of Computer Science & Software Engineering Shenzhen University China Shenzhen Institute of Artificial Intelligence and Robotics for Society China National Engineering Laboratory for Big Data System Computing Technology Shenzhen University China University of Leicester United Kingdom Monash University Australia

Human facial action units (AUs) are mutually related in a hierarchical manner, as not only they are associated with each other in both spatial and temporal domains but also AUs located in the same/close facial regions show stronger relationships than those of different facial regions. While none of existing approach thoroughly model such hierarchical inter-dependencies among AUs, this paper proposes to comprehensively model multi-scale AU-related dynamic and hierarchical spatio-temporal relationship among AUs for their occurrences recognition. Specifically, we first propose a novel multi-scale temporal differencing network with an adaptive weighting block to explicitly capture facial dynamics across frames at different spatial scales, which specifically considers the heterogeneity of range and magnitude in different AUs’ activation. Then, a two-stage strategy is introduced to hierarchically model the relationship among AUs based on their spatial distribution (i.e., local and cross-region AU relationship modelling). Experimental results achieved on BP4D and DISFA show that our approach is the new state-of-the-art in the field of AU occurrence recognition. Our code is publicly available at https://***/CVI-SZU/MDHR. © 2024, CC BY.

关键词： Face recognition

ThiNet Based Pruning Method for GAN Based Steganography Framework UT-GAN 15

学校读者我要写书评

暂无评论

ThiNet Based Pruning Method for GAN Based Steganography Fram...

15th International Symposium on Signals, Circuits and Systems, ISSCS 2021

作者： Li, Qifen Li, Sili Tan, Shunquan Li, Bin Shenzhen University College of Computer Science and Software Engineering Shenzhen Key Laboratory of Media Security Shenzhen Institute of Artificial Intelligence and Robotics for Society Shenzhen518060 China

ISBN: (纸本)9781665449427

With the application of deep-learning framework, both the steganography and steganalysis gain superior performance than before, which has been testified by the previous researchers through experiments. Though the deep-learning models bring the excellent performance, they also result in the over-parameterized models and redundancy in computation and memory storage which make it hard for them to deploy. In this paper, we propose a ThiNet based scheme to prune the state-of the-Art steganographic model based on GAN-UTGAN. We evaluate and sort the significance of the channels of a layer according to the output of the next layer by using the greedy algorithm and obtain the channels which have the similar impact on the next layer compared with all the channels before pruning. The experimental results conducted on SZUBase, BOSSBase, and BOWS2 dataset demonstrate that our proposed ThiNet based method could compact the original UT-GAN model effectively with about only two percent of parameters of the original model and have about only a little decline in detection error rate when analyzed by SRM with ensemble classifier, which has outperformed the ASDL-GAN method. © 2021 IEEE.

关键词： Steganography

HairDiffusion: Vivid Multi-Colored Hair Editing via Latent Diffusion

学校读者我要写书评

暂无评论

arXiv 2024年

作者： Zeng, Yu Zhang, Yang Liu, Jiachen Shen, Linlin Deng, Kaijun He, Weizhao Wang, Jinbao Computer Vision Institute School of Computer Science & Software Engineering Shenzhen University China Shenzhen Institute of Artificial Intelligence and Robotics for Society China National Engineering Laboratory for Big Data System Computing Technology Shenzhen University China Guangdong Provincial Key Laboratory of Intelligent Information Processing China

Hair editing is a critical image synthesis task that aims to edit hair color and hairstyle using text descriptions or reference images, while preserving irrelevant attributes (e.g., identity, background, cloth). Many existing methods are based on StyleGAN to address this task. However, due to the limited spatial distribution of StyleGAN, it struggles with multiple hair color editing and facial preservation. Considering the advancements in diffusion models, we utilize Latent Diffusion Models (LDMs) for hairstyle editing. Our approach introduces Multi-stage Hairstyle Blend (MHB), effectively separating control of hair color and hairstyle in diffusion latent space. Additionally, we train a warping module to align the hair color with the target region. To further enhance multi-color hairstyle editing, we fine-tuned a CLIP model using a multi-color hairstyle dataset. Our method not only tackles the complexity of multi-color hairstyles but also addresses the challenge of preserving original colors during diffusion editing. Extensive experiments showcase the superiority of our method in editing multi-color hairstyles while preserving facial attributes given textual descriptions and reference images. © 2024, CC BY.

关键词： Color image processing