367 Hits in 5.1 sec

Coarse to Fine: Domain Adaptive Crowd Counting via Adversarial Scoring Network [article]

Zhikang Zou, Xiaoye Qu, Pan Zhou, Shuangjie Xu, Xiaoqing Ye, Wenhao Wu, Jin Ye
2021 arXiv   pre-print
To facilitate this issue, this paper proposes a novel adversarial scoring network (ASNet) to gradually bridge the gap across domains from coarse to fine granularity.  ...  In specific, at the coarse-grained stage, we design a dual-discriminator strategy to adapt source domain to be close to the targets from the perspectives of both global and local feature space via adversarial  ...  In this paper, we propose a novel coarse-to-fine framework named Adversarial Scoring Network (ASNet) for domain adaptive crowd counting.  ... 
arXiv:2107.12858v1 fatcat:xheysldadrh4hefguvwncnrzuq

ALADIN: All Layer Adaptive Instance Normalization for Fine-grained Style Similarity [article]

Dan Ruta, Saeid Motiian, Baldo Faieta, Zhe Lin, Hailin Jin, Alex Filipkowski, Andrew Gilbert, John Collomosse
2021 arXiv   pre-print
Learning an embedding that discriminates fine-grained variations in style is hard, due to the difficulty of defining and labelling style.  ...  ALADIN sets a new state of the art accuracy for style-based visual search over both coarse labelled style data (BAM) and BAM-FG; a new 2.62 million image dataset of 310,000 fine-grained style groupings  ...  Generative adversarial networks (GAN) such as cycle-consistent GAN [40] have been trained to map images from one domain to another, including between styles, and require labelled sets of (unpaired) images  ... 
arXiv:2103.09776v1 fatcat:gddjgr4zcnetlp26aihmy2aerq

Domain-adaptive Crowd Counting via High-quality Image Translation and Density Reconstruction [article]

Junyu Gao, Tao Han, Qi Wang, Yuan Yuan
2021 arXiv   pre-print
To remedy the above problems, this paper proposes a Domain-Adaptive Crowd Counting (DACC) framework, which consists of a high-quality image translation and density map reconstruction.  ...  Recently, crowd counting using supervised learning achieves a remarkable improvement. Nevertheless, most counters rely on a large amount of manually labeled data.  ...  [17] present a crowd counting via domain adaptation method, which is easy to land in practice from the perspectives of performance and costs. B.  ... 
arXiv:1912.03677v3 fatcat:2ow3u7j24rgjppxndz4cqh3fg4

Feature-aware Adaptation and Density Alignment for Crowd Counting in Video Surveillance [article]

Junyu Gao, Yuan Yuan, Qi Wang
2020 arXiv   pre-print
To reduce the gap, in this paper, we propose a domain-adaptation-style crowd counting method, which can effectively adapt the model from synthetic data to the specific real-world scenes.  ...  SDA guarantees the network outputs fine density maps with a reasonable distribution on the real domain.  ...  Fig. 2 shows the flowchart of our proposed crowd counting via domain adaptation.  ... 
arXiv:1912.03672v2 fatcat:rgf5yrjltnhexatfseaizu33ee

2021 Index IEEE Transactions on Multimedia Vol. 23

2021 IEEE transactions on multimedia  
Departments and other items may also be covered if they have been judged to have archival value. The Author Index contains the primary entry for each item, listed under the first author's name.  ...  ., +, TMM 2021 1343-1353 Co-Saliency Detection via a General Optimization Model and Adaptive Graph Learning. Jiang, B., +, TMM 2021 3193-3202 Coarse-to-Fine CNN for Image Super-Resolution.  ...  ., +, TMM 2021 1640-1653 Adversarial Network With Multiple Classifiers for Open Set Domain Adaptation.  ... 
doi:10.1109/tmm.2022.3141947 fatcat:lil2nf3vd5ehbfgtslulu7y3lq

Introduction to the Special Section on Contextual Object Analysis in Complex Scenes

Meng Wang, Xianglong Liu, Xun Yang, Liang Zheng
2020 IEEE transactions on circuits and systems for video technology (Print)  
to count all the certain objects in crowded scenes, how to re-identify pedestrians across camera views, and how to recognize or describe the objects in a fine-grained manner.  ...  It is a challenging task due to high appearance similarity, perspective changes, and severe congestion. The article "PCC Net: Perspective crowd counting via spatial convolutional network" by J.  ... 
doi:10.1109/tcsvt.2020.3017118 fatcat:znxhng7ednfbdjxxyn3m23gorq

Forget Less, Count Better: A Domain-Incremental Self-Distillation Learning Benchmark for Lifelong Crowd Counting [article]

Jiaqi Gao, Jingqi Li, Hongming Shan, Yanyun Qu, James Z. Wang, Junping Zhang
2022 arXiv   pre-print
To overcome these issues, we investigate a new task of crowd counting under the incremental domains training setting, namely, Lifelong Crowd Counting.  ...  A robust and practical crowd counting system has to be capable of continuously learning with the new-coming domain data in real-world scenarios instead of fitting one domain only.  ...  Adversarial Scoring Network [41] is applied to adapt to the target domain from coarse to fine granularity.  ... 
arXiv:2205.03307v1 fatcat:scgrxak5oze6bcphhnjpyu32dq

An Adaptive Classifier Based Approach for Crowd Anomaly Detection

Sofia Nishath, P. S. Nithya Darisini
2022 Computers Materials & Continua  
In this approach, Adaptive GoogleNet Neural Network Classifier with Multi-Objective Whale Optimization Algorithm are applied to predict the abnormal video frames in the crowded scenes.  ...  The performance parameters such as accuracy, precision, recall, and F-score are considered to evaluate the proposed technique using the Python simulation tool.  ...  Pre-trained networks are used to fine-tune CNN for each dataset in a homogenous manner.  ... 
doi:10.32604/cmc.2022.023935 fatcat:l7vqii736rf7rd7c5hvhurwiq4

2020 Index IEEE Transactions on Circuits and Systems for Video Technology Vol. 30

2020 IEEE transactions on circuits and systems for video technology (Print)  
Wu, L., +, TCSVT July 2020 2178-2190 PCC Net: Perspective Crowd Counting via Spatial Convolutional Network.  ...  ., +, TCSVT March 2020 781-794 Scale-Aware Crowd Counting via Depth-Embedded Convolutional Neural Networks.  ... 
doi:10.1109/tcsvt.2020.3043861 fatcat:s6z4wzp45vfflphgfcxh6x7npu

Learning Neural Textual Representations for Citation Recommendation

Binh Thanh Kieu, Inigo Jauregi Unanue, Son Bao Pham, Hieu Xuan Phan, Massimo Piccardi
2021 2020 25th International Conference on Pattern Recognition (ICPR)  
DAY 2 -Jan 13, 2021 Jiang, Na; Wen, Xingsen; Shi, Zhiping 463 DAPC: Domain Adaptation People Counting Via Style-Level Transfer Learning and Scene-Aware Estimation DAY 2 -Jan 13, 2021 Huang  ...  for Deep Multi- Agent Reinforcement Learning DAY 2 -Jan 13, 2021 Peng, Tao; Li, Rong; Li, Shang; Zhu, Pengfei 2183 Learning from Web Data: Improving Crowd Counting Via Semi- Supervised Learning  ... 
doi:10.1109/icpr48806.2021.9412725 fatcat:3vge2tpd2zf7jcv5btcixnaikm

Table of Contents

2020 2020 IEEE International Conference on Image Processing (ICIP)  
FOR ...................................................... 683 CROWD COUNTING .  ...  FROM ACTION RECOGNITION TO ........................................... IN ADVERSARIAL DOMAIN ............................................  ...  CODED-APERTURE FOR UNSUPERVISED CLASSIFICATION OF HYPERSEPCTRAL IMAGERY -LDQFKHQ =KX 7RQJ =KDQJ 6KHQJMLH =KDR 7RQJML 8QLYHUVLW\ &KLQD IMT-02.4: ADMM-INSPIRED RECONSTRUCTION NETWORK FOR COMPRESSIVE  ... 
doi:10.1109/icip40778.2020.9191006 fatcat:3fkxl2sjmre2jkryewwo5mlahi

Deep neural network models for computational histopathology: A survey [article]

Chetan L. Srinidhi, Ozan Ciga, Anne L. Martel
2019 arXiv   pre-print
Histopathological images contain rich phenotypic information that can be used to monitor underlying mechanisms contributing to diseases progression and patient survival outcomes.  ...  This auxiliary task also helped increase the adversarial domain adaptation performance on another target dataset.  ...  Hence, it is a common practice in the medical imaging domain to fine-tune a pre-trained network rather than training from scratch.  ... 
arXiv:1912.12378v1 fatcat:xdfkzzwzb5alhjfhffqpcurb2u

Improving Semantic Segmentation via Self-Training [article]

Yi Zhu, Zhongyue Zhang, Chongruo Wu, Zhi Zhang, Tong He, Hang Zhang, R. Manmatha, Mu Li, Alexander Smola
2020 arXiv   pre-print
Lastly, to alleviate the computational burden caused by the large amount of pseudo labels, we propose a fast training schedule to accelerate the training of segmentation models by up to 2x without performance  ...  We also demonstrate the effectiveness of self-training on a challenging cross-domain generalization task, outperforming conventional finetuning method by a large margin.  ...  Domain adaptation. Our cross-domain generalization task is related to unsupervised domain adaptation (UDA).  ... 
arXiv:2004.14960v2 fatcat:32gbkc2buraibhfaathn5dcgvq

Multi-Modal Retrieval using Graph Neural Networks [article]

Aashish Kumar Misraa, Ajinkya Kale, Pranav Aggarwal, Ali Aminian
2020 arXiv   pre-print
This joint model gives the user fine-grained control over the semantics of the result set, allowing them to explore the catalog of images more rapidly.  ...  This graph structure helps us learn multi-modal node embeddings using Graph Neural Networks.  ...  ACKNOWLEDGMENTS The authors would like to thank Kshitiz Garg for his valuable feedback on our work and Tracy King for reviewing and helping edit this paper.  ... 
arXiv:2010.01666v1 fatcat:mtp43eajpbabnhownf6tqaxhki

Synthetic Data for Deep Learning [article]

Sergey I. Nikolenko
2019 arXiv   pre-print
Second, we discuss in detail the synthetic-to-real domain adaptation problem that inevitably arises in applications of synthetic data, including synthetic-to-real refinement with GAN-based models and domain  ...  adaptation at the feature/model level without explicit data transformations.  ...  The authors report improved results for progressive networks compared to simple transfer via fine-tuning.  ... 
arXiv:1909.11512v1 fatcat:qquxnw4dfvgmfeztbpdqhr44gy
« Previous Showing results 1 — 15 out of 367 results