检索结果-内蒙古大学图书馆

Masked Image Training for Generalizable Deep Image Denoising

学校读者我要写书评

暂无评论

Masked Image Training for Generalizable Deep Image Denoising

Conference on computer vision and pattern recognition (CVPR)

作者： Haoyu Chen Jinjin Gu Yihao Liu Salma Abdel Magid Chao Dong Qiong Wang Hanspeter Pfister Lei Zhu The Hong Kong University of Science and Technology (Guangzhou) Shanghai AI Lab The University of Sydney ShenZhen Key Lab of Computer Vision and Pattern Recognition Shenzhen Institute of Advanced Technology Chinese Academy of Sciences University of Chinese Academy of Sciences Harvard University Guangdong Provincial Key Laboratory of Computer Vision and Virtual Reality Technology Shenzhen Institute of Advanced Technology Chinese Academy of Sciences The Hong Kong University of Science and Technology

When capturing and storing images, devices inevitably introduce noise. Reducing this noise is a critical task called image denoising. Deep learning has become the de facto method for image denoising, especially with the emergence of Transformer-based models that have achieved notable state-of-the-art results on various image tasks. However, deep learning-based methods often suffer from a lack of generalization ability. For example, deep models trained on Gaussian noise may perform poorly when tested on other noise distributions. To address this issue, we present a novel approach to enhance the generalization performance of denoising networks, known as masked training. Our method involves masking random pixels of the input image and reconstructing the missing information during training. We also mask out the features in the self-attention layers to avoid the impact of training-testing inconsistency. Our approach exhibits better generalization ability than other deep learning models and is directly applicable to real-world scenarios. Additionally, our interpretability analysis demonstrates the superiority of our method.

关键词：

Deep Learning Based Recalibration of SDSS and DESI BAO Alleviates Hubble and Clustering Tensions

学校读者我要写书评

暂无评论

arXiv 2024年

作者： Shah, Rahul Mukherjee, Purba Saha, Soumadeep Garain, Utpal Pal, Supratik Physics and Applied Mathematics Unit Indian Statistical Institute 203 B.T. Road West Bengal Kolkata700 108 India Centre for Theoretical Physics Jamia Millia Islamia Delhi New Delhi110025 India Computer Vision and Pattern Recognition Unit Indian Statistical Institute 203 B.T. Road Kolkata700 108 India

Conventional calibration of Baryon Acoustic Oscillations (BAO) data relies on estimation of the sound horizon at drag epoch rd from early universe observations by assuming a cosmological model. We present a recalibration of two independent BAO datasets, SDSS and DESI, by employing deep learning techniques for model-independent estimation of rd, and explore the impacts on ΛCDM cosmological parameters. Significant reductions in both Hubble (H0) and clustering (S8) tensions are observed for both the recalibrated datasets. Moderate shifts in some other parameters hint towards further exploration of such data-driven approaches. Copyright © 2024, The Authors. All rights reserved.

关键词： Cosmology

SURDS: Self-Supervised Attention-guided Reconstruction and Dual Triplet Loss for Writer Independent Offline Signature Verification

学校读者我要写书评

暂无评论

arXiv 2022年

作者： Chattopadhyay, Soumitri Manna, Siladittya Bhattacharya, Saumik Pal, Umapada Dept. of Information Technology Jadavpur University Kolkata India Computer Vision and Pattern Recognition Unit Indian Statistical Institute Kolkata India Dept. of Electronics and Electrical Communication Engineering Indian Institute of Technology Kharagpur India

Offline Signature Verification (OSV) is a fundamental biometric task across various forensic, commercial and legal applications. The underlying task at hand is to carefully model fine-grained features of the signatures to distinguish between genuine and forged ones, which differ only in minute deformities. This makes OSV more challenging compared to other verification problems. In this work, we propose a two-stage deep learning framework that leverages self-supervised representation learning as well as metric learning for writer-independent OSV. First, we train an image reconstruction network using an encoder-decoder architecture that is augmented by a 2D spatial attention mechanism using signature image patches. Next, the trained encoder backbone is fine-tuned with a projector head using a supervised metric learning framework, whose objective is to optimize a novel dual triplet loss by sampling negative samples from both within the same writer class as well as from other writers. The intuition behind this is to ensure that a signature sample lies closer to its positive counterpart compared to negative samples from both intra-writer and cross-writer sets. This results in robust discriminative learning of the embedding space. To the best of our knowledge, this is the first work of using self-supervised learning frameworks for OSV. The proposed two-stage framework has been evaluated on two publicly available offline signature datasets and compared with various state-of-the-art methods. It is noted that the proposed method provided promising results outperforming several existing pieces of work. The code is publicly available at: https://***/soumitri2001/SURDS-SSL-OSV. © 2022, CC BY.

关键词： Image reconstruction

Exploiting multi-scale fusion, spatial attention and patch interaction techniques for text-independent writer identification

学校读者我要写书评

暂无评论

arXiv 2021年

作者： Srivastava, Abhishek Chanda, Sukalpa Pal, Umapada Computer Vision & Pattern Recognition Unit Indian Statistical Institute Kolkata India Department of Computer Science and Communication Østfold University College Halden Norway

Text independent writer identification is a challenging problem that differentiates between different handwriting styles to decide the author of the handwritten text. Earlier writer identification relied on handcrafted features to reveal pieces of differences between writers. Recent work with the advent of convolutional neural network, deep learning-based methods have evolved. In this paper, three different deep learning techniques - spatial attention mechanism, multi-scale feature fusion and patch-based CNN were proposed to effectively capture the difference between each writer's handwriting. Our methods are based on the hypothesis that handwritten text images have specific spatial regions which are more unique to a writer's style, multi-scale features propagate characteristic features with respect to individual writers and patch-based features give more general and robust representations that helps to discriminate handwriting from different writers. The proposed methods outperforms various state-of-the-art methodologies on word-level and page-level writer identification methods on three publicly available datasets - CVL, Firemaker, CERUG-EN datasets and give comparable performance on the IAM dataset. © 2021, CC BY.

关键词： Convolutional neural networks

Complete Statistical Analysis to Weather Forecasting 1st

学校读者我要写书评

暂无评论

Complete Statistical Analysis to Weather Forecasting

1st International Conference on Computational Intelligence in pattern recognition, CIPR 2019

作者： Datta, Anisha Si, Shukrity Biswas, Sanket Department of Computer Science and Engineering Jalpaiguri Government Engineering College Jalpaiguri735102 India Computer Vision and Pattern Recognition Unit Indian Statistical Institute Kolkata700108 India

ISBN: (纸本)9789811390418

The primary objective of the model applied in this work is to predict the weather of a city named Austin in Texas using supervised machine learning algorithms. In this case, artificial neural networks and gradient boosting classifier were implemented to build models to predict weather and comparisons between these two models are also made for this dataset. Here, average temperature, average dew point, average pressure of sea level, average percentage of humidity, etc. are the parameters taken into consideration which influence the weather of the place. Using these parameters, the trained models performed a classification to predict whether the weather is rainy (thunderstorm or not), not rainy, snowy, or foggy. © 2020, Springer Nature Singapore Pte Ltd.

关键词： Supervised learning

Automatic Polyp Segmentation with Multiple Kernel Dilated Convolution Network

学校读者我要写书评

暂无评论

arXiv 2022年

作者： Tomar, Nikhil Kumar Srivastava, Abhishek Bagci, Ulas Jha, Debesh School of Informatics and Computer Science Indira Gandhi National Open University India Computer Vision and Pattern Recognition Unit Indian Statistical Institute India Machine and Hybrid Intelligence Lab Department of Radiology Feinberg School of Medicine Northwestern University United States

The detection and removal of precancerous polyps through colonoscopy is the primary technique for the prevention of colorectal cancer worldwide. However, the miss rate of colorectal polyp varies significantly among the endoscopists. It is well known that a computer-aided diagnosis (CAD) system can assist endoscopists in detecting colon polyps and minimize the variation among endoscopists. In this study, we introduce a novel deep learning architecture, named MKDCNet, for automatic polyp segmentation robust to significant changes in polyp data distribution. MKDCNet is simply an encoder-decoder neural network that uses the pre-trained ResNet50 as the encoder and novel multiple kernel dilated convolution (MKDC) block that expands the field of view to learn more robust and heterogeneous representation. Extensive experiments on four publicly available polyp datasets and cell nuclei dataset show that the proposed MKDCNet outperforms the state-of-the-art methods when trained and tested on the same dataset as well when tested on unseen polyp datasets from different distributions. With rich results, we demonstrated the robustness of the proposed architecture. From an efficiency perspective, our algorithm can process at (≈ 45) frames per second on RTX 3090 GPU. MKDCNet can be a strong benchmark for building real-time systems for clinical colonoscopies. The code of the proposed MKDCNet is available at https://***/nikhilroxtomar/MKDCNet. © 2022, CC BY.

关键词： Convolution

DeSRA: Detect and Delete the Artifacts of GAN-based Real-World Super-Resolution Models

学校读者我要写书评

暂无评论

arXiv 2023年

作者： Xie, Liangbin Wang, Xintao Chen, Xiangyu Li, Gen Shan, Ying Zhou, Jiantao Dong, Chao State Key Laboratory of Internet of Things for Smart City University of Macau China Shenzhen Key Lab of Computer Vision and Pattern Recognition Shenzhen Institute of Advanced Technology Chinese Academy of Sciences China ARC Lab Tencent PCG China Shanghai Artificial Intelligence Laboratory China Platform Technologies China

Image super-resolution (SR) with generative adversarial networks (GAN) has achieved great success in restoring realistic details. However, it is notorious that GAN-based SR models will inevitably produce unpleasant and undesirable artifacts, especially in practical scenarios. Previous works typically suppress artifacts with an extra loss penalty in the training phase. They only work for in-distribution artifact types generated during training. When applied in real-world scenarios, we observe that those improved methods still generate obviously annoying artifacts during inference. In this paper, we analyze the cause and characteristics of the GAN artifacts produced in unseen test data without ground-truths. We then develop a novel method, namely, DeSRA, to Detect and then "Delete" those SR Artifacts in practice. Specifically, we propose to measure a relative local variance distance from MSE-SR results and GAN-SR results, and locate the problematic areas based on the above distance and semantic-aware thresholds. After detecting the artifact regions, we develop a finetune procedure to improve GAN-based SR models with a few samples, so that they can deal with similar types of artifacts in more unseen real data. Equipped with our DeSRA, we can successfully eliminate artifacts from inference and improve the ability of SR models to be applied in real-world scenarios. The code will be available at https://***/TencentARC/DeSRA. Copyright © 2023, The Authors. All rights reserved.

关键词： Generative adversarial networks

LVAgent: Long Video Understanding by Multi-Round Dynamical Collaboration of MLLM Agents

学校读者我要写书评

暂无评论

arXiv 2025年

作者： Chen, Boyu Yue, Zhengrong Chen, Siran Wang, Zikang Liu, Yang Li, Peng Wang, Yali Shenzhen Key Lab of Computer Vision and Pattern Recognition Shenzhen Institutes of Advanced Technology Chinese Academy of Sciences China School of Artificial Intelligence University of Chinese Academy of Sciences China Tsinghua University Beijing China Dept. of Comp. Sci. & Tech. Institute for AI Tsinghua University Beijing China Shanghai Artificial Intelligence Laboratory China Shanghai Jiao Tong University China

Existing Multimodal Large Language Models (MLLMs) encounter significant challenges in modeling the temporal context within long videos. Currently, mainstream Agent-based methods use external tools (e.g., search engine, memory banks, OCR, retrieval models) to assist a single MLLM in answering long video questions. Despite such tool-based support, a solitary MLLM still offers only a partial understanding of long videos, resulting in limited performance. In order to better address long video tasks, we introduce LVAgent, the first framework enabling multi-round dynamic collaboration of MLLM agents in long video understanding. Our methodology consists of four key steps: 1) Selection: We pre-select appropriate agents from the model library to form optimal agent teams based on different tasks. 2) Perception: We design an effective retrieval scheme for long videos, improving the coverage of critical temporal segments while maintaining computational efficiency. 3) Action: Agents answer long video-related questions and exchange reasons. 4) Reflection: We evaluate each agent’s performance in each round of discussion and optimize the agent team for dynamic collaboration. The agents iteratively refine their answers by multi-round dynamical collaboration of MLLM agents. LVAgent is the first agent system method that outperforms all closed-source models (including GPT-4o) and open-source models (including InternVL-2.5 and Qwen2-VL) in the long video understanding tasks. Our LVAgent achieves an accuracy of 80% on four mainstream long video understanding tasks. Notably, on the LongVideoBench dataset, LVAgent improves accuracy by up to 13.3% compared with SOTA. © 2025, CC BY-NC-SA.

关键词： Search engines

Low-Resolution Action recognition for Tiny Actions Challenge

学校读者我要写书评

暂无评论

arXiv 2022年

作者： Chen, Boyu Qiao, Yu Wang, Yali ShenZhen Key Lab of Computer Vision and Pattern Recognition Shenzhen Institute of Advanced Technology Chinese Academy of Sciences China University of Chinese Academy of Sciences China Shanghai AI Laboratory Shanghai China SIAT Branch Shenzhen Institute of Artificial Intelligence and Robotics for Society China

Tiny Actions Challenge focuses on understanding human activities in real-world surveillance. Basically, there are two main difficulties for activity recognition in this scenario. First, human activities are often recorded at a distance, and appear in a small resolution without much discriminative clue. Second, these activities are naturally distributed in a long-tailed way. It is hard to alleviate data bias for such heavy category imbalance. To tackle these problems, we propose a comprehensive recognition solution in this paper. First, we train video backbones with data balance, in order to alleviate overfitting in the challenge benchmark. Second, we design a dual-resolution distillation framework, which can effectively guide low-resolution action recognition by super-resolution knowledge. Finally, we apply model ensemble with post-processing, which can further boost performance on the long-tailed categories. Our solution ranks Top-1 on the leaderboard. Copyright © 2022, The Authors. All rights reserved.

关键词： Distillation