检索结果-内蒙古大学图书馆

ieee/cvf conference on computer vision and pattern recognition (CVPR)

作者： Zhu, Lanyun Ji, Deyi Zhu, Shiping Gan, Weihao Wu, Wei Yan, Junjie Beihang Univ Beijing Peoples R China SenseTime Res Los Angeles CA 90007 USA

ISBN: (纸本)9781665445092

Existing semantic segmentation works mainly focus on learning the contextual information in high-level semantic features with CNNs. In order to maintain a precise boundary, low-level texture features are directly skip-connected into the deeper layers. Nevertheless, texture features are not only about local structure, but also include global statistical knowledge of the input image. In this paper, we filly take advantages of the low-level texture features and propose a novel Statistical Texture Learning Network (STL-Net) for semantic segmentation. For the first time, STL-Net analyzes the distribution of low level information and efficiently utilizes them for the task. Specifically, a novel Quantization and Counting Operator (QCO) is designed to describe the texture information in a statistical manner. Based on QCO, two modules are introduced: (1) Texture Enhance Module (TEM), to capture texture-related information and enhance the texture details: (2) Pyramid Texture Feature Extraction Module (PTFEM), to effectively extract the statistical texture features from multiple scales. Through extensive experiments, we show that the proposed STL-Net achieves state-of-the-art performance on three semantic segmentation benchmarks: Cityscapes, PASCAL Context and ADE20K.

关键词： Image segmentation Technological innovation computer vision Quantization (signal) Semantics Benchmark testing Feature extraction

来源：评论

学校读者我要写书评

暂无评论

Learning Graph Embeddings for Compositional Zero-shot Learning

Learning Graph Embeddings for Compositional Zero-shot Learni...

引用

ieee/cvf conference on computer vision and pattern recognition (CVPR)

作者： Naeem, Muhammad Ferjad Xian, Yongqin Tombari, Federico Akata, Zeynep Univ Tubingen Tubingen Germany MPI Informat Tubingen Germany TUM Munich Germany Google Mountain View CA 94043 USA MPI Intelligent Syst Tubingen Germany

ISBN: (纸本)9781665445092

In compositional zero-shot learning, the goal is to recognize unseen compositions (e.g. old dog) of observed visual primitives states (e.g. old, cute) and objects (e.g. car, dog) in the training set. This is challenging because the same state can for example alter the visual appearance of a dog drastically differently from a car. As a solution, we propose a novel graph formulation called Compositional Graph Embedding (CGE) that learns image features, compositional classifiers and latent representations of visual primitives in an end-to-end manner. The key to our approach is exploiting the dependency between states, objects and their compositions within a graph structure to enforce the relevant knowledge transfer from seen to unseen compositions. By learning a joint compatibility that encodes semantics between concepts, our model allows for generalization to unseen compositions without relying on an external knowledge base like WordNet. We show that in the challenging generalized compositional zero-shot setting our CGE significantly outperforms the state of the art on MIT-States and UT-Zappos. We also propose a new benchmark for this task based on the recent GQA dataset.

关键词： Training Visualization Knowledge based systems Semantics Dogs Benchmark testing pattern recognition

来源：评论

学校读者我要写书评

暂无评论

Advancing COVID-19 Detection in 3D CT Scans

Advancing COVID-19 Detection in 3D CT Scans

引用

ieee computer Society conference on computer vision and pattern recognition workshops (CVPRW)

作者： Qingqiu Li Runtian Yuan Junlin Hou Jilan Xu Yuejie Zhang Rui Feng Hao Chen School of Academy for Engineering and Technology Fudan University China School of Computer Science Fudan University China Department of Computer Science and Engineering The Hong Kong University of Science and Technology China

ISBN: (数字)9798350365474

ISBN: (纸本)9798350365481

To make a more accurate diagnosis of COVID-19, we propose a straightforward yet effective model. Firstly, we analyze the characteristics of 3D CT scans and remove the non-lung parts, facilitating the model to focus on lesion-related areas and reducing computational cost. We use ResNeSt-50 as the strong feature extractor, exploring various pre-trained weights and fine-tuning methods. After a thorough comparison, we initialize our model with CMC v1 pre-trained weights which incorporate COVID-19-specific prior knowledge, and perform Visual Prompt Tuning to reduce the number of training parameters. The superiority of our model is demonstrated through extensive experiments, showing significant improvements in COVID-19 detection performance compared to the baseline model. Among 12 participating teams, our method ranked 4th in the 4th COVID-19 Competition Challenge I with an average Macro F1 Score of 94.24%.

关键词： COVID-19 Training Solid modeling Visualization Three-dimensional displays Computational modeling Computed tomography

来源：评论

学校读者我要写书评

暂无评论

XProtoNet: Diagnosis in Chest Radiography with Global and Local Explanations

XProtoNet: Diagnosis in Chest Radiography with Global and Lo...

引用

ieee/cvf conference on computer vision and pattern recognition (CVPR)

作者： Kim, Eunji Kim, Siwon Seo, Minji Yoon, Sungroh Seoul Natl Univ Dept Elect & Comp Engn Seoul South Korea Seoul Natl Univ ASRI INMC ISRC Seoul South Korea Seoul Natl Univ Inst Engn Res Seoul South Korea

ISBN: (纸本)9781665445092

Automated diagnosis using deep neural networks in chest radiography can help radiologists detect life-threatening diseases. However, existing methods only provide predictions without accurate explanations, undermining the trustworthiness of the diagnostic methods. Here, we present XProtoNet, a globally and locally interpretable diagnosis framework for chest radiography. XProtoNet learns representative patterns of each disease from X-ray images, which are prototypes, and makes a diagnosis on a given Xray image based on the patterns. It predicts the area where a sign of the disease is likely to appear and compares the features in the predicted area with the prototypes. It can provide a global explanation, the prototype, and a local explanation, how the prototype contributes to the prediction of a single image. Despite the constraint for interpretability, XProtoNet achieves state-of-the-art classification performance on the public NIH chest X-ray dataset.

关键词： Location awareness Deep learning computer vision Computational modeling Prototypes pattern recognition Diagnostic radiography

来源：评论

学校读者我要写书评

暂无评论

A Single Residual Network with ESA Modules and Distillation

A Single Residual Network with ESA Modules and Distillation

引用

ieee computer Society conference on computer vision and pattern recognition workshops (CVPRW)

作者： Yucong Wang Minjie Cai College of Computer Science and Electronic Engineering Hunan University

Although there are many methods based on deep learning that have superior performance on single image super-resolution (SISR), it is difficult to run in real time on devices with limited computing power. Some recent studies have found that simply relying on reducing parameters or reducing the theoretical FLOPs of the model does not speed up the inference time of the network in a practical sense. Actual speed on the device is probably a better measure than FLOPs. In this work, we propose a new single residual network (SRN). On the one hand, we try to introduce and optimize an attention mechanism module to improve the performance of the network with a relatively small speed loss. On the other hand, we find that residuals in residual blocks do not have a positive impact on networks with adjusted ESA. Therefore, the residual of the network residual block is removed, which not only improves the speed of the network, but also improves the performance of the network. Finally, we reduced the number of channels and the number of residual blocks of the classic model EDSR, and removed the last convolution before the long residual. We set this tuned EDSR as the teacher model and our newly proposed SRN as the student model. Under the joint effect of the original loss and the distillation loss, the performance of the network can be improved without losing the inference time. Combining the above strategies, our proposed model runs much faster than similarly performing models. As an example, we built a Fast and Efficient Network (SRN) and its small version SRN-S, which run 30%-37% faster than the state-of-the-art EISR model: a paper champion RLFN. Furthermore, the shallow version of SRN-S achieves the second-shortest inference time as well as the second-smallest number of activations in the NTIRE2023 challenge. Code will be available at https://***/wnxbwyc/SRN.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Continual Diffusion with STAMINA: STack-And-Mask INcremental Adapters

Continual Diffusion with STAMINA: STack-And-Mask INcremental...

引用

ieee computer Society conference on computer vision and pattern recognition workshops (CVPRW)

作者： James Seale Smith Yen-Chang Hsu Zsolt Kira Yilin Shen Hongxia Jin Samsung Research America Georgia Institute of Technology

ISBN: (数字)9798350365474

ISBN: (纸本)9798350365481

Recent work has demonstrated a remarkable ability to customize text-to-image diffusion models to multiple, fine-grained concepts in a sequential (i.e., continual) manner while only providing a few example images for each concept. This setting is known as continual diffusion. Here, we ask the question: Can we scale these methods to longer concept sequences without forgetting? Although prior work mitigates the forgetting of previously learned concepts, we show that its capacity to learn new tasks reaches saturation over longer sequences. We address this challenge by introducing a novel method, STack-And-Mask INcremental Adapters (STAMINA), which is composed of low-ranked attention-masked adapters and customized MLP tokens. STAMINA is designed to enhance the robust fine-tuning properties of LoRA for sequential concept learning via learnable hard-attention masks parameterized with low rank MLPs, enabling precise, scalable learning via sparse adaptation. Notably, all introduced trainable parameters can be folded back into the model after training, inducing no additional inference parameter costs. We show that STAMINA outperforms the prior SOTA for the setting of text-to-image continual customization on a 50-concept benchmark composed of landmarks and human faces, with no stored replay data. Additionally, we extended our method to the setting of continual learning for image classification, demonstrating that our gains also translate to state-of-the-art performance in this standard benchmark.

关键词： Training Continuing education Costs Text to image Benchmark testing Diffusion models pattern recognition

来源：评论

学校读者我要写书评

暂无评论

ChaLearn Looking at People: IsoGD and ConGD Large-Scale RGB-D Gesture recognition

引用

ieee TRANSACTIONS ON CYBERNETICS 2022年第5期52卷 3422-3433页

作者： Wan, Jun Lin, Chi Wen, Longyin Li, Yunan Miao, Qiguang Escalera, Sergio Anbarjafari, Gholamreza Guyon, Isabelle Guo, Guodong Li, Stan Z. Chinese Acad Sci Inst Automat Natl Lab Pattern Recognit Beijing 100190 Peoples R China Univ Chinese Acad Sci Beijing 100190 Peoples R China Univ Southern Calif Dept Comp Sci Los Angeles CA 90089 USA JD Finance Mountain View CA 94043 USA Xidian Univ Sch Comp Sci & Technol Xian 710071 Peoples R China Xidian Univ Xian Key Lab Big Data & Intelligent Vis Xian 710071 Peoples R China Univ Barcelona Comp Vis Ctr Barcelona 08007 Spain Univ Tartu Inst Technol iCV Lab EE-50090 Tartu Estonia PwC Finland Helsinki 00180 Finland Hasan Kalyoncu Univ Fac Engn TR-27100 Gaziantep Turkey ChaLearn San Francisco CA 94115 USA Univ Paris Saclay F-91190 St Aubin France Baidu Res Inst Deep Learning Beijing 100193 Peoples R China Natl Engn Lab Deep Learning Technol & Applicat Beijing 100193 Peoples R China Westlake Univ Hangzhou 310024 Peoples R China Macau Univ Sci & Technol Taipa Macau Peoples R China

The ChaLearn large-scale gesture recognition challenge has run twice in two workshops in conjunction with the International conference on pattern recognition (ICPR) 2016 and International conference on computer vision (ICCV) 2017, attracting more than 200 teams around the world. This challenge has two tracks, focusing on isolated and continuous gesture recognition, respectively. It describes the creation of both benchmark datasets and analyzes the advances in large-scale gesture recognition based on these two datasets. In this article, we discuss the challenges of collecting large-scale ground-truth annotations of gesture recognition and provide a detailed analysis of the current methods for large-scale isolated and continuous gesture recognition. In addition to the recognition rate and mean Jaccard index (MJI) as evaluation metrics used in previous challenges, we introduce the corrected segmentation rate (CSR) metric to evaluate the performance of temporal segmentation for continuous gesture recognition. Furthermore, we propose a bidirectional long short-term memory (Bi-LSTM) method, determining video division points based on skeleton points. Experiments show that the proposed Bi-LSTM outperforms state-of-the-art methods with an absolute improvement of 8.1% (from 0.8917 to 0.9639) of CSR.

关键词： Gesture recognition Measurement Task analysis Training conferences computer vision Bidirectional long short-term memory (Bi-LSTM) gesture recognition RGB-D

来源：评论

学校读者我要写书评

暂无评论

The Spatially-Correlative Loss for Various Image Translation Tasks

The Spatially-Correlative Loss for Various Image Translation...

引用

ieee/cvf conference on computer vision and pattern recognition (CVPR)

作者： Zheng, Chuanxia Cham, Tat-Jen Cai, Jianfei Nanyang Technol Univ Sch Comp Sci & Engn Singapore Singapore Monash Univ Dept Data Sci & AI Melbourne Vic Australia

ISBN: (纸本)9781665445092

We propose a novel spatially-correlative loss that is simple, efficient and yet effective for preserving scene structure consistency while supporting large appearance changes during unpaired image-to-image (I2I) translation. Previous methods attempt this by using pixel-level cycle-consistency or feature-level matching losses, but the domain-specific nature of these losses hinder translation across large domain gaps. To address this, we exploit the spatial patterns of self-similarity as a means of defining scene structure. Our spatially-correlative loss is geared towards only capturing spatial relationships within an image rather than domain appearance. We also introduce a new self-supervised learning method to explicitly learn spatially-correlative maps for each specific translation task. We show distinct improvement over baseline models in all three modes of unpaired I2I translation: single-modal, multi-modal, and even single-image translation. This new loss can easily be integrated into existing network architectures and thus allows wide applicability. The code is available at https://***/lyndonzheng/F-LSeSim.

关键词： Learning systems Visualization computer vision Codes computer architecture Network architecture Solids

来源：评论

学校读者我要写书评

暂无评论

Coming Down to Earth: Satellite-to-Street View Synthesis for Geo-Localization

Coming Down to Earth: Satellite-to-Street View Synthesis for...

引用

ieee/cvf conference on computer vision and pattern recognition (CVPR)

作者： Toker, Aysim Zhou, Qunjie Maximov, Maxim Leal-Taixe, Laura Tech Univ Munich Munich Germany

ISBN: (纸本)9781665445092

The goal of cross-view image based geo-localization is to determine the location of a given street view image by matching it against a collection of geo-tagged satellite images. This task is notoriously challenging due to the drastic viewpoint and appearance differences between the two domains. We show that we can address this discrepancy explicitly by learning to synthesize realistic street views from satellite inputs. Following this observation, we propose a novel multi-task architecture in which image synthesis and retrieval are considered jointly. The rationale behind this is that we can bias our network to learn latent feature representations that are useful for retrieval if we utilize them to generate images across the two input domains. To the best of our knowledge, ours is the first approach that creates realistic street views from satellite images and localizes the corresponding query street-view simultaneously in an end-to-end manner. In our experiments, we obtain state-of-the-art performance on the CVUSA and CVACT benchmarks. Finally, we show compelling qualitative results for satellite-to-street view synthesis.

关键词： Earth Location awareness Satellites Image synthesis Semantics Image retrieval computer architecture

来源：评论

学校读者我要写书评

暂无评论

Semantic Relation Reasoning for Shot-Stable Few-Shot Object Detection

Semantic Relation Reasoning for Shot-Stable Few-Shot Object ...

引用

ieee/cvf conference on computer vision and pattern recognition (CVPR)

作者： Zhu, Chenchen Chen, Fangyi Ahmed, Uzair Shen, Zhiqiang Savvides, Marios Carnegie Mellon Univ Pittsburgh PA 15213 USA

ISBN: (纸本)9781665445092

Few-shot object detection is an imperative and long-lasting problem due to the inherent long-tail distribution of real-world data. Its performance is largely affected by the data scarcity of novel classes. But the semantic relation between the novel classes and the base classes is constant regardless of the data availability. In this work, we investigate utilizing this semantic relation together with the visual information and introduce explicit relation reasoning into the learning of novel object detection. Specifically, we represent each class concept by a semantic embedding learned from a large corpus of text. The detector is trained to project the image representations of objects into this embedding space. We also identify the problems of trivially using the raw embeddings with a heuristic knowledge graph and propose to augment the embeddings with a dynamic relation graph. As a result, our few-shot detector, termed SRR-FSD, is robust and stable to the variation of shots of novel objects. Experiments show that SRR-FSD can achieve competitive results at higher shots, and more importantly, a significantly better performance given both lower explicit and implicit shots. The benchmark protocol with implicit shots removed from the pretrained classification dataset can serve as a more realistic setting for future research.

关键词： Visualization computer vision Protocols Semantics Object detection Detectors Image representation

来源：评论

学校读者我要写书评

暂无评论

建议与咨询留下您的常用邮箱和电话号码，以便我们向您反馈解决方案和替代方法

时间限定

文献类型

馆藏选择

核心期刊

语言

文献类型

帮助

文字说明：

检索规则说明：

检索范例：

分类表

所选分类

限定检索结果

文献类型

馆藏范围

日期分布

学科分类号

主题

机构

作者

语言

请选择保存的检索档案：

请选择收藏分类：

通借通还

建议与咨询 留下您的常用邮箱和电话号码，以便我们向您反馈解决方案和替代方法

时间限定

文献类型

馆藏选择

核心期刊

语言

文献类型

帮助

文字说明：

检索规则说明：

检索范例：

分类表

所选分类

限定检索结果

文献类型

馆藏范围

日期分布

学科分类号

主题

机构

作者

语言

请选择保存的检索档案： 新增检索档案 确定 取消

请选择收藏分类： 新增自定义分类 确定 取消

通借通还

建议与咨询留下您的常用邮箱和电话号码，以便我们向您反馈解决方案和替代方法

请选择保存的检索档案：

请选择收藏分类：