检索结果-内蒙古大学图书馆

10th International Conference on Learning Representations, ICLR 2022

作者： Huang, Hao Fang, Yi NYU Multimedia and Visual Computing Lab United States Abu Dhabi United Arab Emirates NYU Tandon School of Engineering New York University United States New York University Abu Dhabi United Arab Emirates

We present a novel method for 3D shape representation learning using multi-scale wavelet decomposition. Previous works often decompose 3D shapes into complementary components in spatial domain at a single scale. In this work, we study to decompose 3D shapes into sub-bands components in frequency domain at multiple scales, resulting in a hierarchical decomposition tree in a principled manner rooted in multi-resolution wavelet analysis. Specifically, we propose Adaptive Wavelet Transformer Network (AWT-Net) that firstly generates approximation or detail wavelet coefficients per point, classifying each point into high or low sub-bands components, using lifting scheme at multiple scales recursively and hierarchically. Then, AWT-Net exploits Transformer to enhance the original shape features by querying and fusing features from different but integrated sub-bands. The wavelet coefficients can be learned without direct supervision on coefficients, and AWT-Net is fully differentiable and can be learned in an end-to-end fashion. Extensive experiments demonstrate that AWT-Net achieves competitive performance on 3D shape classification and segmentation benchmarks. © 2022 ICLR 2022 - 10th International Conference on Learning Representationss. All rights reserved.

关键词： Wavelet decomposition

来源：评论

学校读者我要写书评

暂无评论

Psscl: A Progressive Sample Selection Framework with Contrastive Loss Designed for Noisy labels

SSRN

引用

SSRN 2024年

作者： Zhang, Qian Zhu, Yi Cordeiro, Filipe R. Chen, Qiu School of Information Technology Jiangsu Open University Nanjing210036 China Department of Electrical Engineering and Electronics Graduate School of Engineering Kogakuin University Tokyo163-8677 Japan Visual Computing Lab Department of Computing Universidade Federal Rural de Pernambuco Brazil

Large-scale image datasets frequently contain unavoidable noisy labels, resulting in overfitting in deep neural networks and declining performance. Most existing methods for learning from noisy labels operate as one-stage frameworks, where training data division and semi-supervised learning (SSL) are intertwined for optimization. Accordingly, their effectiveness is significantly influenced by the precision of the separated clean set, prior knowledge of noise, and the robustness of SSL. In this paper, we propose a progressive sample selection framework with contrastive loss for noisy labels named PSSCL. This framework operates in two stages, using robust and contrastive losses to augment the robustness of the model. The first stage focuses on identifying a small clean set through a long-term confidence detection strategy, while the second stage aims to enhance performance by expanding this clean set. PSSCL demonstrates significant improvement across various benchmarks when compared with state-of-the-art methods. The code will be available at https://***/LanXiaoPang613/PSSCL. © 2024, The Authors. All rights reserved.

关键词： Deep neural networks

来源：评论

学校读者我要写书评

暂无评论

Efficient Perspective-Correct 3D Gaussian Splatting Using Hybrid Transparency

arXiv

引用

arXiv 2024年

作者： Hahlbohm, Florian Friederichs, Fabian Weyrich, Tim Franke, Linus Kappel, Moritz Castillo, Susana Stamminger, Marc Eisemann, Martin Magnor, Marcus Computer Graphics Lab TU Braunschweig Germany Visual Computing Erlangen FAU Erlangen-Nürnberg Germany University College London United Kingdom University of New Mexico United States

3D Gaussian Splats (3DGS) have proven a versatile rendering primitive, both for inverse rendering as well as real-time exploration of scenes. In these applications, coherence across camera frames and multiple views is crucial, be it for robust convergence of a scene reconstruction or for artifact-free fly-throughs. Recent work started mitigating artifacts that break multi-view coherence, including popping artifacts due to inconsistent transparency sorting and perspective-correct outlines of (2D) splats. At the same time, real-time requirements forced such implementations to accept compromises in how transparency of large assemblies of 3D Gaussians is resolved, in turn breaking coherence in other ways. In our work, we aim at achieving maximum coherence, by rendering fully perspective-correct 3D Gaussians while using a high-quality approximation of accurate blending, hybrid transparency, on a per-pixel level, in order to retain real-time frame rates. Our fast and perspectively accurate approach for evaluation of 3D Gaussians does not require matrix inversions, thereby ensuring numerical stability and eliminating the need for special handling of degenerate splats, and the hybrid transparency formulation for blending maintains similar quality as fully resolved per-pixel transparencies at a fraction of the rendering costs. We further show that each of these two components can be independently integrated into Gaussian splatting systems. In combination, they achieve up to 2× higher frame rates, 2× faster optimization, and equal or better image quality with fewer rendering artifacts compared to traditional 3DGS on common benchmarks. Copyright © 2024, The Authors. All rights reserved.

关键词： Pixels

来源：评论

学校读者我要写书评

暂无评论

Retrieval Augmented Recipe Generation

arXiv

引用

arXiv 2024年

作者： Liu, Guoshan Yin, Hailong Zhu, Bin Chen, Jingjing Ngo, Chong-Wah Jiang, Yu-Gang Shanghai Key Lab of Intelligent Information Processing School of Computer Science Fudan University China Shanghai Collaborative Innovation Center on Intelligent Visual Computing China Singapore Management University Singapore

The growing interest in generating recipes from food images has drawn substantial research attention in recent years. Existing works for recipe generation primarily utilize a two-stage training method—first predicting ingredients from a food image and then generating instructions from both the image and ingredients. Large Multi-modal Models (LMMs), which have achieved notable success across a variety of vision and language tasks, shed light on generating both ingredients and instructions directly from images. Nevertheless, LMMs still face the common issue of hallucinations during recipe generation, leading to suboptimal performance. To tackle this issue, we propose a retrieval augmented large multimodal model for recipe generation. We first introduce Stochastic Diversified Retrieval Augmentation (SDRA) to retrieve recipes semantically related to the image from an existing datastore as a supplement, integrating them into the prompt to add diverse and rich context to the input image. Additionally, Self-Consistency Ensemble Voting mechanism is proposed to determine the most confident prediction recipes as the final output. It calculates the consistency among generated recipe candidates, which use different retrieval recipes as context for generation. Extensive experiments validate the effectiveness of our proposed method, which demonstrates state-of-the-art (SOTA) performance in recipe generation on the Recipe1M dataset. © 2024, CC BY-NC-ND.

关键词： Food ingredients

来源：评论

学校读者我要写书评

暂无评论

Attention Modules Improve Image-Level Anomaly Detection for Industrial Inspection: A DifferNet Case Study

arXiv

引用

arXiv 2023年

作者： Vieira e Silva, André Luiz Simões, Francisco Kowerko, Danny Schlosser, Tobias Battisti, Felipe Teichrieb, Veronica Voxar Labs Centro de Informática Universidade Federal de Pernambuco Brazil Media Computing Chemnitz University of Technology Germany Visual Computing Lab DC Universidade Federal Rural de Pernambuco Brazil

Within (semi-)automated visual industrial inspection, learning-based approaches for assessing visual defects, including deep neural networks, enable the processing of otherwise small defect patterns in pixel size on high-resolution imagery. The emergence of these often rarely occurring defect patterns explains the general need for labeled data corpora. To alleviate this issue and advance the current state of the art in unsupervised visual inspection, this work proposes a DifferNet-based solution enhanced with attention modules: AttentDifferNet. It improves image-level detection and classification capabilities on three visual anomaly detection datasets for industrial inspection: InsPLAD-fault, MVTec AD, and Semiconductor Wafer. In comparison to the state of the art, AttentDifferNet achieves improved results, which are, in turn, highlighted throughout our quali-quantitative study. Our quantitative evaluation shows an average improvement - compared to DifferNet - of 1.77 ± 0.25 percentage points in overall AUROC considering all three datasets, reaching SOTA results in InsPLAD-fault, an industrial inspection in-the-wild dataset. As our variants to AttentDifferNet show great prospects in the context of currently investigated approaches, a baseline is formulated, emphasizing the importance of attention for industrial anomaly detection both in the wild and in controlled environments. © 2023, CC BY-NC-SA.

关键词： Anomaly detection

来源：评论

学校读者我要写书评

暂无评论

Psscl: A Progressive Sample Selection Framework with Contrastive Loss Designed for Noisy labels

SSRN

引用

SSRN 2024年

关键词： Deep neural networks

来源：评论

学校读者我要写书评

暂无评论

Vicinity Vision Transformer

引用

IEEE Transactions on Pattern Analysis and Machine Intelligence 2023年第10期45卷 12635-12649页

作者： Sun, Weixuan Qin, Zhen Deng, Hui Wang, Jianyuan Zhang, Yi Zhang, Kaihao Barnes, Nick Birchfield, Stan Kong, Lingpeng Zhong, Yiran Australian National University The School of Computing CanberraACT2601 Australia The SenseTime Research Shanghai200233 China Northwestern Polytechnical University The School of Electronics and Information Xi'an710072 China University of Oxford The Visual Geometry Group OxfordOX1 4BH United Kingdom The Nvidia RedmondWA98052 United States The University of Hong Kong Hong Kong The Shanghai Ai Lab Shanghai200231 China

Vision transformers have shown great success on numerous computer vision tasks. However, their central component, softmax attention, prohibits vision transformers from scaling up to high-resolution images, due to both the computational complexity and memory footprint being quadratic. Linear attention was introduced in natural language processing (NLP) which reorders the self-attention mechanism to mitigate a similar issue, but directly applying existing linear attention to vision may not lead to satisfactory results. We investigate this problem and point out that existing linear attention methods ignore an inductive bias in vision tasks, i.e., 2D locality. In this article, we propose Vicinity Attention, which is a type of linear attention that integrates 2D locality. Specifically, for each image patch, we adjust its attention weight based on its 2D Manhattan distance from its neighbouring patches. In this case, we achieve 2D locality in a linear complexity where the neighbouring image patches receive stronger attention than far away patches. In addition, we propose a novel Vicinity Attention Block that is comprised of Feature Reduction Attention (FRA) and Feature Preserving Connection (FPC) in order to address the computational bottleneck of linear attention approaches, including our Vicinity Attention, whose complexity grows quadratically with respect to the feature dimension. The Vicinity Attention Block computes attention in a compressed feature space with an extra skip connection to retrieve the original feature distribution. We experimentally validate that the block further reduces computation without degenerating the accuracy. Finally, to validate the proposed methods, we build a linear vision transformer backbone named Vicinity Vision Transformer (VVT). Targeting general vision tasks, we build VVT in a pyramid structure with progressively reduced sequence length. We perform extensive experiments on CIFAR-100, ImageNet-1 k, and ADE20 K datasets to validate the

关键词： Image resolution

来源：评论

学校读者我要写书评

暂无评论

Rapidvol: Rapid Reconstruction of 3D Ultrasound Volumes from Sensorless 2D Scans

Rapidvol: Rapid Reconstruction of 3D Ultrasound Volumes from...

引用

IEEE International Symposium on Biomedical Imaging

作者： Mark C. Eid Pak-Hei Yeung Madeleine K. Wyburd João F. Henriques Ana I.L. Namburete Visual Geometry Group University of Oxford U.K. Oxford Machine Learning in Neuroimaging Lab University of Oxford U.K. College of Computing and Data Science Nanyang Technological University Singapore

ISBN: (数字)9798331520526

ISBN: (纸本)9798331520533

Two-dimensional (2D) freehand ultrasonography is a widely used medical imaging modality, particularly in obstetrics and gynaecology. However, it only captures 2D cross-sectional views of inherently 3D anatomies, losing valuable contextual information. As an alternative to costly 3D ultrasound (US) scanners, 3D volumes can be artificially reconstructed from 2D scans, but this is usually prohibitively slow. Hence, we propose RapidVol: a neural representation framework to speed up slice-to-volume US reconstruction. We use tensor-rank decomposition to decompose the typical 3D volume into tri-planes, which are stored alongside a small neural network. With a set of 2D US scans and their estimated 3D orientation, RapidVol can achieve complete 3D reconstruction. To evaluate our method, we form reconstructions from real fetal brain scans, and then request novel cross-sectional views. Compared to prior fully implicit (e.g. neural radiance field) approaches, our method is over 3x quicker, 46% more accurate, and more robust to errors in pose estimation. We also demonstrate that further speed-up is achievable by reconstructing from a structural prior rather than from random initialisation.

关键词： Three-dimensional displays Accuracy Two-dimensional displays Pose estimation Ultrasonography Neural radiance field Probes Obstetrics Image reconstruction Biomedical imaging

来源：评论

学校读者我要写书评

暂无评论

Detection Hub: Unifying Object Detection Datasets via Query Adaptation on Language Embedding

Detection Hub: Unifying Object Detection Datasets via Query ...

引用

Conference on Computer Vision and Pattern Recognition (CVPR)

作者： Lingchen Meng Xiyang Dai Yinpeng Chen Pengchuan Zhang Dongdong Chen Mengchen Liu Jianfeng Wang Zuxuan Wu Lu Yuan Yu-Gang Jiang Shanghai Key Lab of Intell. Info. Processing School of CS Fudan University Shanghai Collaborative Innovation Center of Intelligent Visual Computing Microsoft

Combining multiple datasets enables performance boost on many computer vision tasks. But similar trend has not been witnessed in object detection when combining multiple datasets due to two inconsistencies among detection datasets: taxonomy difference and domain gap. In this paper, we address these challenges by a new design (named Detection Hub) that is dataset-aware and category-aligned. It not only mitigates the dataset inconsistency but also provides coherent guidance for the detector to learn across multiple datasets. In particular, the dataset-aware design is achieved by learning a dataset embedding that is used to adapt object queries as well as convolutional kernels in detection heads. The categories across datasets are semantically aligned into a unified space by replacing one-hot category representations with word embedding and leveraging the semantic coherence of language embedding. Detection Hub fulfills the benefits of large data on object detection. Experiments demonstrate that joint training on multiple datasets achieves significant performance gains over training on each dataset alone. Detection Hub further achieves SoTA performance on UODB benchmark with wide variety of datasets.

关键词：

来源：评论

学校读者我要写书评

暂无评论

MSMDFusion: Fusing LiDAR and Camera at Multiple Scales with Multi-Depth Seeds for 3D Object Detection

MSMDFusion: Fusing LiDAR and Camera at Multiple Scales with ...

引用

Conference on Computer Vision and Pattern Recognition (CVPR)

作者： Yang Jiao Zequn Jie Shaoxiang Chen Jingjing Chen Lin Ma Yu-Gang Jiang Shanghai Key Lab of Intell. Info. Processing School of CS Fudan University Shanghai Collaborative Innovation Center of Intelligent Visual Computing Meituan

Fusing LiDAR and camera information is essential for accurate and reliable 3D object detection in autonomous driving systems. This is challenging due to the difficulty of combining multi-granularity geometric and semantic features from two drastically different modalities. Recent approaches aim at exploring the semantic densities of camera features through lifting points in 2D camera images (referred to as “seeds”) into 3D space, and then incorporate 2D semantics via cross-modal interaction or fusion techniques. However, depth information is under-investigated in these approaches when lifting points into 3D space, thus 2D semantics can not be reliably fused with 3D points. Moreover, their multi-modal fusion strategy, which is implemented as concatenation or attention, either can not effectively fuse 2D and 3D information or is unable to perform fine-grained interactions in the voxel space. To this end, we propose a novel framework with better utilization of the depth information and fine-grained cross-modal interaction between LiDAR and camera, which consists of two important components. First, a Multi-Depth Unprojection (MDU) method is used to enhance the depth quality of the lifted points at each interaction level. Second, a Gated Modality-Aware Convolution (GMA-Conv) block is applied to modulate voxels involved with the camera modality in a fine-grained manner and then aggregate multi-modal features into a unified space. Together they provide the detection head with more comprehensive features from LiDAR and camera. On the nuScenes test benchmark, our proposed method, abbreviated as MSMD-Fusion, achieves state-of-the-art results on both 3D object detection and tracking tasks without using test-time-augmentation and ensemble techniques. The code is available at https://***/SxJyJay/MSMDFusion.

关键词：

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：