检索结果-内蒙古大学图书馆

Proceedings of the 36th International Conference on Neural Information Processing systems

作者： Huiyang Shao Qianqian Xu Zhiyong Yang Shilong Bao Qingming Huang Key Lab of Intell. Info. Process. Inst. of Comput. Tech. CAS and School of Computer Science and Tech. University of Chinese Academy of Sciences Key Lab of Intell. Info. Process. Inst. of Comput. Tech. CAS School of Computer Science and Tech. University of Chinese Academy of Sciences State Key Lab of Info. Security Inst. of Info. Engineering CAS and School of Cyber Security University of Chinese Academy of Sciences Key Lab of Intell. Info. Process. Inst. of Comput. Tech. CAS and School of Computer Science and Tech. University of Chinese Academy of Sciences and BDKM University of Chinese Academy of Sciences and Peng Cheng Laboratory

ISBN: (纸本)9781713871088

The Partial Area Under the ROC Curve (PAUC), typically including One-way Partial AUC (OPAUC) and Two-way Partial AUC (TPAUC), measures the average performance of a binary classifier within a specific false positive rate and/or true positive rate interval, which is a widely adopted measure when decision constraints must be considered. Consequentiy, PAUC optimization has naturally attracted increasing attention in the machine learning community within the last few years. Nonetheless, most of the existing methods could only optimize PAUC approximately, leading to inevitable biases that are not controllable. Fortunately, a recent work presents an unbiased formulation of the PAUC optimization problem via distributional robust optimization. However, it is based on the pair-wise formulation of AUC, which suffers from the limited scalability w.r.t. sample size and a slow convergence rate, especially for TPAUC. To address this issue, we present a simpler reformulation of the problem in an asymptotically unbiased and instance-wise manner. For both OPAUC and TPAUC, we come to a nonconvex strongly concave minimax regularized problem of instance-wise functions. On top of this, we employ an efficient solver enjoys a linear per-iteration computational complexity w.r.t. the sample size and a time-complexity of O(ε-1/3) to reach a ε stationary point. Furthermore, we find that the minimax reformulation also facilitates the theoretical analysis of generalization error as a byproduct. Compared with the existing results, we present new error bounds that are much easier to prove and could deal with hypotheses with real-valued outputs. Finally, extensive experiments on several benchmark datasets demonstrate the effectiveness of our method.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Building Bridge Across the Time: Disruption and Restoration of Murals In the Wild

Building Bridge Across the Time: Disruption and Restoration ...

引用

International Conference on Computer Vision (ICCV)

作者： Huiyang Shao Qianqian Xu Peisong Wen Peifeng Gao Zhiyong Yang Qingming Huang Key Lab of Intell. Info. Process. Inst. of Comput. Tech. CAS School of Computer Science and Tech. University of Chinese Academy of Sciences State Key Lab of Info. Security Inst. of Info. Engineering CAS School of Cyber Security University of Chinese Academy of Sciences BDKM University of Chinese Academy of Sciences Peng Cheng Laboratory

In this paper, we focus on the mural-restoration task, which aims to detect damaged regions in the mural and repaint them automatically. Different from traditional image restoration tasks like in/out/blind-painting and image renovation, the corrupted mural suffers from more complicated degradation. However, existing mural-restoration methods and datasets still focus on simple degradation like masking. Such a significant gap prevents mural-restoration from being applied to real scenarios. To fill this gap, in this work, we propose a systematic framework to simulate the physical process for damaged murals and provide a new benchmark dataset for mural-restoration. Limited by the simplification of the data synthesis process, the previous mural-restoration methods suffer from poor performance in our proposed dataset. To handle this problem, we propose the Attention Diffusion Framework (ADF) for this challenging task. Within the framework, a damage attention map module is proposed to estimate the damage extent. Facing the diversity of defects, we propose a series of loss functions to choose repair strategies adaptively. Finally, experimental results support the effectiveness of the proposed framework in terms of both mural synthesis and restoration.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Detection Transformer with Stable Matching

arXiv

引用

arXiv 2023年

作者： Liu, Shilong Ren, Tianhe Chen, Jiayu Zeng, Zhaoyang Zhang, Hao Li, Feng Li, Hongyang Huang, Jun Su, Hang Zhu, Jun Zhang, Lei Dept. of Comp. Sci. and Tech. BNRist Center State Key Lab for Intell. Tech. & Sys. Institute for AI Tsinghua-Bosch Joint Center for ML Tsinghua University China Alibaba Group China The Hong Kong University of Science and Technology Hong Kong South China University of Technology China

This paper is concerned with the matching stability problem across different decoder layers in DEtection TRansformers (DETR). We point out that the unstable matching in DETR is caused by a multi-optimization path problem, which is highlighted by the one-to-one matching design in DETR. To address this problem, we show that the most important design is to use and only use positional metrics (like IOU) to supervise classification scores of positive examples. Under the principle, we propose two simple yet effective modifications by integrating positional metrics to DETR’s classification loss and matching cost, named position-supervised loss and position-modulated cost. We verify our methods on several DETR variants. Our methods show consistent improvements over baselines. By integrating our methods with DINO, we achieve 50.4 and 51.5 AP on the COCO detection benchmark using ResNet-50 backbones under 1× (12 epochs) and 2× (24 epochs) training settings, achieving a new record under the same setting. We achieve 63.8 AP on COCO detection test-dev with a Swin-Large backbone. Our code will be made available at https://***/IDEA-Research/Stable-DINO. Copyright © 2023, The Authors. All rights reserved.

关键词： Machine learning

来源：评论

学校读者我要写书评

暂无评论

Detection Transformer with Stable Matching

Detection Transformer with Stable Matching

引用

International Conference on Computer Vision (ICCV)

作者： Shilong Liu Tianhe Ren Jiayu Chen Zhaoyang Zeng Hao Zhang Feng Li Hongyang Li Jun Huang Hang Su Jun Zhu Lei Zhang Dept. of Comp. Sci. and Tech. BNRist Center State Key Lab for Intell. Tech. & Sys. Institute for AI Tsinghua-Bosch Joint Center for ML Tsinghua University International Digital Economy Academy (IDEA) Platform of AI (PAI) Alibaba Group The Hong Kong University of Science and Technology South China University of Technology

关键词：

来源：评论

学校读者我要写书评

暂无评论

One Transformer Fits All Distributions in Multi-Modal Diffusion at Scale

arXiv

引用

arXiv 2023年

作者： Bao, Fan Nie, Shen Xue, Kaiwen Li, Chongxuan Pu, Shi Wang, Yaole Yue, Gang Cao, Yue Su, Hang Zhu, Jun Dept. of Comp. Sci. & Tech. Institute for AI Tsinghua-Huawei Joint Center for AI BNRist Center State Key Lab for Intell. Tech. & Sys. Tsinghua University China ShengShu Beijing China Gaoling School of AI Renmin University of China Beijing Key Lab of Big Data Management and Analysis Methods Beijing China Beijing Academy of Artificial Intelligence China Guangzhou China

This paper proposes a unified diffusion framework (dubbed UniDiffuser) to fit all distributions relevant to a set of multi-modal data in one model. Our key insight is – learning diffusion models for marginal, conditional, and joint distributions can be unified as predicting the noise in the perturbed data, where the perturbation levels (i.e. timesteps) can be different for different modalities. Inspired by the unified view, UniDiffuser learns all distributions simultaneously with a minimal modification to the original diffusion model – perturbs data in all modalities instead of a single modality, inputs individual timesteps in different modalities, and predicts the noise of all modalities instead of a single modality. UniDiffuser is parameterized by a transformer for diffusion models to handle input types of different modalities. Implemented on large-scale paired image-text data, UniDiffuser is able to perform image, text, text-to-image, image-to-text, and image-text pair generation by setting proper timesteps without additional overhead. In particular, UniDiffuser is able to produce perceptually realistic samples in all tasks and its quantitative results (e.g., the FID and CLIP score) are not only superior to existing general-purpose models but also comparable to the bespoken models (e.g., Stable Diffusion and DALL·E 2) in representative tasks (e.g., text-to-image generation). Our code is available at https://***/thu-ml/unidiffuser. Copyright © 2023, The Authors. All rights reserved.

关键词： Diffusion

来源：评论

学校读者我要写书评

暂无评论

Bi-level score matching for learning energy-based latent variable models 34

Bi-level score matching for learning energy-based latent var...

引用

34th Conference on Neural Information Processing systems, NeurIPS 2020

作者： Bao, Fan Li, Chongxuan Xu, Kun Su, Hang Zhu, Jun Zhang, Bo Dept. of Comp. Sci. & Tech. Institute for AI THBI Lab. BNRist Center State Key Lab for Intell. Tech. & Sys. Tsinghua University Beijing China

Score matching (SM) [24] provides a compelling approach to learn energy-based models (EBMs) by avoiding the calculation of partition function. However, it remains largely open to learn energy-based latent variable models (EBLVMs), except some special cases. This paper presents a bi-level score matching (BiSM) method to learn EBLVMs with general structures by reformulating SM as a bilevel optimization problem. The higher level introduces a variational posterior of the latent variables and optimizes a modified SM objective, and the lower level optimizes the variational posterior to fit the true posterior. To solve BiSM efficiently, we develop a stochastic optimization algorithm with gradient unrolling. Theoretically, we analyze the consistency of BiSM and the convergence of the stochastic algorithm. Empirically, we show the promise of BiSM in Gaussian restricted Boltzmann machines and highly nonstructural EBLVMs parameterized by deep convolutional neural networks. BiSM is comparable to the widely adopted contrastive divergence and SM methods when they are applicable;and can learn complex EBLVMs with intractable posteriors to generate natural images. © 2020 Neural information processing systems foundation. All rights reserved.

关键词： Convolutional neural networks

来源：评论

学校读者我要写书评

暂无评论

Grounding DINO: Marrying DINO with Grounded Pre-Training for Open-Set Object Detection

arXiv

引用

arXiv 2023年

作者： Liu, Shilong Zeng, Zhaoyang Ren, Tianhe Li, Feng Zhang, Hao Yang, Jie Jiang, Qing Li, Chunyuan Yang, Jianwei Su, Hang Zhu, Jun Zhang, Lei Dept. of Comp. Sci. and Tech. BNRist Center State Key Lab for Intell. Tech. & Sys. Institute for AI Tsinghua-Bosch Joint Center for ML Tsinghua University China China The Hong Kong University of Science and Technology Hong Kong The Chinese University of Hong Kong Shenzhen China Microsoft Research Redmond United States South China University of Technology China

In this paper, we develop an open-set object detector, called Grounding DINO, by marrying Transformer-based detector DINO with grounded pre-training, which can detect arbitrary objects with human inputs such as category names or referring expressions. The key solution of open-set object detection is introducing language to a closed-set detector for open-set concept generalization. To effectively fuse language and vision modalities, we conceptually divide a closed-set detector into three phases and propose a tight fusion solution, which includes a feature enhancer, a language-guided query selection, and a cross-modality decoder for modalities fusion. We first pre-train Grounding DINO on large-scale datasets, including object detection data, grounding data, and caption data, and evaluate the model on both open-set object detection and referring object detection benchmarks. Grounding DINO performs remarkably well on all three settings, including benchmarks on COCO, LVIS, ODinW, and RefCOCO/+/g. Grounding DINO achieves a 52.5 AP on the COCO zero-shot1 detection benchmark. It sets a new record on the ODinW zero-shot benchmark with a mean 26.1 AP. We release some checkpoints and inference codes at https://***/IDEA-Research/GroundingDINO. Copyright © 2023, The Authors. All rights reserved.

关键词： Object detection

来源：评论

学校读者我要写书评

暂无评论

DAB-DETR: DYNAMIC ANCHOR BOXES ARE BETTER QUERIES FOR DETR

arXiv

引用

arXiv 2022年

作者： Liu, Shilong Li, Feng Zhang, Hao Yang, Xiao Qi, Xianbiao Su, Hang Zhu, Jun Zhang, Lei Dept. of Comp. Sci. and Tech. BNRist Center State Key Lab for Intell. Tech. & Sys. Institute for AI Tsinghua-Bosch Joint Center for ML Tsinghua University China China Hong Kong University of Science and Technology Hong Kong Peng Cheng Laboratory Guangdong Shenzhen China

We present in this paper a novel query formulation using dynamic anchor boxes for DETR (DEtection TRansformer) and offer a deeper understanding of the role of queries in DETR. This new formulation directly uses box coordinates as queries in Transformer decoders and dynamically updates them layer-by-layer. Using box coordinates not only helps using explicit positional priors to improve the query-to-feature similarity and eliminate the slow training convergence issue in DETR, but also allows us to modulate the positional attention map using the box width and height information. Such a design makes it clear that queries in DETR can be implemented as performing soft ROI pooling layer-by-layer in a cascade manner. As a result, it leads to the best performance on MS-COCO benchmark among the DETR-like detection models under the same setting, e.g., AP 45.7% using ResNet50-DC5 as backbone trained in 50 epochs. We also conducted extensive experiments to confirm our analysis and verify the effectiveness of our methods. Code is available at https://***/SlongLiu/DAB-DETR. Copyright © 2022, The Authors. All rights reserved.

关键词： Benchmarking

来源：评论

学校读者我要写书评

暂无评论

Maximum Likelihood Training for Score-Based Diffusion ODEs by High-Order Denoising Score Matching

arXiv

引用

arXiv 2022年

作者： Lu, Cheng Zheng, Kaiwen Bao, Fan Chen, Jianfei Li, Chongxuan Zhu, Jun Dept. of Comp. Sci. & Tech. Institute for AI Tsinghua-Bosch Joint Center for ML BNRist Center State Key Lab for Intell. Tech. & Sys. Tsinghua University Peng Cheng Laboratory China Gaoling School of AI Renmin University of China Beijing Key Lab of Big Data Management and Analysis Methods Beijing China

Score-based generative models have excellent performance in terms of generation quality and likelihood. They model the data distribution by matching a parameterized score network with first-order data score functions. The score network can be used to define an ODE ("score-based diffusion ODE") for exact likelihood evaluation. However, the relationship between the likelihood of the ODE and the score matching objective is unclear. In this work, we prove that matching the first-order score is not sufficient to maximize the likelihood of the ODE, by showing a gap between the maximum likelihood and score matching objectives. To fill up this gap, we show that the negative likelihood of the ODE can be bounded by controlling the first, second, and third-order score matching errors;and we further present a novel high-order denoising score matching method to enable maximum likelihood training of score-based diffusion ODEs. Our algorithm guarantees that the higher-order matching error is bounded by the training error and the lower-order errors. We empirically observe that by high-order score matching, score-based diffusion ODEs achieve better likelihood on both synthetic data and CIFAR-10, while retaining the high generation quality. Copyright © 2022, The Authors. All rights reserved.

关键词： Diffusion

来源：评论

学校读者我要写书评

暂无评论

Estimating the Optimal Covariance with Imperfect Mean in Diffusion Probabilistic Models

arXiv

引用

arXiv 2022年

作者： Bao, Fan Li, Chongxuan Sun, Jiacheng Zhu, Jun Zhang, Bo Dept. of Comp. Sci. & Tech. Institute for AI Tsinghua-Huawei Joint Center for AI BNRist Center State Key Lab for Intell. Tech. & Sys. Tsinghua University China Gaoling School of AI Renmin University of China Beijing Key Lab of Big Data Management and Analysis Methods Beijing China Huawei Noah's Ark Lab. China

Diffusion probabilistic models (DPMs) are a class of powerful deep generative models (DGMs). Despite their success, the iterative generation process over the full timesteps is much less efficient than other DGMs such as GANs. Thus, the generation performance on a subset of timesteps is crucial, which is greatly influenced by the covariance design in DPMs. In this work, we consider diagonal and full covariances to improve the expressive power of DPMs. We derive the optimal result for such covariances, and then correct it when the mean of DPMs is imperfect. Both the optimal and the corrected ones can be decomposed into terms of conditional expectations over functions of noise. Building upon it, we propose to estimate the optimal covariance and its correction given imperfect mean by learning these conditional expectations. Our method can be applied to DPMs with both discrete and continuous timesteps. We consider the diagonal covariance in our implementation for computational efficiency. For an efficient practical implementation, we adopt a parameter sharing scheme and a two-stage training process. Empirically, our method outperforms a wide variety of covariance design on likelihood results, and improves the sample quality especially on a small number of timesteps. Copyright © 2022, The Authors. All rights reserved.

关键词： Iterative methods

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：