检索结果-内蒙古大学图书馆

38th Conference on Neural Information Processing Systems, NeurIPS 2024

作者： Chung, Hojun Lee, Junseo Kim, Minsoo Kim, Dohyeong Oh, Songhwai Interdisciplinary Program in Artificial Intelligence ASRI Seoul National University Korea Republic of Department of Electrical and Computer Engineering ASRI Seoul National University Korea Republic of

Training agents that are robust to environmental changes remains a significant challenge in deep reinforcement learning (RL). Unsupervised environment design (UED) has recently emerged to address this issue by generating a set of training environments tailored to the agent's capabilities. While prior works demonstrate that UED has the potential to learn a robust policy, their performance is constrained by the capabilities of the environment generation. To this end, we propose a novel UED algorithm, adversarial environment design via regret-guided diffusion models (ADD). The proposed method guides the diffusion-based environment generator with the regret of the agent to produce environments that the agent finds challenging but conducive to further improvement. By exploiting the representation power of diffusion models, ADD can directly generate adversarial environments while maintaining the diversity of training environments, enabling the agent to effectively learn a robust policy. Our experimental results demonstrate that the proposed method successfully generates an instructive curriculum of environments, outperforming UED baselines in zero-shot generalization across novel, out-of-distribution environments. Project page: https://***/projects/ADD. © 2024 Neural information processing systems foundation. All rights reserved.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Semantic Token Reweighting for Interpretable and Controllable Text Embeddings in CLIP

Semantic Token Reweighting for Interpretable and Controllabl...

引用

2024 Conference on Empirical Methods in Natural Language Processing, EMNLP 2024

作者： Kim, Eunji Shim, Kyuhong Chang, Simyung Yoon, Sungroh Department of Electrical and Computer Engineering Seoul National University Korea Republic of Qualcomm AI Research an initiative of Qualcomm Technologies Inc. Qualcomm Korea YH Korea Republic of Interdisciplinary Program in Artificial Intelligence Seoul National University Korea Republic of

ISBN: (纸本)9798891761681

A text encoder within Vision-Language Models (VLMs) like CLIP plays a crucial role in translating textual input into an embedding space shared with images, thereby facilitating the interpretative analysis of vision tasks through natural language. Despite the varying significance of different textual elements within a sentence depending on the context, efforts to account for variation of importance in constructing text embeddings have been lacking. We propose a framework of Semantic Token Reweighting to build Interpretable text embeddings (SToRI), which incorporates controllability as well. SToRI refines the text encoding process in CLIP by differentially weighting semantic elements based on contextual importance, enabling finer control over emphasis responsive to data-driven insights and user preferences. The efficacy of SToRI is demonstrated through comprehensive experiments on few-shot image classification and image retrieval tailored to user preferences. © 2024 Association for Computational Linguistics.

关键词： Embeddings

来源：评论

学校读者我要写书评

暂无评论

Unsupervised Homography Estimation on Multimodal Image Pair via Alternating Optimization 38

Unsupervised Homography Estimation on Multimodal Image Pair ...

引用

38th Conference on Neural Information Processing Systems, NeurIPS 2024

作者： Song, Sanghyeob Lew, Jaihyun Jang, Hyemi Yoon, Sungroh Interdisciplinary Program in Artificial Intelligence Seoul National University Korea Republic of Department of Electrical and Computer Engineering Seoul National University Korea Republic of Samsung Electro-Mechanics Korea Republic of

Estimating the homography between two images is crucial for mid- or high-level vision tasks, such as image stitching and fusion. However, using supervised learning methods is often challenging or costly due to the difficulty of collecting ground-truth data. In response, unsupervised learning approaches have emerged. Most early methods, though, assume that the given image pairs are from the same camera or have minor lighting differences. Consequently, while these methods perform effectively under such conditions, they generally fail when input image pairs come from different domains, referred to as multimodal image pairs. To address these limitations, we propose AltO, an unsupervised learning framework for estimating homography in multimodal image pairs. Our method employs a two-phase alternating optimization framework, similar to Expectation-Maximization (EM), where one phase reduces the geometry gap and the other addresses the modality gap. To handle these gaps, we use Barlow Twins loss for the modality gap and propose an extended version, Geometry Barlow Twins, for the geometry gap. As a result, we demonstrate that our method, AltO, can be trained on multimodal datasets without any ground-truth data. It not only outperforms other unsupervised methods but is also compatible with various architectures of homography estimators. The source code can be found at: https://***/songsang7/AltO. © 2024 Neural information processing systems foundation. All rights reserved.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Textual Training for the Hassle-Free Removal of Unwanted Visual Data: Case Studies on OOD and Hateful Image Detection 38

Textual Training for the Hassle-Free Removal of Unwanted Vis...

引用

38th Conference on Neural Information Processing Systems, NeurIPS 2024

作者： Lee, Saehyung Mok, Jisoo Park, Sangha Shin, Yongho Jung, Dahuin Yoon, Sungroh Department of Electrical and Computer Engineering Seoul National University Korea Republic of Qualcomm Korea YH Seoul Korea Republic of School of Computer Science and Engineering Soongsil University Korea Republic of Interdisciplinary Program in Artificial Intelligence Seoul National University Korea Republic of

In our study, we explore methods for detecting unwanted content lurking in visual datasets. We provide a theoretical analysis demonstrating that a model capable of successfully partitioning visual data can be obtained using only textual data. Based on the analysis, we propose Hassle-Free Textual Training (HFTT), a streamlined method capable of acquiring detectors for unwanted visual content, using only synthetic textual data in conjunction with pre-trained vision-language models. HFTT features an innovative objective function that significantly reduces the necessity for human involvement in data annotation. Furthermore, HFTT employs a clever textual data synthesis method, effectively emulating the integration of unknown visual data distribution into the training process at no extra cost. The unique characteristics of HFTT extend its utility beyond traditional out-of-distribution detection, making it applicable to tasks that address more abstract concepts. We complement our analyses with experiments in out-of-distribution detection and hateful image detection. Our codes are available at https://***/Saehyung-Lee/HFTT. © 2024 Neural information processing systems foundation. All rights reserved.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Introducing Spectral Attention for Long-Range Dependency in Time Series Forecasting 38

Introducing Spectral Attention for Long-Range Dependency in ...

引用

38th Conference on Neural Information Processing Systems, NeurIPS 2024

作者： Kang, Bong Gyun Lee, Dongjun Kim, HyunGi Chung, DoHyun Yoon, Sungroh Interdisciplinary Program in Artificial Intelligence Seoul National University Korea Republic of Department of Electrical and Computer Engineering Seoul National University Korea Republic of Department of Future Automotive Mobility Seoul National University Korea Republic of

Sequence modeling faces challenges in capturing long-range dependencies across diverse tasks. Recent linear and transformer-based forecasters have shown superior performance in time series forecasting. However, they are constrained by their inherent inability to effectively address long-range dependencies in time series data, primarily due to using fixed-size inputs for prediction. Furthermore, they typically sacrifice essential temporal correlation among consecutive training samples by shuffling them into mini-batches. To overcome these limitations, we introduce a fast and effective Spectral Attention mechanism, which preserves temporal correlations among samples and facilitates the handling of long-range information while maintaining the base model structure. Spectral Attention preserves long-period trends through a low-pass filter and facilitates gradient to flow between samples. Spectral Attention can be seamlessly integrated into most sequence models, allowing models with fixed-sized look-back windows to capture long-range dependencies over thousands of steps. Through extensive experiments on 11 real-world time series datasets using 7 recent forecasting models, we consistently demonstrate the efficacy of our Spectral Attention mechanism, achieving state-of-the-art results. © 2024 Neural information processing systems foundation. All rights reserved.

关键词：

来源：评论

学校读者我要写书评

暂无评论

SF(DA)2: SOURCE-FREE DOMaiN ADAPTATION THROUGH THE LENS OF DATA AUGMENTATION 12

SF(DA)2: SOURCE-FREE DOMAIN ADAPTATION THROUGH THE LENS OF D...

引用

12th International Conference on Learning Representations, ICLR 2024

作者： Hwang, Uiwon Lee, Jonghyun Shin, Juhyeon Yoon, Sungroh Division of Digital Healthcare Yonsei University Korea Republic of Department of Electrical and Computer Engineering Seoul National University Korea Republic of Interdisciplinary Program in Artificial Intelligence Seoul National University Korea Republic of

In the face of the deep learning model's vulnerability to domain shift, source-free domain adaptation (SFDA) methods have been proposed to adapt models to new, unseen target domains without requiring access to source domain data. Although the potential benefits of applying data augmentation to SFDA are attractive, several challenges arise such as the dependence on prior knowledge of class-preserving transformations and the increase in memory and computational requirements. In this paper, we propose Source-free Domain Adaptation Through the Lens of Data Augmentation (SF(DA)2), a novel approach that leverages the benefits of data augmentation without suffering from these challenges. We construct an augmentation graph in the feature space of the pretrained model using the neighbor relationships between target features and propose spectral neighborhood clustering to identify partitions in the prediction space. Furthermore, we propose implicit feature augmentation and feature disentanglement as regularization loss functions that effectively utilize class semantic information within the feature space. These regularizers simulate the inclusion of an unlimited number of augmented target features into the augmentation graph while minimizing computational and memory demands. Our method shows superior adaptation performance in SFDA scenarios, including 2D image and 3D point cloud datasets and a highly imbalanced dataset. © 2024 12th International Conference on Learning Representations, ICLR 2024. All rights reserved.

关键词： Deep learning

来源：评论

学校读者我要写书评

暂无评论

NEW INSIGHTS FOR THE STABILITY-PLASTICITY DILEMMA IN ONLINE CONTINUAL LEARNING 11

NEW INSIGHTS FOR THE STABILITY-PLASTICITY DILEMMA IN ONLINE ...

引用

11th International Conference on Learning Representations, ICLR 2023

作者： Jung, Dahuin Lee, Dongjin Hong, Sunwon Jang, Hyemi Bae, Ho Yoon, Sungroh Department of Electrical and Computer Engineering Seoul National University Korea Republic of DeepBrain AI Inc. Korea Republic of Department of Cyber Security Ewha Womans University Korea Republic of Interdisciplinary Program in Artificial Intelligence Seoul National University Seoul08826 Korea Republic of

The aim of continual learning is to learn new tasks continuously (i.e., plasticity) without forgetting previously learned knowledge from old tasks (i.e., stability). In the scenario of online continual learning, wherein data comes strictly in a streaming manner, the plasticity of online continual learning is more vulnerable than offline continual learning because the training signal that can be obtained from a single data point is limited. To overcome the stability-plasticity dilemma in online continual learning, we propose an online continual learning framework named multi-scale feature adaptation network (MuFAN) that utilizes a richer context encoding extracted from different levels of a pre-trained network. Additionally, we introduce a novel structure-wise distillation loss and replace the commonly used batch normalization layer with a newly proposed stability-plasticity normalization module to train MuFAN that simultaneously maintains high plasticity and stability. MuFAN outperforms other state-of-the-art continual learning methods on the SVHN, CIFAR100, miniImageNet, and CORe50 datasets. Extensive experiments and ablation studies validate the significance and scalability of each proposed component: 1) multi-scale feature maps from a pre-trained encoder, 2) the structure-wise distillation loss, and 3) the stability-plasticity normalization module in MuFAN. Code is publicly available at https://***/whitesnowdrop/MuFAN. © 2023 11th International Conference on Learning Representations, ICLR 2023. All rights reserved.

关键词： Stability

来源：评论

学校读者我要写书评

暂无评论

Normality Addition via Normality Detection in Industrial Image Anomaly Detection Models

arXiv

引用

arXiv 2024年

作者： Yi, Jihun Jung, Dahuin Yoon, Sungroh Department of Electrical and Computer Engineering Seoul National University Seoul Korea Republic of School of Computer Science and Engineering Soongsil University Seoul Korea Republic of Department of Electrical and Computer Engineering and Interdisciplinary Program in AI Seoul National University Seoul Korea Republic of

The task of image anomaly detection (IAD) aims to identify deviations from normality in image data. These anomalies are patterns that deviate significantly from what the IAD model has learned from the data during training. However, in real-world scenarios, the criteria for what constitutes normality often change, necessitating the reclassification of previously anomalous instances as normal. To address this challenge, we propose a new scenario termed "normality addition," involving the post-training adjustment of decision boundaries to incorporate new normalities. To address this challenge, we propose a method called Normality Addition via Normality Detection (NAND), leveraging a vision-language model. NAND performs normality detection which detect patterns related to the intended normality within images based on textual descriptions. We then modify the results of a pre-trained IAD model to implement this normality addition. Using the benchmark dataset in IAD, MVTec AD, we establish an evaluation protocol for the normality addition task and empirically demonstrate the effectiveness of the NAND method. Copyright © 2024, The Authors. All rights reserved.

关键词： Visual languages

来源：评论

学校读者我要写书评

暂无评论

Text2PointCloud: Text-Driven Stylization for Sparse PointCloud

Text2PointCloud: Text-Driven Stylization for Sparse PointClo...

引用

44th Annual Conference on European Association for computer Graphics, EUROGRAPHICS 2023

作者： Hwang, Inwoo Kim, Hyeonwoo Lim, Donggeun Park, Inbum Kim, Young Min Seoul National University Department of Electrical and Computer Engineering Korea Republic of Seoul National University Interdisciplinary Program in Artificial Intelligence and INMC Korea Republic of

ISBN: (纸本)9783038682097

We present Text2PointCloud, a method to process sparse, noisy point cloud input and generate high-quality stylized output. Given point cloud data, our iterative pipeline stylizes and deforms points guided by a text description and gradually densifies the point cloud. As our framework utilizes the existing resources of image and text embedding, it does not require dedicated 3D datasets with high-quality textures, which are produced by skillful artists or high-resolution colored 3D models. Also, since we represent 3D shapes as a point cloud, we can visualize fine-grained geometric variations with a complex topology such as flowers or fire. To the best of our knowledge, it is the first approach for directly stylizing the uncolored, sparse point cloud input without converting it into a mesh or implicit representation, which might fail to express the original information in the measurements, especially when the object exhibits complex topology. © 2023 Authors.

关键词： Textures

来源：评论

学校读者我要写书评

暂无评论

Unsupervised homography estimation on multimodal image pair via alternating optimization 24

Unsupervised homography estimation on multimodal image pair ...

引用

Proceedings of the 38th International Conference on Neural Information Processing Systems

作者： Sanghyeob Song Jaihyun Lew Hyemi Jang Sungroh Yoon Interdisciplinary Program in Artificial Intelligence Seoul National University and Samsung Electro-Mechanics Interdisciplinary Program in Artificial Intelligence Seoul National University Department of Electrical and Computer Engineering Seoul National University Interdisciplinary Program in Artificial Intelligence Seoul National University and Department of Electrical and Computer Engineering Seoul National University

ISBN: (纸本)9798331314385

Estimating the homography between two images is crucial for mid- or high-level vision tasks, such as image stitching and fusion. However, using supervised learning methods is often challenging or costly due to the difficulty of collecting ground-truth data. In response, unsupervised learning approaches have emerged. Most early methods, though, assume that the given image pairs are from the same camera or have minor lighting differences. Consequently, while these methods perform effectively under such conditions, they generally fail when input image pairs come from different domains, referred to as multimodal image *** address these limitations, we propose AltO, an unsupervised learning framework for estimating homography in multimodal image pairs. Our method employs a two-phase alternating optimization framework, similar to Expectation-Maximization (EM), where one phase reduces the geometry gap and the other addresses the modality gap. To handle these gaps, we use Barlow Twins loss for the modality gap and propose an extended version, Geometry Barlow Twins, for the geometry gap. As a result, we demonstrate that our method, AltO, can be trained on multimodal datasets without any ground-truth data. It not only outperforms other unsupervised methods but is also compatible with various architectures of homography estimators. The source code can be found at: https://***/songsang7/AltO

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：