计算机视觉论文-2021-11-03

本专栏是计算机视觉方向论文收集积累,时间:2021年9月15日,来源:paper digest

欢迎关注原创公众号 【计算机视觉联盟】,回复 【西瓜书手推笔记】 可获取我的机器学习纯手推笔记!

直达笔记地址:机器学习手推笔记(GitHub地址)

标题:Mix Face :改进面向细粒度条件的人脸验证
作者:郑君如等。
类别: cs.简历 [cs.简历|
亮点:我们提出了一种新的损失函数, Mix Face ,结合分类和度量损失。

标题:基于深度学习目标检测和单目深度估计模型的绝对距离预测
作者:马苏敏等。
类别: cs.简历 [cs.简历|
亮点:本文提出了一种深度学习框架,由两个深度网络的深度估计和对象检测使用一个单一的图像。

标题:多尺度高分辨率视觉变换器
作者:顾佳琪等。
类别: cs.简历 [cs.简历, cs.艾, cs.LG |
亮点:为了提高 ViT 更有能力学习语义丰富和空间精确的多尺度表示,在这项工作中,我们提出了一个有效的集成高分辨率的多分支架构与视觉变压器,称为 HR Vi T ,推动密集的预测任务的帕累托前一个新的水平。

标题:基于深度学习的半监督视频异常检测方法研究
作者:穆罕默德巴拉达兰;罗伯特贝格万
类别: cs.简历 [cs.简历|
亮点:本文介绍了该领域的研究人员到一个新的角度,并回顾了最近的基于深度学习的半监督视频异常检测方法,基于一个共同的策略,他们使用的异常检测。

标题:多边形跟踪:带约束多边形的跟踪
作者:加斯帕尔·福尔;休斯·佩雷奥特;纪尧姆·亚历山大·比洛多;尼古拉·索尼尔
类别: cs.简历 [cs.简历|
亮点:本文提出了一种新的基于边界多边形的多目标快速跟踪分割方法。

6,标题6,标题:所有行业的StyleGAN:仅经过预先训练的StyleGAN图像处理
作者:敏金冲,李新英,戴维福赛斯
类别: cs.简历 [cs.简历, cs.LG |
HIGHLIGHT :在这项工作中,我们更深入地研究了 Style GAN 的空间属性。

标题:三注意融合引导的多模态分割网络
作者:周同学;阮素;维拉;卡努
类别:综合类【综合类】
亮点:考虑到不同的 MR 模式之间的相关性,在本文中,我们提出了一种新的三注意融合引导的多模态分割网络。

第八条标题:细粒度分类中的人的注意
作者:姚荣;徐文佳;赤田泽尼普;恩克莱达·卡塞奇
类别: cs.简历 [cs.简历|
亮点:为了验证人类的注意力包含有价值的信息,决策过程,如细粒度的分类,我们比较人类的关注和模型的解释,发现重要的功能。为了实现这一目标,我们收集人类的视线数据的细粒度分类数据集 CUB ,并建立一个名为 CUB - GH A (基于视线的人类注意力)的数据集。

标题:HHP - Net :一种具有不确定性的头部姿态估计的轻型异方差神经网络
作者:乔治·坎塔里尼;费德里科·费加里·托梅诺蒂;尼古拉塔·诺切蒂;弗朗切斯卡·欧东内
类别: cs.简历 [cs.简历|
亮点:在本文中,我们介绍了一种新的方法来估计人的头部姿势在单一的图像从一个小组的头部的关键点。

第十条标题:精确目标检测中的边界分布估计
作者:周浩然;黄航;赵瑞;王伟;周庆国
类别: cs.简历 [cs.简历|
亮点:在本文中,我们通过理论分析和实验验证,证明了以前的方法的缺陷,并提出了一种新的解决方案,准确地检测对象。

第 11 条标题:三维激光雷达点云的无簇全景分割
作者:李恩旭;拉扎尼;徐一萱;刘冰冰
类别: cs.简历 [cs.简历|
亮点:在本文中,我们提出了一种新的实时端到端的全光分割网络的激光雷达点云,称为 CP Seg 。

第 12 章,标题:一种用于弱监督少片段语义分割的像素级元学习器
作者:李元浩;杨福恩;王宇强
类别: cs.简历 [cs.简历|
亮点:为了解决这个问题,我们提出了一个新的元学习框架,预测伪像素级分割口罩从有限的数据量和语义标签。

第十三条标题:关系自我注意:视频理解中的注意缺失
作者:金满珍;权熙成;王春雨;郭素霞;赵敏素
类别:综合类
亮点:在这项工作中,我们引入了一个关系的功能转换,称为关系的自我关注( RSA ),利用丰富的时空关系结构的视频动态生成的关系内核和聚合的关系上下文。

第十四条标题:梯度频率调制视觉解释视频理解模型
作者:林欣淼;包文涛;马修·赖特;于空
类别:综合类
亮点:在本文中,我们提出了基于频率的极值扰动( F - EP )来解释视频理解模型的决策。

第 15 条,标题:视觉变形金刚能现卷积吗?
作者:李善达;陈香宁;何迪;谢秋菊
类别: cs.简历 [cs.简历, cs.LG |
亮点:在这项工作中,我们证明了一个单一的 ViT 层与图像补丁作为输入可以执行任何卷积操作建设性,其中多头注意机制和相对位置编码发挥重要作用。

第十六条,标题:ALS 患者的个性化一次性唇读
作者:比巴沙·森;阿迪蒂亚·阿加瓦尔;鲁德拉巴·穆克霍帕迪耶;维奈·南布迪里;扎瓦哈尔
类别: cs.简历 [cs.简历, cs.CL|
亮点:在这项工作中,我们提出了一个个性化的网络 lip read ALS 患者只使用一个镜头的例子。

第 17 条,标题:从互联网视频中估计三维运动和人与物体相互作用的力
作者:李宗棉等。
类别: cs.简历 [cs.简历|
亮点:在本文中,我们介绍了一种方法来自动重建的三维运动的人与对象从一个单一的 RGB 视频。

第 18 条,标题:检测与分割:伤口图像自动分割的深度学习方法
作者:贾泰诺等。
类别:综合类【综合类】
亮点:我们提出了检测和分段( DS ),深度学习方法产生伤口分割地图具有高泛化能力。

第 19 条标题:神经场景流先验
作者:李学谦:乔尼·凯斯模庞特斯:西蒙·卢西
类别: cs.简历 [cs.简历|
亮点:本文回顾了场景流问题,主要依赖于运行时优化和强正则化。

第 20 条,标题:运动边界和遮挡的联合检测
作者:金哈林;于淑芝;卡洛托马西
类别: cs.简历 [cs.简历|
亮点:我们提出 MO Net ,一个卷积神经网络,联合检测运动边界(MBs)和遮挡区域( Oc cs )在视频中,无论是向前和向后的时间。

第 21 条,标题:基于属性的深度眼周识别:利用软生物特征提高眼周的识别
作者:韦鲁·塔勒贾;纳塞尔·纳斯拉巴迪;马修· C ·瓦伦蒂
类别:综合类【综合类】
亮点:本文提出了一种新的深度眼周识别框架,称为基于属性的深眼周围识别( A DPR ),它预测软生物特征,并将预测到一个眼周的识别算法,以确定身份,从周围的图像具有高精度。

第 22 条,标题:从循环的角度探讨半监督视频对象分割问题
作者:李玉玺;徐宁;杨文杰;西俊;林伟尧
类别: cs.简历 [cs.简历|
亮点:在本文中,我们将半监督视频对象分割问题放置到一个循环工作流,发现上述缺陷可以通过半监督 VOS 系统的固有的循环属性共同解决。

第二十三条,标题:跨模态视频检索的掩蔽模型
作者:加伯尔;纳格拉尼;孙晨;阿拉哈里;施密德
类别: cs.简历 [cs.简历|
重点:我们在输入中屏蔽整个模态,并使用其他两种模态来预测它。

第 24 条,标题:补丁游戏:学习在参考游戏中标记中级补丁
作者:卡迈勒·古普塔等。
类别: cs.简历 [cs.简历, cs.LG |
亮点:我们研究一个参考的游戏(一种类型的信令游戏),其中两个代理通过一个离散的瓶颈彼此通信,以实现一个共同的目标。

第 25 条,标题:基于元学习的黑盒随机搜索对抗攻击的搜索分布
作者:马克西姆·雅素拉;扬·亨德里克·梅津;马提亚·海因
类别: cs.LG [cs.LG, cs.艾, cs.简历|
亮点:我们研究如何解决这个问题,可以适应提案分布的基础上获得的信息在攻击过程中在线。

第 26 条标题:健身景观足迹:一个比较神经网络架构搜索问题的框架
作者:卡里福·任特洛尔;安德烈·卡梅罗;朱晓翔
类别: cs.LG [cs.LG, cs.艾, cs.简历, cs.NE]
亮点:在本文中,我们建议使用适应度景观分析研究神经网络架构的搜索问题。

第 27 条,标题:Log Avg Exp 提供了一个原则性和性能良好的全局池操作符
作者:斯科特 c .劳;托马斯特拉彭贝格;萨基夫奥雷
类别: cs.LG [cs.LG, cs.艾, cs.简历|
亮点:我们寻求改善神经网络的池操作,通过应用一个更理论上合理的运营商。

第 28 条,标题:从单幅图像学习手眼摄像机标定
作者:尤金·瓦拉萨基斯;卡米尔·德雷茨科夫斯基;爱德华·约翰斯
类别:中华人民共和国【中华民国,中华民国cs.LG]
亮点:我们提出了一项研究,使用基于学习的方法解决这个问题,在线从一个单一的 RGB 图像,同时训练我们的模型与完全合成的数据。

第 29 条,标题:基于图的双尺度上下文融合轨迹预测
作者:张璐;李培亮;陈静;沈少杰
类别: RO 号[ RO 号, CV 号]
亮点:在本文中,我们提出了一种基于图形的轨迹预测网络命名的双尺度预测器( DSP ),它编码的静态和动态的驱动上下文在一个层次的方式。

第 30 条,标题:基于生成对抗网络和分层相关传播的可解释医学图像分割
作者:阿瓦德拉赫曼·艾哈迈德;林·阿里
类别: EESS . IV 【 ESS . IV ,第四章,第五章】cs.LG]
亮点:这项工作的一个主要贡献是提供解释的预测,使用层明智的相关性传播方法指定的输入图像像素是相关的预测和程度。

第 31 条,标题:用于 COVID - 19 CX R 诊断的联合分割视觉变换器
作者:朴尚俊;金光均;金正松;金保;叶正哲
类别:第四组[第四、第六、第五组]
亮点:为了合并这些方法,从而最大限度地发挥其独特的优势,在这里,我们表明, Vision Transformer ,一个最近开发的深度学习架构与简单的可分解配置,是理想的分割学习不牺牲性能的合适。

第 32 条,标题:欠显示相机的 ISP 独立图像重建
作者:苗琪;李玉琪;黑德里希
类别:第四组【第四、第五组】
亮点:在本文中,我们提出了一个图像恢复管道是 ISP 不可知的,即它可以与任何遗留 ISP 相结合,以产生一个最终的图像,匹配使用相同的 ISP 的常规相机的外观。

第 33 条,标题:基于 CT 数据构建高阶符号距离图及其在骨形态计量学中的应用
作者:布莱斯·贝斯勒;坦尼斯·肯普;尼尔斯·弗克特;史蒂文· K ·博伊德
类别:第四组【第四、第五组】
亮点:提出了一种构造两相材料 CT 成像高阶符号距离场的算法。

第 34 条,标题:皮肤和疟疾图像的分布外检测
作者:穆罕默德·扎伊达等。
类别:第四组【第四、第五组】
亮点:我们提出了一种方法来稳健地分类 OOD 样本在皮肤和疟疾图像,而不需要访问标记的 OOD 样品在训练。


1, TITLE: MixFace: Improving Face Verification Focusing on Fine-grained Conditions
AUTHORS: JUNUK JUNG et. al.
CATEGORY: cs.CV [cs.CV]
HIGHLIGHT: We propose a novel loss function, MixFace, that combines classification and metric losses.

2, TITLE: Absolute Distance Prediction Based on Deep Learning Object Detection and Monocular Depth Estimation Models
AUTHORS: ARMIN MASOUMIAN et. al.
CATEGORY: cs.CV [cs.CV]
HIGHLIGHT: This paper presents a deep learning framework that consists of two deep networks for depth estimation and object detection using a single image.

3, TITLE: HRViT: Multi-Scale High-Resolution Vision Transformer
AUTHORS: JIAQI GU et. al.
CATEGORY: cs.CV [cs.CV, cs.AI, cs.LG]
HIGHLIGHT: To enhance ViTs with more capability to learn semantically-rich and spatially-precise multi-scale representations, in this work, we present an efficient integration of high-resolution multi-branch architectures with vision transformers, dubbed HRViT, pushing the Pareto front of dense prediction tasks to a new level.

4, TITLE: A Critical Study on The Recent Deep Learning Based Semi-Supervised Video Anomaly Detection Methods
AUTHORS: Mohammad Baradaran ; Robert Bergevin
CATEGORY: cs.CV [cs.CV]
HIGHLIGHT: This paper introduces the researchers of the field to a new perspective and reviews the recent deep-learning based semi-supervised video anomaly detection approaches, based on a common strategy they use for anomaly detection.

5, TITLE: PolyTrack: Tracking with Bounding Polygons
AUTHORS: Gaspar Faure ; Hughes Perreault ; Guillaume-Alexandre Bilodeau ; Nicolas Saunier
CATEGORY: cs.CV [cs.CV]
HIGHLIGHT: In this paper, we present a novel method called PolyTrack for fast multi-object tracking and segmentation using bounding polygons.

6, TITLE: StyleGAN of All Trades: Image Manipulation with Only Pretrained StyleGAN
AUTHORS: Min Jin Chong ; Hsin-Ying Lee ; David Forsyth
CATEGORY: cs.CV [cs.CV, cs.LG]
HIGHLIGHT: In this work, we take a deeper look at the spatial properties of StyleGAN.

7, TITLE: A Tri-attention Fusion Guided Multi-modal Segmentation Network
AUTHORS: Tongxue Zhou ; Su Ruan ; Pierre Vera ; St�phane Canu
CATEGORY: cs.CV [cs.CV, eess.IV]
HIGHLIGHT: Considering the correlation between different MR modalities, in this paper, we propose a multi-modality segmentation network guided by a novel tri-attention fusion.

8, TITLE: Human Attention in Fine-grained Classification
AUTHORS: Yao Rong ; Wenjia Xu ; Zeynep Akata ; Enkelejda Kasneci
CATEGORY: cs.CV [cs.CV]
HIGHLIGHT: To validate that human attention contains valuable information for decision-making processes such as fine-grained classification, we compare human attention and model explanations in discovering important features. Towards this goal, we collect human gaze data for the fine-grained classification dataset CUB and build a dataset named CUB-GHA (Gaze-based Human Attention).

9, TITLE: HHP-Net: A Light Heteroscedastic Neural Network for Head Pose Estimation with Uncertainty
AUTHORS: Giorgio Cantarini ; Federico Figari Tomenotti ; Nicoletta Noceti ; Francesca Odone
CATEGORY: cs.CV [cs.CV]
HIGHLIGHT: In this paper we introduce a novel method to estimate the head pose of people in single images starting from a small set of head keypoints.

10, TITLE: Boundary Distribution Estimation to Precise Object Detection
AUTHORS: Haoran Zhou ; Hang Huang ; Rui Zhao ; Wei Wang ; Qingguo Zhou
CATEGORY: cs.CV [cs.CV]
HIGHLIGHT: In this paper, we prove the flaws in the previous method through theoretical analysis and experimental verification and propose a novel solution to detect objects precisely.

11, TITLE: CPSeg: Cluster-free Panoptic Segmentation of 3D LiDAR Point Clouds
AUTHORS: Enxu Li ; Ryan Razani ; Yixuan Xu ; Bingbing Liu
CATEGORY: cs.CV [cs.CV]
HIGHLIGHT: In this paper, we propose a novel real-time end-to-end panoptic segmentation network for LiDAR point clouds, called CPSeg.

12, TITLE: A Pixel-Level Meta-Learner for Weakly Supervised Few-Shot Semantic Segmentation
AUTHORS: Yuan-Hao Lee ; Fu-En Yang ; Yu-Chiang Frank Wang
CATEGORY: cs.CV [cs.CV]
HIGHLIGHT: To address this problem, we propose a novel meta-learning framework, which predicts pseudo pixel-level segmentation masks from a limited amount of data and their semantic labels.

13, TITLE: Relational Self-Attention: What's Missing in Attention for Video Understanding
AUTHORS: Manjin Kim ; Heeseung Kwon ; Chunyu Wang ; Suha Kwak ; Minsu Cho
CATEGORY: cs.CV [cs.CV]
HIGHLIGHT: In this work, we introduce a relational feature transform, dubbed the relational self-attention (RSA), that leverages rich structures of spatio-temporal relations in videos by dynamically generating relational kernels and aggregating relational contexts.

14, TITLE: Gradient Frequency Modulation for Visually Explaining Video Understanding Models
AUTHORS: Xinmiao Lin ; Wentao Bao ; Matthew Wright ; Yu Kong
CATEGORY: cs.CV [cs.CV]
HIGHLIGHT: In this paper, we propose Frequency-based Extremal Perturbation (F-EP) to explain a video understanding model's decisions.

15, TITLE: Can Vision Transformers Perform Convolution?
AUTHORS: Shanda Li ; Xiangning Chen ; Di He ; Cho-Jui Hsieh
CATEGORY: cs.CV [cs.CV, cs.LG]
HIGHLIGHT: In this work, we prove that a single ViT layer with image patches as the input can perform any convolution operation constructively, where the multi-head attention mechanism and the relative positional encoding play essential roles.

16, TITLE: Personalized One-Shot Lipreading for An ALS Patient
AUTHORS: Bipasha Sen ; Aditya Agarwal ; Rudrabha Mukhopadhyay ; Vinay Namboodiri ; C V Jawahar
CATEGORY: cs.CV [cs.CV, cs.CL]
HIGHLIGHT: In this work, we propose a personalized network to lipread an ALS patient using only one-shot examples.

17, TITLE: Estimating 3D Motion and Forces of Human-Object Interactions from Internet Videos
AUTHORS: ZONGMIAN LI et. al.
CATEGORY: cs.CV [cs.CV]
HIGHLIGHT: In this paper, we introduce a method to automatically reconstruct the 3D motion of a person interacting with an object from a single RGB video.

18, TITLE: Detect-and-Segment: A Deep Learning Approach to Automate Wound Image Segmentation
AUTHORS: GAETANO SCEBBA et. al.
CATEGORY: cs.CV [cs.CV, eess.IV]
HIGHLIGHT: We present Detect-and-Segment (DS), a deep learning approach to produce wound segmentation maps with high generalization capabilities.

19, TITLE: Neural Scene Flow Prior
AUTHORS: Xueqian Li ; Jhony Kaesemodel Pontes ; Simon Lucey
CATEGORY: cs.CV [cs.CV]
HIGHLIGHT: This paper revisits the scene flow problem that relies predominantly on runtime optimization and strong regularization.

20, TITLE: Joint Detection of Motion Boundaries and Occlusions
AUTHORS: Hannah Halin Kim ; Shuzhi Yu ; Carlo Tomasi
CATEGORY: cs.CV [cs.CV]
HIGHLIGHT: We propose MONet, a convolutional neural network that jointly detects motion boundaries (MBs) and occlusion regions (Occs) in video both forward and backward in time.

21, TITLE: Attribute-Based Deep Periocular Recognition: Leveraging Soft Biometrics to Improve Periocular Recognition
AUTHORS: Veeru Talreja ; Nasser M. Nasrabadi ; Matthew C. Valenti
CATEGORY: cs.CV [cs.CV, eess.IV]
HIGHLIGHT: This paper presents a new deep periocular recognition framework called attribute-based deep periocular recognition (ADPR), which predicts soft biometrics and incorporates the prediction into a periocular recognition algorithm to determine identity from periocular images with high accuracy.

22, TITLE: Exploring The Semi-supervised Video Object Segmentation Problem from A Cyclic Perspective
AUTHORS: Yuxi Li ; Ning Xu ; Wenjie Yang ; John See ; Weiyao Lin
CATEGORY: cs.CV [cs.CV]
HIGHLIGHT: In this paper, we place the semi-supervised video object segmentation problem into a cyclic workflow and find the defects above can be collectively addressed via the inherent cyclic property of semi-supervised VOS systems.

23, TITLE: Masking Modalities for Cross-modal Video Retrieval
AUTHORS: Valentin Gabeur ; Arsha Nagrani ; Chen Sun ; Karteek Alahari ; Cordelia Schmid
CATEGORY: cs.CV [cs.CV]
HIGHLIGHT: We mask an entire modality in the input and predict it using the other two modalities.

24, TITLE: PatchGame: Learning to Signal Mid-level Patches in Referential Games
AUTHORS: KAMAL GUPTA et. al.
CATEGORY: cs.CV [cs.CV, cs.LG]
HIGHLIGHT: We study a referential game (a type of signaling game) where two agents communicate with each other via a discrete bottleneck to achieve a common goal.

25, TITLE: Meta-Learning The Search Distribution of Black-Box Random Search Based Adversarial Attacks
AUTHORS: Maksym Yatsura ; Jan Hendrik Metzen ; Matthias Hein
CATEGORY: cs.LG [cs.LG, cs.AI, cs.CV]
HIGHLIGHT: We study how this issue can be addressed by adapting the proposal distribution online based on the information obtained during the attack.

26, TITLE: Fitness Landscape Footprint: A Framework to Compare Neural Architecture Search Problems
AUTHORS: Kalifou Ren� Traor� ; Andr�s Camero ; Xiao Xiang Zhu
CATEGORY: cs.LG [cs.LG, cs.AI, cs.CV, cs.NE]
HIGHLIGHT: In this paper, we propose to use fitness landscape analysis to study a neural architecture search problem.

27, TITLE: LogAvgExp Provides A Principled and Performant Global Pooling Operator
AUTHORS: Scott C. Lowe ; Thomas Trappenberg ; Sageev Oore
CATEGORY: cs.LG [cs.LG, cs.AI, cs.CV]
HIGHLIGHT: We seek to improve the pooling operation in neural networks, by applying a more theoretically justified operator.

28, TITLE: Learning Eye-in-Hand Camera Calibration from A Single Image
AUTHORS: Eugene Valassakis ; Kamil Dreczkowski ; Edward Johns
CATEGORY: cs.RO [cs.RO, cs.CV, cs.LG]
HIGHLIGHT: We present a study on using learning-based methods for solving this problem online from a single RGB image, whilst training our models with entirely synthetic data.

29, TITLE: Trajectory Prediction with Graph-based Dual-scale Context Fusion
AUTHORS: Lu Zhang ; Peiliang Li ; Jing Chen ; Shaojie Shen
CATEGORY: cs.RO [cs.RO, cs.CV]
HIGHLIGHT: In this paper, we present a graph-based trajectory prediction network named the Dual Scale Predictor (DSP), which encodes both the static and dynamical driving context in a hierarchical manner.

30, TITLE: Explainable Medical Image Segmentation Via Generative Adversarial Networks and Layer-wise Relevance Propagation
AUTHORS: Awadelrahman M. A. Ahmed ; Leen A. M. Ali
CATEGORY: eess.IV [eess.IV, cs.CV, cs.LG]
HIGHLIGHT: A major contribution of this work is to provide explanations for the predictions using a layer-wise relevance propagation approach designating which input image pixels are relevant to the predictions and to what extent.

31, TITLE: Federated Split Vision Transformer for COVID-19CXR Diagnosis Using Task-Agnostic Training
AUTHORS: Sangjoon Park ; Gwanghyun Kim ; Jeongsol Kim ; Boah Kim ; Jong Chul Ye
CATEGORY: eess.IV [eess.IV, cs.AI, cs.CV]
HIGHLIGHT: To amalgamate these methods and thereby maximize their distinct strengths, here we show that the Vision Transformer, a recently developed deep learning architecture with straightforward decomposable configuration, is ideally suitable for split learning without sacrificing performance.

32, TITLE: ISP-Agnostic Image Reconstruction for Under-Display Cameras
AUTHORS: Miao Qi ; Yuqi Li ; Wolfgang Heidrich
CATEGORY: eess.IV [eess.IV, cs.CV]
HIGHLIGHT: In this paper, we propose an image-restoration pipeline that is ISP-agnostic, i.e. it can be combined with any legacy ISP to produce a final image that matches the appearance of regular cameras using the same ISP.

33, TITLE: Constructing High-Order Signed Distance Maps from Computed Tomography Data with Application to Bone Morphometry
AUTHORS: Bryce A. Besler ; Tannis D. Kemp ; Nils D. Forkert ; Steven K. Boyd
CATEGORY: eess.IV [eess.IV, cs.CV]
HIGHLIGHT: An algorithm is presented for constructing high-order signed distance fields for two phase materials imaged with computed tomography.

34, TITLE: Out of Distribution Detection for Skin and Malaria Images
AUTHORS: MUHAMMAD ZAIDA et. al.
CATEGORY: eess.IV [eess.IV, cs.CV]
HIGHLIGHT: We propose an approach to robustly classify OoD samples in skin and malaria images without the need to access labeled OoD samples during training.

  • 0
    点赞
  • 0
    收藏
    觉得还不错? 一键收藏
  • 0
    评论
评论
添加红包

请填写红包祝福语或标题

红包个数最小为10个

红包金额最低5元

当前余额3.43前往充值 >
需支付:10.00
成就一亿技术人!
领取后你会自动成为博主和红包主的粉丝 规则
hope_wisdom
发出的红包
实付
使用余额支付
点击重新获取
扫码支付
钱包余额 0

抵扣说明:

1.余额是钱包充值的虚拟货币,按照1:1的比例进行支付金额的抵扣。
2.余额无法直接购买下载,可以购买VIP、付费专栏及课程。

余额充值