本专栏是计算机视觉方向论文收集积累，时间：2021年4月6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）
1, TITLE: IDOL-Net: An Interactive Dual-Domain Parallel Network for CT Metal Artifact Reduction
AUTHORS: TAO WANG et. al.
CATEGORY: physics.med-ph [physics.med-ph, cs.CV]
HIGHLIGHT: To address this problem, in this paper, we propose a novel interactive dualdomain parallel network for CT MAR, dubbed as IDOLNet.
2, TITLE: FixMyPose: Pose Correctional Captioning and Retrieval
AUTHORS: Hyounghun Kim ; Abhay Zala ; Graham Burri ; Mohit Bansal
CATEGORY: cs.CL [cs.CL, cs.AI, cs.CV]
HIGHLIGHT: Thus, automated pose correction systems are required more than ever, and we introduce a new captioning dataset named FixMyPose to address this need. To verify the sim-to-real transfer of our FixMyPose dataset, we collect a set of real images and show promising performance on these images.
3, TITLE: Talk, Don't Write: A Study of Direct Speech-Based Image Retrieval
AUTHORS: Ramon Sanabria ; Austin Waters ; Jason Baldridge
CATEGORY: cs.CL [cs.CL, cs.CV, cs.IR, cs.LG]
HIGHLIGHT: In this work, we extensively study and expand choices of encoder architectures, training methodology (including unimodal and multimodal pretraining), and other factors.
4, TITLE: Domain Generalization with MixStyle
AUTHORS: Kaiyang Zhou ; Yongxin Yang ; Yu Qiao ; Tao Xiang
CATEGORY: cs.CV [cs.CV, cs.LG]
HIGHLIGHT: In this paper, a novel approach is proposed based on probabilistically mixing instance-level feature statistics of training samples across source domains.
5, TITLE: Multi-Atlas Based Pathological Stratification of D-TGA Congenital Heart Disease
AUTHORS: Maria A. Zuluaga ; Alex F. Mendelson ; M. Jorge Cardoso ; Andrew M. Taylor ; S�bastien Ourselin
CATEGORY: cs.CV [cs.CV]
HIGHLIGHT: In this work, we exploit the segmentation errors associated with poor atlas selection to build a computer aided diagnosis (CAD) system for pathological classification in post-operative dextro-transposition of the great arteries (d-TGA).
6, TITLE: Uncertainty-Aware Annotation Protocol to Evaluate Deformable Registration Algorithms
AUTHORS: Loic Peter ; Daniel C. Alexander ; Caroline Magnain ; Juan Eugenio Iglesias
CATEGORY: cs.CV [cs.CV]
HIGHLIGHT: In this paper, we introduce a principled strategy for the construction of a gold standard in deformable registration.
7, TITLE: Instance Level Affinity-Based Transfer for Unsupervised Domain Adaptation
AUTHORS: Astuti Sharma ; Tarun Kalluri ; Manmohan Chandraker
CATEGORY: cs.CV [cs.CV]
HIGHLIGHT: We address this issue in our work and propose an instance affinity based criterion for source to target transfer during adaptation, called ILA-DA.
8, TITLE: Unsupervised Discovery of The Long-Tail in Instance Segmentation Using Hierarchical Self-Supervision
AUTHORS: Zhenzhen Weng ; Mehmet Giray Ogut ; Shai Limonchik ; Serena Yeung
CATEGORY: cs.CV [cs.CV]
HIGHLIGHT: The goal of this paper is to propose a method that can perform unsupervised discovery of long-tail categories in instance segmentation, through learning instance embeddings of masked regions.
9, TITLE: A Semantic Segmentation Network for Urban-Scale Building Footprint Extraction Using RGB Satellite Imagery
AUTHORS: Aatif Jiwani ; Shubhrakanti Ganguly ; Chao Ding ; Nan Zhou ; David M. Chan
CATEGORY: cs.CV [cs.CV]
HIGHLIGHT: In this paper, we propose a modified DeeplabV3+ module with a Dilated ResNet backbone to generate masks of building footprints from only three-channel RGB satellite imagery.
10, TITLE: Convolutional Neural Opacity Radiance Fields
AUTHORS: HAIMIN LUO et. al.
CATEGORY: cs.CV [cs.CV]
HIGHLIGHT: In this paper, we propose a novel scheme to generate opacity radiance fields with a convolutional neural renderer for fuzzy objects, which is the first to combine both explicit opacity supervision and convolutional mechanism into the neural radiance field framework so as to enable high-quality appearance and global consistent alpha mattes generation in arbitrary novel views.
11, TITLE: High-resolution Depth Maps Imaging Via Attention-based Hierarchical Multi-modal Fusion
AUTHORS: ZHIWEI ZHONG et. al.
CATEGORY: cs.CV [cs.CV]
HIGHLIGHT: In this paper, we propose a novel attention-based hierarchical multi-modal fusion (AHMF) network for guided DSR.
12, TITLE: Robust Trust Region for Weakly Supervised Segmentation
AUTHORS: Dmitrii Marin ; Yuri Boykov
CATEGORY: cs.CV [cs.CV]
HIGHLIGHT: We propose a new robust trust region approach for regularized losses improving the state-of-the-art results.
13, TITLE: Fingerspelling Detection in American Sign Language
AUTHORS: Bowen Shi ; Diane Brentari ; Greg Shakhnarovich ; Karen Livescu
CATEGORY: cs.CV [cs.CV, cs.CL]
HIGHLIGHT: In this paper, we consider the task of fingerspelling detection in raw, untrimmed sign language videos. We propose a benchmark and a suite of evaluation metrics, some of which reflect the effect of detection on the downstream fingerspelling recognition task.
14, TITLE: Deepfake Detection Scheme Based on Vision Transformer and Distillation
AUTHORS: Young-Jin Heo ; Young-Ju Choi ; Young-Woon Lee ; Byung-Gyu Kim
CATEGORY: cs.CV [cs.CV, cs.AI]
HIGHLIGHT: In this paper, we propose a Vision Transformer model with distillation methodology for detecting fake videos.
15, TITLE: Generation of Gradient-Preserving Images Allowing HOG Feature Extraction
AUTHORS: Masaki Kitayama ; Hitoshi Kiya
CATEGORY: cs.CV [cs.CV]
HIGHLIGHT: In this paper, we propose a method for generating visually protected images, referred to as gradient-preserving images.
16, TITLE: Graph Contrastive Clustering
AUTHORS: HUASONG ZHONG et. al.
CATEGORY: cs.CV [cs.CV]
HIGHLIGHT: Recently, some contrastive learning methods have been proposed to simultaneously learn representations and clustering assignments, achieving significant improvements.
17, TITLE: Uncertainty for Identifying Open-Set Errors in Visual Object Detection
AUTHORS: Dimity Miller ; Niko S�nderhauf ; Michael Milford ; Feras Dayoub
CATEGORY: cs.CV [cs.CV, cs.AI, cs.LG, cs.RO]
HIGHLIGHT: We propose GMM-Det, a real-time method for extracting epistemic uncertainty from object detectors to identify and reject open-set errors.
18, TITLE: Recursively Refined R-CNN: Instance Segmentation with Self-RoI Rebalancing
AUTHORS: Leonardo Rossi ; Akbar Karimi ; Andrea Prati
CATEGORY: cs.CV [cs.CV, I.4.6; I.5.1]
HIGHLIGHT: To address this issue, we propose Recursively Refined R-CNN ($R^3$-CNN) which avoids duplicates by introducing a loop mechanism instead.
19, TITLE: DARCNN: Domain Adaptive Region-based Convolutional Neural Network for Unsupervised Instance Segmentation in Biomedical Images
AUTHORS: Joy Hsu ; Wah Chiu ; Serena Yeung
CATEGORY: cs.CV [cs.CV, I.4.10]
HIGHLIGHT: We propose a Domain Adaptive Region-based Convolutional Neural Network (DARCNN), that adapts knowledge of object definition from COCO, a large labelled vision dataset, to multiple biomedical datasets.
20, TITLE: Task-Independent Knowledge Makes for Transferable Representations for Generalized Zero-Shot Learning
AUTHORS: Chaoqun Wang ; Xuejin Chen ; Shaobo Min ; Xiaoyan Sun ; Houqiang Li
CATEGORY: cs.CV [cs.CV, cs.AI]
HIGHLIGHT: In this paper, we propose a novel Dual-Contrastive Embedding Network (DCEN) that simultaneously learns task-specific and task-independent knowledge via semantic alignment and instance discrimination.
21, TITLE: Few-Cost Salient Object Detection with Adversarial-Paced Learning
AUTHORS: Dingwen Zhang ; Haibin Tian ; Jungong Han
CATEGORY: cs.CV [cs.CV]
HIGHLIGHT: To address this problem, this paper proposes to learn the effective salient object detection model based on the manual annotation on a few training images only, thus dramatically alleviating human labor in training models.
22, TITLE: PDWN: Pyramid Deformable Warping Network for Video Interpolation
AUTHORS: Zhiqi Chen ; Ran Wang ; Haojie Liu ; Yao Wang
CATEGORY: cs.CV [cs.CV]
HIGHLIGHT: Following the recent development in using deformable convolution (DConv) for video interpolation, we propose a light but effective model, called Pyramid Deformable Warping Network (PDWN).
23, TITLE: Perceptual Indistinguishability-Net (PI-Net): Facial Image Obfuscation with Manipulable Semantics
AUTHORS: Jia-Wei Chen ; Li-Ju Chen ; Chia-Mu Yu ; Chun-Shien Lu
CATEGORY: cs.CV [cs.CV]
HIGHLIGHT: In this study, with the consideration of the perceptual similarity, we propose perceptual indistinguishability (PI) as a formal privacy notion particularly for images.
24, TITLE: Potential Convolution: Embedding Point Clouds Into Potential Fields
AUTHORS: DENGSHENG CHEN et. al.
CATEGORY: cs.CV [cs.CV]
HIGHLIGHT: In this work, rather than defining a continuous or discrete kernel, we directly embed convolutional kernels into the learnable potential fields, giving rise to potential convolution.
25, TITLE: Learning Neural Representation of Camera Pose with Matrix Representation of Pose Shift Via View Synthesis
AUTHORS: Yaxuan Zhu ; Ruiqi Gao ; Siyuan Huang ; Song-chun Zhu ; Yingnian Wu
CATEGORY: cs.CV [cs.CV]
HIGHLIGHT: In this work, we propose an approach to learn neural representations of camera poses and 3D scenes, coupled with neural representations of local camera movements.
26, TITLE: Aggregated Contextual Transformations for High-Resolution Image Inpainting
AUTHORS: Yanhong Zeng ; Jianlong Fu ; Hongyang Chao ; Baining Guo
CATEGORY: cs.CV [cs.CV]
HIGHLIGHT: To overcome these two challenges, we propose an enhanced GAN-based model, named Aggregated COntextual-Transformation GAN (AOT-GAN), for high-resolution image inpainting.
27, TITLE: A Video Is Worth Three Views: Trigeminal Transformers for Video-based Person Re-identification
AUTHORS: XUEHU LIU et. al.
CATEGORY: cs.CV [cs.CV, cs.AI]
HIGHLIGHT: To capture richer perceptions and extract more comprehensive video representations, in this paper we propose a novel framework named Trigeminal Transformers (TMT) for video-based person Re-ID.
28, TITLE: HLA-Face: Joint High-Low Adaptation for Low Light Face Detection
AUTHORS: Wenjing Wang ; Wenhan Yang ; Jiaying Liu
CATEGORY: cs.CV [cs.CV]
HIGHLIGHT: To address the issue, we propose a joint High-Low Adaptation (HLA) framework.
29, TITLE: A Dual-Critic Reinforcement Learning Framework for Frame-level Bit Allocation in HEVC/H.265
AUTHORS: Yung-Han Ho ; Guo-Lun Jin ; Yun Liang ; Wen-Hsiao Peng ; Xiaobo Li
CATEGORY: cs.CV [cs.CV]
HIGHLIGHT: This paper introduces a dual-critic reinforcement learning (RL) framework to address the problem of frame-level bit allocation in HEVC/H.265.
30, TITLE: Branch-and-Pruning Optimization Towards Global Optimality in Deep Learning
AUTHORS: Yuanwei Wu ; Ziming Zhang ; Guanghui Wang
CATEGORY: cs.CV [cs.CV]
HIGHLIGHT: In this paper, we propose a novel approximation algorithm, {\em BPGrad}, towards optimizing deep models globally via branch and pruning.
31, TITLE: Non-Homogeneous Haze Removal Via Artificial Scene Prior and Bidimensional Graph Reasoning
AUTHORS: HAORAN WEI et. al.
CATEGORY: cs.CV [cs.CV]
HIGHLIGHT: In this paper, we propose a Non-Homogeneous Haze Removal Network (NHRN) via artificial scene prior and bidimensional graph reasoning.
32, TITLE: Adversarial Attack in The Context of Self-driving
AUTHORS: Zhenhua Chen ; Chuhua Wang ; David J. Crandall
CATEGORY: cs.CV [cs.CV]
HIGHLIGHT: In this paper, we propose a model that can attack segmentation models with semantic and dynamic targets in the context of self-driving.
33, TITLE: TATL: Task Agnostic Transfer Learning for Skin Attributes Detection
AUTHORS: DUY M. H. NGUYEN et. al.
CATEGORY: cs.CV [cs.CV]
HIGHLIGHT: In this work, we propose Task Agnostic Transfer Learning (TATL), a novel framework motivated by dermatologists' behaviors in the skincare context.
34, TITLE: MetaHTR: Towards Writer-Adaptive Handwritten Text Recognition
AUTHORS: AYAN KUMAR BHUNIA et. al.
CATEGORY: cs.CV [cs.CV]
HIGHLIGHT: In this paper, we take a completely different perspective -- we work on the assumption that there is always a new style that is drastically different, and that we will only have very limited data during testing to perform adaptation.
35, TITLE: Adaptive Prototype Learning and Allocation for Few-Shot Segmentation
AUTHORS: GEN LI et. al.
CATEGORY: cs.CV [cs.CV]
HIGHLIGHT: In this paper, we propose two novel modules, named superpixel-guided clustering (SGC) and guided prototype allocation (GPA), for multiple prototype extraction and allocation.
36, TITLE: "Forget" The Forget Gate: Estimating Anomalies in Videos Using Self-contained Long Short-Term Memory Networks
AUTHORS: Habtamu Fanta ; Zhiwen Shao ; Lizhuang Ma
CATEGORY: cs.CV [cs.CV]
HIGHLIGHT: In this paper, we present an approach of detecting anomalies in videos by learning a novel LSTM based self-contained network on normal dense optical flow.
37, TITLE: MIST: Multiple Instance Self-Training Framework for Video Anomaly Detection
AUTHORS: Jia-Chang Feng ; Fa-Ting Hong ; Wei-Shi Zheng
CATEGORY: cs.CV [cs.CV]
HIGHLIGHT: In this work, we develop a multiple instance self-training framework (MIST)to efficiently refine task-specific discriminative representations with only video-level annotations.
38, TITLE: Efficient DETR: Improving End-to-End Object Detector with Dense Prior
AUTHORS: Zhuyu Yao ; Jiangbo Ai ; Boxun Li ; Chi Zhang
CATEGORY: cs.CV [cs.CV]
HIGHLIGHT: In this paper, we investigate that the random initialization of object containers, which include object queries and reference points, is mainly responsible for the requirement of multiple iterations.
39, TITLE: Lipstick Ain't Enough: Beyond Color Matching for In-the-Wild Makeup Transfer
AUTHORS: Thao Nguyen ; Anh Tran ; Minh Hoai
CATEGORY: cs.CV [cs.CV]
HIGHLIGHT: In this work, we propose a holistic makeup transfer framework that can handle all the mentioned makeup components. To train and evaluate such a system, we also introduce new makeup datasets for real and synthetic extreme makeup.
40, TITLE: Can Audio-visual Integration Strengthen Robustness Under Multimodal Attacks?
AUTHORS: Yapeng Tian ; Chenliang Xu
CATEGORY: cs.CV [cs.CV, cs.CR, cs.SD, eess.AS]
HIGHLIGHT: In this paper, we propose to make a systematic study on machines multisensory perception under attacks.
41, TITLE: Monocular 3D Multi-Person Pose Estimation By Integrating Top-Down and Bottom-Up Networks
AUTHORS: Yu Cheng ; Bo Wang ; Bo Yang ; Robby T. Tan
CATEGORY: cs.CV [cs.CV]
HIGHLIGHT: To address these challenges, we propose the integration of top-down and bottom-up approaches to exploit their strengths.
42, TITLE: OnTarget: An Electronic Archery Scoring
AUTHORS: Andreea Danielescu
CATEGORY: cs.CV [cs.CV]
HIGHLIGHT: There are several challenges in creating an electronic archery scoring system using computer vision techniques.
43, TITLE: MMBERT: Multimodal BERT Pretraining for Improved Medical VQA
AUTHORS: YASH KHARE et. al.
CATEGORY: cs.CV [cs.CV, cs.CL, cs.LG]
HIGHLIGHT: To overcome these limitations, we propose a solution inspired by self-supervised pretraining of Transformer-style architectures for NLP, Vision and Language tasks.
44, TITLE: Graph Sampling Based Deep Metric Learning for Generalizable Person Re-Identification
AUTHORS: Shengcai Liao ; Ling Shao
CATEGORY: cs.CV [cs.CV]
HIGHLIGHT: In this paper, beyond representation learning, we consider how to formulate person image matching directly in deep feature maps.
45, TITLE: Learning Mobile CNN Feature Extraction Toward Fast Computation of Visual Object Tracking
AUTHORS: Tsubasa Murate ; Takashi Watanabe ; Masaki Yamada
CATEGORY: cs.CV [cs.CV, cs.GR, cs.LG, 68T10, 68T05, 68T07]
HIGHLIGHT: In this paper, we construct a lightweight, high-precision and high-speed object tracking using a trained CNN.
46, TITLE: BTS-Net: Bi-directional Transfer-and-Selection Network For RGB-D Salient Object Detection
AUTHORS: Wenbo Zhang ; Yao Jiang ; Keren Fu ; Qijun Zhao
CATEGORY: cs.CV [cs.CV]
HIGHLIGHT: To address this limitation, we propose to conduct progressive bi-directional interactions as early in the encoder stage, yielding a novel bi-directional transfer-and-selection network named BTS-Net, which adopts a set of bi-directional transfer-and-selection (BTS) modules to purify features during encoding.
47, TITLE: Towards Rolling Shutter Correction and Deblurring in Dynamic Scenes
AUTHORS: Zhihang Zhong ; Yinqiang Zheng ; Imari Sato
CATEGORY: cs.CV [cs.CV]
HIGHLIGHT: To enable learning-based approaches to address real-world RSCD problem, we contribute the first dataset, BS-RSCD, which includes both ego-motion and object-motion in dynamic scenes.
48, TITLE: Hierarchical Pyramid Representations for Semantic Segmentation
AUTHORS: Hiroaki Aizawa ; Yukihiro Domae ; Kunihito Kato
CATEGORY: cs.CV [cs.CV]
HIGHLIGHT: In this study, we design novel hierarchical, contextual, and multiscale pyramidal representations to capture the properties from an input image.
49, TITLE: An Empirical Study of Training Self-Supervised Visual Transformers
AUTHORS: Xinlei Chen ; Saining Xie ; Kaiming He
CATEGORY: cs.CV [cs.CV, cs.LG]
HIGHLIGHT: This paper does not describe a novel method.
50, TITLE: Generating Furry Cars: Disentangling Object Shape & Appearance Across Multiple Domains
AUTHORS: Utkarsh Ojha ; Krishna Kumar Singh ; Yong Jae Lee
CATEGORY: cs.CV [cs.CV, cs.GR, cs.LG]
HIGHLIGHT: Our key technical contribution is to represent object appearance with a differentiable histogram of visual features, and to optimize the generator so that two images with the same latent appearance factor but different latent shape factors produce similar histograms.
51, TITLE: Beyond Short Clips: End-to-End Video-Level Learning with Collaborative Memories
AUTHORS: Xitong Yang ; Haoqi Fan ; Lorenzo Torresani ; Larry Davis ; Heng Wang
CATEGORY: cs.CV [cs.CV]
HIGHLIGHT: To overcome these limitations, we introduce a collaborative memory mechanism that encodes information across multiple sampled clips of a video at each training iteration.
52, TITLE: Scene Text Retrieval Via Joint Text Detection and Similarity Learning
AUTHORS: HAO WANG et. al.
CATEGORY: cs.CV [cs.CV]
HIGHLIGHT: In this paper, we address this problem by directly learning a cross-modal similarity between a query text and each text instance from natural images.
53, TITLE: Distill and Fine-tune: Effective Adaptation from A Black-box Source Model
AUTHORS: Jian Liang ; Dapeng Hu ; Ran He ; Jiashi Feng
CATEGORY: cs.CV [cs.CV, cs.LG]
HIGHLIGHT: For this new problem, we propose a novel two-step adaptation framework called Distill and Fine-tune (Dis-tune).
54, TITLE: Performance Analysis of Facial Recognition: A Critical Review Through Glass Factor
AUTHORS: Jiashu He
CATEGORY: cs.CV [cs.CV, cs.LG]
HIGHLIGHT: This paper provides a comprehensive review of glass factor.
55, TITLE: Hypercorrelation Squeeze for Few-Shot Segmentation
AUTHORS: Juhong Min ; Dahyun Kang ; Minsu Cho
CATEGORY: cs.CV [cs.CV]
HIGHLIGHT: To address the problem, we propose Hypercorrelation Squeeze Networks (HSNet) that leverages multi-level feature correlation and efficient 4D convolutions.
56, TITLE: Hierarchical Image Peeling: A Flexible Scale-space Filtering Framework
AUTHORS: FU YUANBIN et. al.
CATEGORY: cs.CV [cs.CV]
HIGHLIGHT: Different from image segmentation with the spatial whole-part consideration, this work designs a modern framework for disassembling an image into a family of derived signals from a scale-space perspective.
57, TITLE: Cyclic Co-Learning of Sounding Object Visual Grounding and Sound Separation
AUTHORS: Yapeng Tian ; Di Hu ; Chenliang Xu
CATEGORY: cs.CV [cs.CV, cs.MM, cs.SD, eess.AS]
HIGHLIGHT: Based on this observation, in this paper, we propose a cyclic co-learning (CCoL) paradigm that can jointly learn sounding object visual grounding and audio-visual sound separation in a unified framework.
58, TITLE: Reducing Racial Bias in Facial Age Prediction Using Unsupervised Domain Adaptation in Regression
AUTHORS: Apoorva Gokhale ; Astuti Sharma ; Kaustav Datta ; Savyasachi
CATEGORY: cs.CV [cs.CV, cs.LG]
HIGHLIGHT: We propose an approach for unsupervised domain adaptation for the task of estimating someone's age from a given face image.
59, TITLE: SGCN:Sparse Graph Convolution Network for Pedestrian Trajectory Prediction
AUTHORS: LIUSHUAI SHI et. al.
CATEGORY: cs.CV [cs.CV]
HIGHLIGHT: To cope with these issues, we present a Sparse Graph Convolution Network~(SGCN) for pedestrian trajectory prediction.
60, TITLE: GSECnet: Ground Segmentation of Point Clouds for Edge Computing
AUTHORS: Dong He ; Jie Cheng ; Jong-Hwan Kim
CATEGORY: cs.CV [cs.CV]
HIGHLIGHT: This paper proposes the GSECnet - Ground Segmentation network for Edge Computing, an efficient ground segmentation framework of point clouds specifically designed to be deployable on a low-power edge computing unit.
61, TITLE: Weakly-supervised Instance Segmentation Via Class-agnostic Learning with Salient Images
AUTHORS: XINGGANG WANG et. al.
CATEGORY: cs.CV [cs.CV]
HIGHLIGHT: The BoxCaseg model is jointly trained using box-supervised images and salient images in a multi-task learning manner.
62, TITLE: 3D Human Body Reshaping with Anthropometric Modeling
AUTHORS: Yanhong Zeng ; Jianlong Fu ; Hongyang Chao
CATEGORY: cs.CV [cs.CV, cs.GR]
HIGHLIGHT: In this paper, we have designed a 3D human body reshaping system by proposing a novel feature-selection-based local mapping technique, which enables automatic anthropometric parameter modeling for each body facet.
63, TITLE: Misclassification-Aware Gaussian Smoothing Improves Robustness Against Domain Shifts
AUTHORS: Athanasios Tsiligkaridis ; Theodoros Tsiligkaridis
CATEGORY: cs.LG [cs.LG, cs.AI, cs.CV]
HIGHLIGHT: In this paper, a misclassification-aware Gaussian smoothing approach is presented to improve the robustness of image classifiers against a variety of corruptions while maintaining clean accuracy.
64, TITLE: Towards Self-Adaptive Metric Learning On The Fly
AUTHORS: Yang Gao ; Yi-Fan Li ; Swarup Chandra ; Latifur Khan ; Bhavani Thuraisingham
CATEGORY: cs.LG [cs.LG, cs.CV, cs.IR]
HIGHLIGHT: Existing studies have proposed various solutions to learn a Mahalanobis or bilinear metric in an online fashion by either restricting distances between similar (dissimilar) pairs to be smaller (larger) than a given lower (upper) bound or requiring similar instances to be separated from dissimilar instances with a given margin.
65, TITLE: Faster Convolution Inference Through Using Pre-Calculated Lookup Tables
AUTHORS: Grigor Gatchev ; Valentin Mollov
CATEGORY: cs.LG [cs.LG, cs.CV]
HIGHLIGHT: Faster Convolution Inference Through Using Pre-Calculated Lookup Tables
66, TITLE: Explainability-aided Domain Generalization for Image Classification
AUTHORS: Robin M. Schmidt
CATEGORY: cs.LG [cs.LG, cs.CV]
HIGHLIGHT: In this work, we empirically demonstrate that applying methods and architectures from the explainability literature can, in fact, achieve state-of-the-art performance for the challenging task of domain generalization while offering a framework for more insights into the prediction and training process.
67, TITLE: Training Deep Normalizing Flow Models in Highly Incomplete Data Scenarios with Prior Regularization
AUTHORS: Edgar A. Bernal
CATEGORY: cs.LG [cs.LG, cs.CV]
HIGHLIGHT: We propose a novel framework to facilitate the learning of data distributions in high paucity scenarios that is inspired by traditional formulations of solutions to ill-posed problems.
68, TITLE: Deep Learning-Based Autonomous Driving Systems: A Survey of Attacks and Defenses
AUTHORS: YAO DENG et. al.
CATEGORY: cs.LG [cs.LG, cs.CR, cs.CV, cs.DC]
HIGHLIGHT: This survey provides a thorough analysis of different attacks that may jeopardize ADSs, as well as the corresponding state-of-the-art defense mechanisms.
69, TITLE: Evaluating Explainable Artificial Intelligence Methods for Multi-label Deep Learning Classification Tasks in Remote Sensing
AUTHORS: Ioannis Kakogeorgiou ; Konstantinos Karantzalos
CATEGORY: cs.LG [cs.LG, cs.CV]
HIGHLIGHT: To this end, we have applied explainable artificial intelligence (XAI) methods in remote sensing multi-label classification tasks towards producing human-interpretable explanations and improve transparency.
70, TITLE: Unsupervised Multi-source Domain Adaptation Without Access to Source Data
AUTHORS: Sk Miraj Ahmed ; Dripta S. Raychaudhuri ; Sujoy Paul ; Samet Oymak ; Amit K. Roy-Chowdhury
CATEGORY: cs.LG [cs.LG, cs.CV]
HIGHLIGHT: To answer this, we propose a novel and efficient algorithm which automatically combines the source models with suitable weights in such a way that it performs at least as good as the best source model.
71, TITLE: Procrustean Training for Imbalanced Deep Learning
AUTHORS: Han-Jia Ye ; De-Chuan Zhan ; Wei-Lun Chao
CATEGORY: cs.LG [cs.LG, cs.CV]
HIGHLIGHT: In this paper, we provide a novel explanation of this issue.
72, TITLE: Multimedia Technology Applications and Algorithms: A Survey
AUTHORS: Palak Tiwary ; Sanjida Ahmed
CATEGORY: cs.MM [cs.MM, cs.CV]
HIGHLIGHT: This survey gives an overview of the various multimedia technologies and algorithms developed in the domains mentioned.
73, TITLE: Robotic Waste Sorter with Agile Manipulation and Quickly Trainable Detector
AUTHORS: Takuya Kiyokawa ; Hiroki Katayama ; Yuya Tatsuta ; Jun Takamatsu ; Tsukasa Ogasawara
CATEGORY: cs.RO [cs.RO, cs.CV]
HIGHLIGHT: To achieve this, we propose three methods.
74, TITLE: Synergies Between Affordance and Geometry: 6-DoF Grasp Detection Via Implicit Representations
AUTHORS: Zhenyu Jiang ; Yifeng Zhu ; Maxwell Svetlik ; Kuan Fang ; Yuke Zhu
CATEGORY: cs.RO [cs.RO, cs.AI, cs.CV]
HIGHLIGHT: In this work, we draw insight that 3D reconstruction and grasp learning are two intimately connected tasks, both of which require a fine-grained understanding of local geometry details.
75, TITLE: Generative Locally Linear Embedding
AUTHORS: Benyamin Ghojogh ; Ali Ghodsi ; Fakhri Karray ; Mark Crowley
CATEGORY: stat.ML [stat.ML, cs.CV, cs.LG]
HIGHLIGHT: In this work, we propose two novel generative versions of LLE, named Generative LLE (GLLE), whose linear reconstruction steps are stochastic rather than deterministic.
76, TITLE: MR-Contrast-Aware Image-to-Image Translations with Generative Adversarial Networks
AUTHORS: Jonas Denck ; Jens Guehring ; Andreas Maier ; Eva Rothgang
CATEGORY: eess.IV [eess.IV, cs.CV]
HIGHLIGHT: Methods Therefore, we trained an image-to-image generative adversarial network conditioned on the MR acquisition parameters repetition time and echo time.
77, TITLE: 3D Convolutional Neural Networks for Stalled Brain Capillary Detection
AUTHORS: Roman Solovyev ; Alexandr A. Kalinin ; Tatiana Gabruseva
CATEGORY: eess.IV [eess.IV, cs.CV]
HIGHLIGHT: Here, we describe a deep learning-based approach for automatic detection of stalled capillaries in brain images based on 3D convolutional neural networks.
78, TITLE: Multi-class Motion-based Semantic Segmentation for Ureteroscopy and Laser Lithotripsy
AUTHORS: Soumya Gupta ; Sharib Ali ; Louise Goldsmith ; Ben Turney ; Jens Rittscher
CATEGORY: eess.IV [eess.IV, cs.CV]
HIGHLIGHT: We propose an end-to-end CNN-based framework for the segmentation of stones and laser fiber.
79, TITLE: FocusNetv2: Imbalanced Large and Small Organ Segmentation with Adversarial Shape Constraint for Head and Neck CT Images
AUTHORS: YUNHE GAO et. al.
CATEGORY: eess.IV [eess.IV, cs.CV]
HIGHLIGHT: We propose a novel two-stage deep neural network, FocusNetv2, to solve this challenging problem by automatically locating, ROI-pooling, and segmenting small organs with specifically designed small-organ localization and segmentation sub-networks while maintaining the accuracy of large organ segmentation.
80, TITLE: Contrast-enhanced MRI Synthesis Using 3D High-Resolution ConvNets
AUTHORS: CHAO CHEN et. al.
CATEGORY: eess.IV [eess.IV, cs.CV]
HIGHLIGHT: In this work, we present a deep learning based approach for contrast-enhanced T1 synthesis on brain tumor patients.
81, TITLE: Detection of COVID-19 Disease Using Deep Neural Networks with Ultrasound Imaging
AUTHORS: Carlos Rojas-Azabache ; Karen Vilca-Janampa ; Renzo Guerrero-Huayta ; Dennis N��ez-Fern�ndez
CATEGORY: eess.IV [eess.IV, cs.CV]
HIGHLIGHT: This paper presents a work in progress that proposes the analysis of images of lung ultrasound scans using a convolutional neural network.
82, TITLE: Using Spatial-temporal Ensembles of Convolutional Neural Networks for Lumen Segmentation in Ureteroscopy
AUTHORS: JORGE F. LAZO et. al.
CATEGORY: eess.IV [eess.IV, cs.CV]
HIGHLIGHT: In order to obtain an accurate segmentation of the hollow lumen, this paper presents an automatic method based on Convolutional Neural Networks (CNNs).
83, TITLE: Global Guidance Network for Breast Lesion Segmentation in Ultrasound Images
AUTHORS: CHENG XUE et. al.
CATEGORY: eess.IV [eess.IV, cs.CV, cs.LG]
HIGHLIGHT: In this paper, we develop a deep convolutional neural network equipped with a global guidance block (GGB) and breast lesion boundary detection (BD) modules for boosting the breast ultrasound lesion segmentation.
84, TITLE: Cascaded Robust Learning at Imperfect Labels for Chest X-ray Segmentation
AUTHORS: Cheng Xue ; Qiao Deng ; Xiaomeng Li ; Qi Dou ; Pheng Ann Heng
CATEGORY: eess.IV [eess.IV, cs.CV]
HIGHLIGHT: In this paper, we present a novel cascaded robust learning framework for chest X-ray segmentation with imperfect annotation.
85, TITLE: Opportunistic Screening of Osteoporosis Using Plain Film Chest X-ray
AUTHORS: FAKAI WANG et. al.
CATEGORY: eess.IV [eess.IV, cs.CV]
HIGHLIGHT: In this paper, we propose a method to predict BMD from Chest X-ray (CXR), one of the most common, accessible, and low-cost medical image examinations.
86, TITLE: Adaptive Gradient Balancing for UndersampledMRI Reconstruction and Image-to-Image Translation
AUTHORS: ITZIK MALKIEL et. al.
CATEGORY: eess.IV [eess.IV, cs.CV]
HIGHLIGHT: In this work, we enhance the image quality by using a Conditional Wasserstein Generative Adversarial Network combined with a novel Adaptive Gradient Balancing (AGB) technique that automates the process of combining the adversarial and pixel-wise terms and streamlines hyperparameter tuning.
87, TITLE: Removing Pixel Noises and Spatial Artifacts with Generative Diversity Denoising Methods
AUTHORS: Mangal Prakash ; Mauricio Delbracio ; Peyman Milanfar ; Florian Jug
CATEGORY: eess.IV [eess.IV, cs.CV, cs.LG, q-bio.QM]
HIGHLIGHT: In this work we show, for the first time, that generative diversity denoising (GDD) approaches can learn to remove structured noises without supervision.
88, TITLE: Automated Lung Segmentation from CT Images of Normal and COVID-19 Pneumonia Patients
AUTHORS: FAEZE GHOLAMIANKHAH et. al.
CATEGORY: eess.IV [eess.IV, cs.CV, physics.med-ph]
HIGHLIGHT: This study investigates the performance of a deep learning-based model for lung segmentation from CT images for normal and COVID-19 patients.