本专栏是计算机视觉方向论文收集积累，时间：2021年4月2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: Commonsense Spatial Reasoning for Visually Intelligent Agents
AUTHORS: Agnese Chiatti ; Gianluca Bardaro ; Enrico Motta ; Enrico Daga
CATEGORY: cs.AI [cs.AI, cs.CV, cs.RO]
HIGHLIGHT: In this paper, we present a framework for commonsense spatial reasoning which is tailored to real-world robotic applications.
2, TITLE: The Surprising Impact of Mask-head Architecture on Novel Class Segmentation
AUTHORS: Vighnesh Birodkar ; Zhichao Lu ; Siyang Li ; Vivek Rathod ; Jonathan Huang
CATEGORY: cs.CV [cs.CV]
HIGHLIGHT: In this work, we focus on a popular family of models which apply differentiable cropping to a feature map and predict a mask based on the resulting crop.
3, TITLE: Unconstrained Scene Generation with Locally Conditioned Radiance Fields
AUTHORS: Terrance DeVries ; Miguel Angel Bautista ; Nitish Srivastava ; Graham W. Taylor ; Joshua M. Susskind
CATEGORY: cs.CV [cs.CV, cs.LG]
HIGHLIGHT: In this paper, we introduce Generative Scene Networks (GSN), which learns to decompose scenes into a collection of many local radiance fields that can be rendered from a free moving camera.
4, TITLE: Unsupervised Degradation Representation Learning for Blind Super-Resolution
AUTHORS: LONGGUANG WANG et. al.
CATEGORY: cs.CV [cs.CV]
HIGHLIGHT: In this paper, we propose an unsupervised degradation representation learning scheme for blind SR without explicit degradation estimation.
5, TITLE: Online Multiple Object Tracking with Cross-Task Synergy
AUTHORS: Song Guo ; Jingya Wang ; Xinchao Wang ; Dacheng Tao
CATEGORY: cs.CV [cs.CV]
HIGHLIGHT: In this paper, we propose a novel unified model with synergy between position prediction and embedding association.
6, TITLE: Motion Guided Attention Fusion to Recognize Interactions from Videos
AUTHORS: Tae Soo Kim ; Jonathan Jones ; Gregory D. Hager
CATEGORY: cs.CV [cs.CV]
HIGHLIGHT: We present a dual-pathway approach for recognizing fine-grained interactions from videos.
7, TITLE: Linear Semantics in Generative Adversarial Networks
AUTHORS: Jianjin Xu ; Changxi Zheng
CATEGORY: cs.CV [cs.CV, cs.AI]
HIGHLIGHT: In this work, we aim to better understand the semantic representation of GANs, and thereby enable semantic control in GAN's generation process.
8, TITLE: Target Transformed Regression for Accurate Tracking
AUTHORS: Yutao Cui ; Cheng Jiang ; Limin Wang ; Gangshan Wu
CATEGORY: cs.CV [cs.CV]
HIGHLIGHT: The code and models will be made available at https://github.com/MCG-NJU/TREG.
9, TITLE: Frozen in Time: A Joint Video and Image Encoder for End-to-End Retrieval
AUTHORS: Max Bain ; Arsha Nagrani ; G�l Varol ; Andrew Zisserman
CATEGORY: cs.CV [cs.CV]
HIGHLIGHT: Our objective in this work is video-text retrieval - in particular a joint embedding that enables efficient text-to-video retrieval.
10, TITLE: A Joint Network for Grasp Detection Conditioned on Natural Language Commands
AUTHORS: Yiye Chen ; Ruinian Xu ; Yunzhi Lin ; Patricio A. Vela
CATEGORY: cs.CV [cs.CV, cs.RO]
HIGHLIGHT: This work proposes a model named Command Grasping Network(CGNet) to directly output command satisficing grasps from RGB image and textual command inputs.
11, TITLE: TrajeVAE -- Controllable Human Motion Generation from Trajectories
AUTHORS: Kacper Kania ; Marek Kowalski ; Tomasz Trzci?ski
CATEGORY: cs.CV [cs.CV, cs.AI]
HIGHLIGHT: To leverage this notion, we propose a novel transformer-like architecture, TrajeVAE, that provides a versatile framework for 3D human animation.
12, TITLE: RePOSE: Real-Time Iterative Rendering and Refinement for 6D Object Pose Estimation
AUTHORS: Shun Iwase ; Xingyu Liu ; Rawal Khirodkar ; Rio Yokota ; Kris M. Kitani
CATEGORY: cs.CV [cs.CV]
HIGHLIGHT: Instead of using a CNN to extract image features from a rendered RGB image, we propose to directly render a deep feature image.
13, TITLE: Exploiting Relationship for Complex-scene Image Generation
AUTHORS: TIANYU HUA et. al.
CATEGORY: cs.CV [cs.CV]
HIGHLIGHT: With the help of relationships, we propose three major updates in the generation framework.
14, TITLE: UC2: Universal Cross-lingual Cross-modal Vision-and-Language Pre-training
AUTHORS: MINGYANG ZHOU et. al.
CATEGORY: cs.CV [cs.CV]
HIGHLIGHT: To generalize this success to non-English languages, we introduce UC2, the first machine translation-augmented framework for cross-lingual cross-modal representation learning.
15, TITLE: One-Shot Neural Ensemble Architecture Search By Diversity-Guided Search Space Shrinking
AUTHORS: Minghao Chen ; Houwen Peng ; Jianlong Fu ; Haibin Ling
CATEGORY: cs.CV [cs.CV]
HIGHLIGHT: In this paper, we propose a one-shot neural ensemble architecture search (NEAS) solution that addresses the two challenges.
16, TITLE: Wide-Depth-Range 6D Object Pose Estimation in Space
AUTHORS: Yinlin Hu ; Sebastien Speierer ; Wenzel Jakob ; Pascal Fua ; Mathieu Salzmann
CATEGORY: cs.CV [cs.CV, cs.GR, cs.RO]
HIGHLIGHT: We instead propose a single-stage hierarchical end-to-end trainable network that is more robust to scale variations.
17, TITLE: Efficient and Differentiable Shadow Computation for Inverse Problems
AUTHORS: LINJIE LYU et. al.
CATEGORY: cs.CV [cs.CV]
HIGHLIGHT: To this end, we propose an accurate yet efficient approach for differentiable visibility and soft shadow computation.
18, TITLE: SCALoss: Side and Corner Aligned Loss for Bounding Box Regression
AUTHORS: Tu Zheng ; Shuai Zhao ; Yang Liu ; Zili Liu ; Deng Cai
CATEGORY: cs.CV [cs.CV]
HIGHLIGHT: In this paper, we propose Side Overlap (SO) loss by maximizing the side overlap of two bounding boxes, which puts more penalty for low overlapping bounding box cases.
19, TITLE: Fostering Generalization in Single-view 3D Reconstruction By Learning A Hierarchy of Local and Global Shape Priors
AUTHORS: Jan Bechtold ; Maxim Tatarchenko ; Volker Fischer ; Thomas Brox
CATEGORY: cs.CV [cs.CV]
HIGHLIGHT: In this work, we address this issue by learning a hierarchy of priors at different levels of locality from ground truth input depth maps.
20, TITLE: Reconstructing 3D Human Pose By Watching Humans in The Mirror
AUTHORS: Qi Fang ; Qing Shuai ; Junting Dong ; Hujun Bao ; Xiaowei Zhou
CATEGORY: cs.CV [cs.CV]
HIGHLIGHT: In this paper, we introduce the new task of reconstructing 3D human pose from a single image in which we can see the person and the person's image through a mirror. To validate the proposed approach, we collect a large-scale dataset named Mirrored-Human, which covers a large variety of human subjects, poses and backgrounds.
21, TITLE: Students Are The Best Teacher: Exit-Ensemble Distillation with Multi-Exits
AUTHORS: Hojung Lee ; Jong-Seok Lee
CATEGORY: cs.CV [cs.CV, cs.AI, cs.LG]
HIGHLIGHT: This paper proposes a novel knowledge distillation-based learning method to improve the classification performance of convolutional neural networks (CNNs) without a pre-trained teacher network, called exit-ensemble distillation.
22, TITLE: STMTrack: Template-free Visual Tracking with Space-time Memory Networks
AUTHORS: Zhihong Fu ; Qingjie Liu ; Zehua Fu ; Yunhong Wang
CATEGORY: cs.CV [cs.CV]
HIGHLIGHT: In this paper, we propose a novel tracking framework built on top of a space-time memory network that is competent to make full use of historical information related to the target for better adapting to appearance variations during tracking.
23, TITLE: Jigsaw Clustering for Unsupervised Visual Representation Learning
AUTHORS: Pengguang Chen ; Shu Liu ; Jiaya Jia
CATEGORY: cs.CV [cs.CV]
HIGHLIGHT: We propose a new jigsaw clustering pretext task in this paper, which only needs to forward each training batch itself, and reduces the training cost.
24, TITLE: Domain-Adversarial Training of Self-Attention Based Networks for Land Cover Classification Using Multi-temporal Sentinel-2 Satellite Imagery
AUTHORS: Martini Mauro ; Vittorio Mazzia ; Aleem Khaliq ; Marcello Chiaberge
CATEGORY: cs.CV [cs.CV, cs.AI]
HIGHLIGHT: In this paper, we investigate adversarial training of deep neural networks to bridge the domain discrepancy between distinct geographical zones.
25, TITLE: Neural Video Portrait Relighting in Real-time Via Consistency Modeling
AUTHORS: Longwen Zhang ; Qixuan Zhang ; Minye Wu ; Jingyi Yu ; Lan Xu
CATEGORY: cs.CV [cs.CV, cs.GR]
HIGHLIGHT: In this paper, we propose a neural approach for real-time, high-quality and coherent video portrait relighting, which jointly models the semantic, temporal and lighting consistency using a new dynamic OLAT dataset.
26, TITLE: Famous Companies Use More Letters in Logo:A Large-Scale Analysis of Text Area in Logo
AUTHORS: Shintaro Nishi ; Takeaki Kadota ; Seiichi Uchida
CATEGORY: cs.CV [cs.CV]
HIGHLIGHT: This paper analyzes a large number of logo images from the LLD-logo dataset, by recent deep learning-based techniques, to understand not only design trends of logo images and but also the correlation to their owner company.
27, TITLE: Unsupervised Foreground-Background Segmentation with Equivariant Layered GANs
AUTHORS: Yu Yang ; Hakan Bilen ; Qiran Zou ; Wing Yin Cheung ; Xiangyang Ji
CATEGORY: cs.CV [cs.CV]
HIGHLIGHT: We propose an unsupervised foreground-background segmentation method via training a segmentation network on the synthetic pseudo segmentation dataset generated from GANs, which are trained from a collection of images without annotations to explicitly disentangle foreground and background.
28, TITLE: LED2-Net: Monocular 360 Layout Estimation Via Differentiable Depth Rendering
AUTHORS: Fu-En Wang ; Yu-Hsuan Yeh ; Min Sun ; Wei-Chen Chiu ; Yi-Hsuan Tsai
CATEGORY: cs.CV [cs.CV]
HIGHLIGHT: Specifically, we propose the Differentiable Depth Rendering procedure to make the conversion from layout to depth prediction differentiable, thus making our proposed model end-to-end trainable while leveraging the 3D geometric information, without the need of providing the ground truth depth.
29, TITLE: Sketch2Mesh: Reconstructing and Editing 3D Shapes from Sketches
AUTHORS: Benoit Guillard ; Edoardo Remelli ; Pierre Yvernay ; Pascal Fua
CATEGORY: cs.CV [cs.CV]
HIGHLIGHT: In this paper, we use an encoder/decoder architecture for the sketch to mesh translation.
30, TITLE: Text to Image Generation with Semantic-Spatial Aware GAN
AUTHORS: Wentong Liao ; Kai Hu ; Michael Ying Yang ; Bodo Rosenhahn
CATEGORY: cs.CV [cs.CV, cs.LG]
HIGHLIGHT: A text to image generation (T2I) model aims to generate photo-realistic images which are semantically consistent with the text descriptions.
31, TITLE: RGB-D Local Implicit Function for Depth Completion of Transparent Objects
AUTHORS: LUYANG ZHU et. al.
CATEGORY: cs.CV [cs.CV, cs.RO]
HIGHLIGHT: In this paper, we introduce a new approach for depth completion of transparent objects from a single RGB-D image. To train the whole pipeline, we build a large scale synthetic dataset with transparent objects.
32, TITLE: Towards Evaluating and Training Verifiably Robust Neural Networks
AUTHORS: ZHAOYANG LYU et. al.
CATEGORY: cs.CV [cs.CV, cs.CR, cs.LG]
HIGHLIGHT: In this paper, we study the relationship between IBP and CROWN, and prove that CROWN is always tighter than IBP when choosing appropriate bounding lines.
33, TITLE: Composable Augmentation Encoding for Video Representation Learning
AUTHORS: Chen Sun ; Arsha Nagrani ; Yonglong Tian ; Cordelia Schmid
CATEGORY: cs.CV [cs.CV]
HIGHLIGHT: To overcome this limitation, we propose an 'augmentation aware' contrastive learning framework, where we explicitly provide a sequence of augmentation parameterisations (such as the values of the time shifts used to create data views) as composable augmentation encodings (CATE) to our model when projecting the video representations for contrastive learning.
34, TITLE: Modular Adaptation for Cross-Domain Few-Shot Learning
AUTHORS: XIAO LIN et. al.
CATEGORY: cs.CV [cs.CV]
HIGHLIGHT: Specifically, we propose a modular adaptation method that selectively performs multiple state-of-the-art (SOTA) adaptation methods in sequence.
35, TITLE: EfficientNetV2: Smaller Models and Faster Training
AUTHORS: Mingxing Tan ; Quoc V. Le
CATEGORY: cs.CV [cs.CV]
HIGHLIGHT: This paper introduces EfficientNetV2, a new family of convolutional networks that have faster training speed and better parameter efficiency than previous models.
36, TITLE: Arbitrary-Shaped Text Detection WithAdaptive Text Region Representation
AUTHORS: Xiufeng Jiang ; Shugong Xu ; Shunqing Zhang ; Shan Cao
CATEGORY: cs.CV [cs.CV]
HIGHLIGHT: In this paper, we propose a novel text regionrepresentation method, with a robust pipeline, which can precisely detect dense adjacent text instances witharbitrary shapes.
37, TITLE: Semi-Supervised Domain Adaptation Via Selective Pseudo Labeling and Progressive Self-Training
AUTHORS: Yoonhyung Kim ; Changick Kim
CATEGORY: cs.CV [cs.CV]
HIGHLIGHT: Based on this observation, in this paper, we propose a novel method that further exploits the labeled target images for SSDA.
38, TITLE: Bipartite Graph Network with Adaptive Message Passing for Unbiased Scene Graph Generation
AUTHORS: Rongjie Li ; Songyang Zhang ; Bo Wan ; Xuming He
CATEGORY: cs.CV [cs.CV, cs.AI]
HIGHLIGHT: To address these issues, we introduce a novel confidence-aware bipartite graph neural network with adaptive message propagation mechanism for unbiased scene graph generation. In addition, we propose an efficient bi-level data resampling strategy to alleviate the imbalanced data distribution problem in training our graph network.
39, TITLE: In&Out : Diverse Image Outpainting Via GAN Inversion
AUTHORS: YEN-CHI CHENG et. al.
CATEGORY: cs.CV [cs.CV]
HIGHLIGHT: In this work, we formulate the problem from the perspective of inverting generative adversarial networks.
40, TITLE: PhySG: Inverse Rendering with Spherical Gaussians for Physics-based Material Editing and Relighting
AUTHORS: Kai Zhang ; Fujun Luan ; Qianqian Wang ; Kavita Bala ; Noah Snavely
CATEGORY: cs.CV [cs.CV, cs.GR]
HIGHLIGHT: We present PhySG, an end-to-end inverse rendering pipeline that includes a fully differentiable renderer and can reconstruct geometry, materials, and illumination from scratch from a set of RGB input images.
41, TITLE: Anchor Pruning for Object Detection
AUTHORS: Maxim Bonnaerens ; Matthias Freiberger ; Joni Dambre
CATEGORY: cs.CV [cs.CV]
HIGHLIGHT: In this work we demonstrate an additional pruning technique, specifically for object detection: anchor pruning.
42, TITLE: Unsupervised Learning of Monocular Depth and Ego-Motion Using Multiple Masks
AUTHORS: Guangming Wang ; Hesheng Wang ; Yiling Liu ; Weidong Chen
CATEGORY: cs.CV [cs.CV, cs.RO]
HIGHLIGHT: A new unsupervised learning method of depth and ego-motion using multiple masks from monocular video is proposed in this paper.
43, TITLE: Modeling High-order Interactions Across Multi-interests for Micro-video Reommendation
AUTHORS: DONG YAO et. al.
CATEGORY: cs.CV [cs.CV, cs.IR]
HIGHLIGHT: To solve these problems, we propose a Self-over-Co Attention module to enhance user's interest representation.
44, TITLE: MeanShift++: Extremely Fast Mode-Seeking With Applications to Segmentation and Object Tracking
AUTHORS: Jennifer Jang ; Heinrich Jiang
CATEGORY: cs.CV [cs.CV, cs.LG]
HIGHLIGHT: We propose MeanShift++, an extremely fast mode-seeking algorithm based on MeanShift that uses a grid-based approach to speed up the mean shift step, replacing the computationally expensive neighbors search with a density-weighted mean of adjacent grid cells.
45, TITLE: A Realistic Evaluation of Semi-Supervised Learning for Fine-Grained Classification
AUTHORS: Jong-Chyi Su ; Zezhou Cheng ; Subhransu Maji
CATEGORY: cs.CV [cs.CV, cs.LG]
HIGHLIGHT: We evaluate the effectiveness of semi-supervised learning (SSL) on a realistic benchmark where data exhibits considerable class imbalance and contains images from novel classes.
46, TITLE: Explore Image Deblurring Via Blur Kernel Space
AUTHORS: Phong Tran ; Anh Tran ; Quynh Phung ; Minh Hoai
CATEGORY: cs.CV [cs.CV, cs.AI]
HIGHLIGHT: This paper introduces a method to encode the blur operators of an arbitrary dataset of sharp-blur image pairs into a blur kernel space.
47, TITLE: Group-Free 3D Object Detection Via Transformers
AUTHORS: Ze Liu ; Zheng Zhang ; Yue Cao ; Han Hu ; Xin Tong
CATEGORY: cs.CV [cs.CV]
HIGHLIGHT: In this paper, we present a simple yet effective method for directly detecting 3D objects from the 3D point cloud.
48, TITLE: Unsupervised Sound Localization Via Iterative Contrastive Learning
AUTHORS: Yan-Bo Lin ; Hung-Yu Tseng ; Hsin-Ying Lee ; Yen-Yu Lin ; Ming-Hsuan Yang
CATEGORY: cs.CV [cs.CV, cs.SD, eess.AS, eess.IV]
HIGHLIGHT: In this work, we propose an iterative contrastive learning framework that requires no data annotations.
49, TITLE: Putting NeRF on A Diet: Semantically Consistent Few-Shot View Synthesis
AUTHORS: Ajay Jain ; Matthew Tancik ; Pieter Abbeel
CATEGORY: cs.CV [cs.CV, cs.AI, cs.GR, cs.LG]
HIGHLIGHT: We present DietNeRF, a 3D neural scene representation estimated from a few images.
50, TITLE: Deep Two-View Structure-from-Motion Revisited
AUTHORS: JIANYUAN WANG et. al.
CATEGORY: cs.CV [cs.CV]
HIGHLIGHT: In contrast, we propose to revisit the problem of deep two-view SfM by leveraging the well-posedness of the classic pipeline.
51, TITLE: SimPoE: Simulated Character Control for 3D Human Pose Estimation
AUTHORS: Ye Yuan ; Shih-En Wei ; Tomas Simon ; Kris Kitani ; Jason Saragih
CATEGORY: cs.CV [cs.CV, cs.LG]
HIGHLIGHT: To demonstrate this, we present SimPoE, a Simulation-based approach for 3D human Pose Estimation, which integrates image-based kinematic inference and physics-based dynamics modeling.
52, TITLE: A Front-End for Dense Monocular SLAM Using A Learned Outlier Mask Prior
AUTHORS: Yihao Zhang ; John J. Leonard
CATEGORY: cs.CV [cs.CV, cs.RO]
HIGHLIGHT: In this work, we explore the use of the outlier mask, a by-product from unsupervised learning of depth from video, as a prior in a classical probability model for depth estimate fusion to step up the outlier-resistant tracking performance of a SLAM front-end.
53, TITLE: Multiview Pseudo-Labeling for Semi-supervised Learning from Video
AUTHORS: Bo Xiong ; Haoqi Fan ; Kristen Grauman ; Christoph Feichtenhofer
CATEGORY: cs.CV [cs.CV, cs.AI, cs.LG]
HIGHLIGHT: We present a multiview pseudo-labeling approach to video learning, a novel framework that uses complementary views in the form of appearance and motion information for semi-supervised learning in video.
54, TITLE: NeuralRecon: Real-Time Coherent 3D Reconstruction from Monocular Video
AUTHORS: Jiaming Sun ; Yiming Xie ; Linghao Chen ; Xiaowei Zhou ; Hujun Bao
CATEGORY: cs.CV [cs.CV, cs.RO]
HIGHLIGHT: We present a novel framework named NeuralRecon for real-time 3D scene reconstruction from a monocular video.
55, TITLE: Learning to Track Instances Without Video Annotations
AUTHORS: YANG FU et. al.
CATEGORY: cs.CV [cs.CV]
HIGHLIGHT: To resolve these challenges, we introduce a novel semi-supervised framework by learning instance tracking networks with only a labeled image dataset and unlabeled video sequences.
56, TITLE: LoFTR: Detector-Free Local Feature Matching with Transformers
AUTHORS: Jiaming Sun ; Zehong Shen ; Yuang Wang ; Hujun Bao ; Xiaowei Zhou
CATEGORY: cs.CV [cs.CV, cs.RO]
HIGHLIGHT: We present a novel method for local image feature matching.
57, TITLE: CUPID: Adaptive Curation of Pre-training Data for Video-and-Language Representation Learning
AUTHORS: Luowei Zhou ; Jingjing Liu ; Yu Cheng ; Zhe Gan ; Lei Zhang
CATEGORY: cs.CV [cs.CV]
HIGHLIGHT: In this paper, we first bring to light the sensitivity of pre-training objectives (contrastive vs. reconstructive) to domain discrepancy.
58, TITLE: Mesh Graphormer
AUTHORS: Kevin Lin ; Lijuan Wang ; Zicheng Liu
CATEGORY: cs.CV [cs.CV]
HIGHLIGHT: In this paper, we study how to combine graph convolutions and self-attentions in a transformer to model both local and global interactions.
59, TITLE: Improving Calibration for Long-Tailed Recognition
AUTHORS: Zhisheng Zhong ; Jiequan Cui ; Shu Liu ; Jiaya Jia
CATEGORY: cs.CV [cs.CV]
HIGHLIGHT: Motivated by the fact that predicted probability distributions of classes are highly related to the numbers of class instances, we propose label-aware smoothing to deal with different degrees of over-confidence for classes and improve classifier learning.
60, TITLE: Improved Image Generation Via Sparse Modeling
AUTHORS: Roy Ganz ; Michael Elad
CATEGORY: cs.CV [cs.CV, eess.IV]
HIGHLIGHT: In this paper, we aim to provide a better understanding and design of the image generation process.
61, TITLE: An Energy-Efficient Quad-Camera Visual System for Autonomous Machines on FPGA Platform
AUTHORS: ZISHEN WAN et. al.
CATEGORY: cs.AR [cs.AR, cs.CV, cs.RO]
HIGHLIGHT: In this paper, based on the observation that the visual frontend is a major performance and energy consumption bottleneck, we present our design and implementation of an energy-efficient hardware architecture for ORB (Oriented-Fast and Rotated- BRIEF) based localization system on FPGAs.
62, TITLE: An Investigation of Critical Issues in Bias Mitigation Techniques
AUTHORS: Robik Shrestha ; Kushal Kafle ; Christopher Kanan
CATEGORY: cs.LG [cs.LG, cs.AI, cs.CV, stat.ML]
HIGHLIGHT: To address this, we introduce an improved evaluation protocol, sensible metrics, and a new dataset, which enables us to ask and answer critical questions about bias mitigation algorithms. We introduce a new dataset called Biased MNIST that enables assessment of robustness to multiple bias sources.
63, TITLE: Federated Few-Shot Learning with Adversarial Learning
AUTHORS: Chenyou Fan ; Jianwei Huang
CATEGORY: cs.LG [cs.LG, cs.CV]
HIGHLIGHT: In this paper, we propose a federated few-shot learning (FedFSL) framework to learn a few-shot classification model that can classify unseen data classes with only a few labeled samples.
64, TITLE: Avalanche: An End-to-End Library for Continual Learning
AUTHORS: VINCENZO LOMONACO et. al.
CATEGORY: cs.LG [cs.LG, cs.AI, cs.CV, cs.SE]
HIGHLIGHT: In this work, we propose Avalanche, an open-source end-to-end library for continual learning research based on PyTorch.
65, TITLE: Domain Invariant Adversarial Learning
AUTHORS: Matan Levi ; Idan Attias ; Aryeh Kontorovich
CATEGORY: cs.LG [cs.LG, cs.CV]
HIGHLIGHT: In this work, we aim to achieve better trade-off between robust and natural performances by enforcing a domain invariant feature representation.
66, TITLE: Touch-based Curiosity for Sparse-Reward Tasks
AUTHORS: SAI RAJESWAR et. al.
CATEGORY: cs.LG [cs.LG, cs.AI, cs.CV, cs.RO]
HIGHLIGHT: In this work, we leverage surprise from mismatches in touch feedback to guide exploration in hard sparse-reward reinforcement learning tasks.
67, TITLE: Is Label Smoothing Truly Incompatible with Knowledge Distillation: An Empirical Study
AUTHORS: ZHIQIANG SHEN et. al.
CATEGORY: cs.LG [cs.LG, cs.AI, cs.CL, cs.CV]
HIGHLIGHT: This work aims to empirically clarify a recently discovered perspective that label smoothing is incompatible with knowledge distillation.
68, TITLE: Fusing RGBD Tracking and Segmentation Tree Sampling for Multi-Hypothesis Volumetric Segmentation
AUTHORS: Andrew Price ; Kun Huang ; Dmitry Berenson
CATEGORY: cs.RO [cs.RO, cs.CV]
HIGHLIGHT: In this work, we propose Multihypothesis Segmentation Tracking (MST), a novel method for volumetric segmentation in changing scenes, which allows scene ambiguity to be tracked and our estimates to be adjusted over time as we interact with the scene.
69, TITLE: Hierarchical Road Topology Learning for Urban Map-less Driving
AUTHORS: LI ZHANG et. al.
CATEGORY: cs.RO [cs.RO, cs.CV, cs.LG]
HIGHLIGHT: In this paper, we tackle the problem of online road map extraction via leveraging the sensory system aboard the vehicle itself.
70, TITLE: Deep Multi-Resolution Dictionary Learning for Histopathology Image Analysis
AUTHORS: Nima Hatami ; Mohsin Bilal ; Nasir Rajpoot
CATEGORY: eess.IV [eess.IV, cs.CV, cs.LG]
HIGHLIGHT: In this paper, we propose a deep dictionary learning approach to solve the problem of tissue phenotyping in histology images.
71, TITLE: Explaining COVID-19 and Thoracic Pathology Model Predictions By Identifying Informative Input Features
AUTHORS: ASHKAN KHAKZAR et. al.
CATEGORY: eess.IV [eess.IV, cs.CV, cs.LG]
HIGHLIGHT: We propose Inverse IBA to identify all informative regions.
72, TITLE: State-of-the-art Segmentation Network Fooled to Segment A Heart Symbol in Chest X-Ray Images
AUTHORS: Gerda Bortsova ; Florian Dubost ; Laurens Hogeweg ; Ioannis Katramados ; Marleen de Bruijne
CATEGORY: eess.IV [eess.IV, cs.CV]
HIGHLIGHT: In this article, we studied the effectiveness of adversarial attacks in targeted modification of segmentations of anatomical structures in chest X-rays.
73, TITLE: Rapid Quantification of COVID-19 Pneumonia Burden from Computed Tomography with Convolutional LSTM Networks
AUTHORS: KAJETAN GRODECKI et. al.
CATEGORY: eess.IV [eess.IV, cs.CV, cs.LG]
HIGHLIGHT: We propose a new fully automated deep learning framework for rapid quantification and differentiation between lung lesions in COVID-19 pneumonia from both contrast and non-contrast CT images using convolutional Long Short-Term Memory (ConvLSTM) networks.
74, TITLE: Learning Deep Latent Subspaces for Image Denoising
AUTHORS: Yunhao Yang ; Yuhan Zheng ; Yi Wang ; Chandrajit Bajaj
CATEGORY: eess.IV [eess.IV, cs.CV, cs.LG]
HIGHLIGHT: In this paper, we present a structured deep learning model that solves the heterogeneous image artifact filtering problem.
75, TITLE: SpectralNET: Exploring Spatial-Spectral WaveletCNN for Hyperspectral Image Classification
AUTHORS: Tanmay Chakraborty ; Utkarsh Trehan
CATEGORY: eess.IV [eess.IV, cs.CV, cs.LG]
HIGHLIGHT: In this article, we propose SpectralNET, a wavelet CNN, which is a variation of 2D CNN for multi-resolution HSI classification.
76, TITLE: High-quality Low-dose CT Reconstruction Using Convolutional Neural Networks with Spatial and Channel Squeeze and Excitation
AUTHORS: Jingfeng Lu ; Shuo Wang ; Ping Li ; Dong Ye
CATEGORY: eess.IV [eess.IV, cs.CV]
HIGHLIGHT: In this work, we present a High-Quality Imaging network (HQINet) for the CT image reconstruction from Low-dose computed tomography (CT) acquisitions.