学习
文章平均质量分 87
Ah丶Weii
...
展开
-
[LETR]Line Segment Detection Using Transformers without Edges(CVPR.2021 oral)
1. MotivationDespite its practical and scientific importance, line segment detection remains an unsolved problem in computer vision.Deep learning techniques still consist of heuristics-guided modules such as edge/junction/region detection, line grou.原创 2021-07-22 15:55:52 · 468 阅读 · 0 评论 -
[IQDet] (CVPR. 2021)
1. MotivationThe improvements in sampling strategies can be divided into two tendencies.(1) From Static to Dynamic.(2) From Sample-wise to Instance-wise.These sampling strategies might have a few limitations.(1) Static rules are not learnable and.原创 2021-07-15 22:10:16 · 325 阅读 · 0 评论 -
[Auto-Aug] Scale-aware Automatic Automentation for Object Detection(CVPR. 2021)
1. Motivation这篇文章主要关注于目标检测中的数据增强。This paper focuses on data augmentation for object detection.之前的工作,对于如何将尺度适应性融入网络的方法主要来源与网络的结构(FPN)以及数据增强。Previous work handles this challenge which brings the scale adaptation to the network efficiently mainly f.原创 2021-07-15 10:03:28 · 612 阅读 · 1 评论 -
[OTA]Optimal Transport Assignment for Object Detection(CVPR. 2021)
1. MotivationDeTR [3] examines the idea of global optimal matching. But the Hungarian algo- rithm they adopted can only work in a one-to-one assign- ment manner.One-to-Many 的方法。So far, for the CNN based detectors in one-to-many scenarios, a global .原创 2021-07-14 15:23:49 · 2404 阅读 · 0 评论 -
python logging日志笔记
import loggingimport oslogging.basicConfig( format='[%(asctime)s] %(message)s', # format 和 datefmt都要有。 datefmt='%Y/%M/%d %H:%M:%S', level=logging.DEBUG, handlers=[ logging.FileHandler(os.path.join('/home/you/you/chenwei/AdelaiDe原创 2021-07-09 22:34:40 · 82 阅读 · 0 评论 -
[WSIS] Weakly-supervised Instance Segmentation via Class-agnostic Learning with Salient Images
1. Motivation弱监督实例分割(WSIS)Weakly-supervised instance segmentation (WSIS) is important in computer vision for at least two reasons.Humans have a strong class-agnostic object segmentation ability and can outline boundaries ofunknown objects precisely.原创 2021-05-19 20:25:26 · 665 阅读 · 0 评论 -
[MOCO v1] Momentum Constrast for Unsupervised Visual Representation Learning(CVPR 2020)
文章目录1. Motivation and Contribution1.1 Motivation1.2 Contribution2. Method2.1 Contrastive Learning as Dictionary Look-up2.2 Momentum Contrast2.3 Relations to previous mechanisms2.4 pseudo code2.5 Pretext Task2.5.1 Technical details.2.5.2 Shuffling BN3. Ex.原创 2021-05-18 17:44:33 · 201 阅读 · 0 评论 -
[COD] Camouflaged Object Detection(CVPR 2020.oral)
文章目录1. Motivation2. Contribution3. Relation Work3.1 Generic and Salient Object Detection3.2 Camouflaged Object Detection3.2.1 Types of Camouflage3.2.2 COD Formulation3.2.3 Evaluation Metrics.4. Dataset4.1 Professional Annotation4.2 Dataset Features and ...原创 2021-05-14 11:34:53 · 783 阅读 · 0 评论 -
[ResMLP]ResMLP: Feedforward networks for image claissification with data-efficient training
文章目录1. Contribution2. Summary3. Methods3.1 The overall ResMLP architecture3.2 The Residual Multi-Perceptron Layer3.3 Relationship to the Vision Transformer.3.4 Class-MLP: MLP with class embedding4. Experiment4.1 Comparison with Transformers and convnets ..原创 2021-05-12 17:05:49 · 333 阅读 · 0 评论 -
[QueryInst]QueryInst: Parallelly Supervised Mask Query fo Instance Segmentation
# 1. MotivationQuery based object detection。Query based object detection frameworks achieve comparable performance with previous state-of-the-art object detectors.How to fully leverage such frameworks to perform instance segmentation remains an open p.原创 2021-05-10 21:51:18 · 1135 阅读 · 4 评论 -
[VarifocalNet] VarifocalNet: An IoU-aware Dense Object Detector (CVPR. 2021oral)
1. Motivation之前的工作,使用分类分数或者结合分类和定位的分数来筛选候选框。Prior work uses the classification score or a combination of classification and predicted localization scores to rank candidates.在检测中的后处理操作中,一般会使用NMS,通过分类分数来对候选框进行排名,然而这会影响检测的性能,作者认为原因在于分类的分数不是总作为衡量bbox定位精.原创 2021-05-08 20:46:52 · 411 阅读 · 0 评论 -
[Mixer]MLP-Mixer: An all-MLP Architecture forvision
1. MotivationIn this paper we show that while convolutions and attention are both sufficient for good performance, neither of them are necessary.2. ContributionWe propose the MLP-Mixer architecture (or “Mixer” for short), a competitive but conceptua.原创 2021-05-08 20:46:10 · 427 阅读 · 0 评论 -
[BCNet] Deep Occlusion-Aware Instance Segmentation with Overlapping BiLayers(CVPR. 2021)
1. Motivationoverlapping,occlusion,分割高度重叠的对象具有挑战性,因为通常在真实对象轮廓contours和遮挡边界occlusion boundaries之间没有区别。之前的工作在mask regression上做的很少,并且COCO训练数据中,大部分物体是没有遮挡信息的。mask R-CNN以及它的改进都是直接回归了被遮挡物实例occludee,这种做法忽略了遮挡物实例occluding 以及物体之间重叠的关系。Segmenting highly-overl..原创 2021-04-23 13:00:25 · 1952 阅读 · 7 评论 -
[Swin Transformer] Swin Transformer: HierarchicalVision Transformer using Shifted Windows
1. Motivation将transformer从NLP应用于CV领域存在以下2个方面的挑战,图像尺度的多样性,以及图像像素相对于words的高分辨率,这会造成内存大的花销。Challenges in adapting Transformer from language to vision arise from differences between the two domains, such as large variations in the scale of visual entities .原创 2021-04-05 17:16:38 · 369 阅读 · 0 评论 -
[PVT] Pyramid Vision Transformer: A Versatile Backbone for Dense Prediction without Convolution
paper: https://arxiv.org/abs/2102.12122code: https://github.com/whai362/PVT/文章目录1. Motivation2. Contribution3. Method3.1 Overall Architecture3.2 Feature Pyramid for Transformer3.3 Spatial-Reduction Attention3.3 Detailed settings of PVT series4. Experime.原创 2021-04-01 11:35:36 · 416 阅读 · 0 评论 -
[BoT Net] Bottleneck Transformers for Visual Recognition
1. Motivation 作者认为虽然堆叠更多层可以改善backbone的性能,但是隐式的结果来建模全局依赖(global dependencies),而不需要太多层,可以成为一种powerful和scalable的方案。Although stacking more layers indeed improves the performance of these backbones [72], an explicit mechanism to model global (non-local) de.原创 2021-03-25 21:48:02 · 449 阅读 · 0 评论 -
[YOLOF] You Only Look One-level Feature (CVPR. 2021)
代码:https://github.com/megvii-model/YOLOF文章目录1. Motivation2. Contribution3. Cost Analysis of MiMo Encoders4. Method4.1 Limited Scale Range4.2 Dilated Encoder4.3 Imbalance Problem on Positive Anchors4.4 Uniform Matching5. YOLOF6. Experiments6.1 Comparison..原创 2021-03-21 16:18:31 · 1214 阅读 · 0 评论 -
[VIT] Visual Transformer
1. MotivationTransformer在视觉上的应用存在limited。在视觉中,attention方法是用于连接卷积网络,或者用于取代卷积网络的部分构成,但同时保留了总体结构。 While the Transformer architecture has become the de-facto standard for natural language processing tasks, its applications to computer vision remain limit.原创 2021-03-17 19:47:42 · 294 阅读 · 0 评论 -
[MEInst] Mask Encoding for Single Shot Instance Segmentation(CVPR. 2020)
1. Motivation单阶段的分割在mask AP上比不过Mask R-CNN。one-stage alternatives cannot compete with Mask R-CNN in mask AP.作者提出了一个假设:“Is it possible to predict the object mask in the intrinsic low-dimensional space and still achieve competitive accuracy?" 并给出了肯定的.原创 2021-03-11 16:40:58 · 723 阅读 · 0 评论 -
[MIAL] Multiple Instace Active Learning for Object Detection(CVPR. 2021)
1. Motivation 目前主动学习(active learning)在图像分类上取得了巨大的进步,但是在目标检测领域,还缺乏一种instance-level的主动学习方法。 在这篇文章中,作者提出了多实例主动学习(MIAL),通过观察instance-level的uncertainty,来为检测器的训练挑选最informative的图片。 如图1所示,图a表示传统的方法,没有考虑负样本在目标检测中的不平衡问题,负样本产生了背景中的noisy instances,并干扰了image u原创 2021-03-07 11:41:18 · 1364 阅读 · 0 评论 -
[python]读写CSV基础笔记
csv库读入import csvwith open('ap.csv', 'r') as f: reader = csv.reader(f) title = next(reader) print(title) step = [] ap = [] for r in reader: step.append((int(r[1])+1.0)/1000) ap.append(float(r[2])/100) #原创 2021-02-28 16:55:33 · 113 阅读 · 0 评论 -
[ATSS]Bridging the Gap Between Anchor-based and Anchor-free Detection via Adaptive TrainingCVPR.2020
1. Motivation anchor-based method(RetinaNet)和 anchor-free method(FCOS)的主要差异体现在以下4点:The number of anchors tiled per location.The definition of positive and negative samples.The regression starting status.而目前FCOS的实验结果会比RetinaNet好,因此在这三个差异中,哪一点是造.原创 2021-02-25 17:25:36 · 172 阅读 · 0 评论 -
[TSP-FCOS]Rethinking Transformer-based Set Prediction for Object Detection
文章目录1. Motivation2. Contribution3. What Causes the Slow Convergence of DETR?3.1 Does Instability of the Bipartite Matching Affect Convergence?3.2 Are the Attention Modules the Main Cause?3.3 **Does DETR Really Need Cross-attention?**4. The Proposed Method.原创 2021-02-10 00:14:40 · 1903 阅读 · 0 评论 -
[DCN]Deformable Convolutional Networks
文章目录1. Motivation2. Contribution3. Deformable Convolutional Networks3.1 Deformable Convolution3.2 Deformable RoI Pooling3.3 Position-Sensitive (PS) RoI Pooling3.4 Deformable ConvNets1. Motivation 由于CNNs固定的几何结构,它们在建模几何变化中受到了限制。Convolutional neural net.原创 2021-02-02 22:07:22 · 314 阅读 · 0 评论 -
[PSS]Object Detection Made Simpler by Eliminating Heuristic NMS
文章目录1. Motivation2. Contribution3. Our Method3.1 Overall Training Objective3.1.1 PSS LOSS3.1.2 Ranking Loss3.2 One-to-many Label Assignment3.3 One-to-one Label Assignment3.4 Conflict in the Tow Classification Loss Terms3.5 Stop Gradient4. Experiments4.1 A.原创 2021-02-01 17:00:31 · 297 阅读 · 0 评论 -
[Xshell秘钥登录]使用XShell秘钥登录服务器并配好VSCODE
1. Xshell 新建公钥与私钥公钥存入服务器,私钥存入自己的电脑中。主要操作的新建用户秘钥生成向导,根据下列步骤或者私钥和公钥。注意,填写秘钥也需要一个口令密码,这个密码可以为空,那么后续进入VSCODE的时候,就不用了再输入密码了,但是安全性会低一点,有利有弊,我没有填写。导出私钥2. 服务器存入公钥# 使用原先的口令登录服务器# 进入到自己账户底下的.ssh/ 注意可以不是/root/.ssh 因为服务器 没有这么高的权限cd .ssh/cat xx.pub >原创 2021-01-13 20:32:31 · 446 阅读 · 0 评论 -
[Paper Reading]FCOS: Fully Convolutional One-Stage Object Detection
FCOS: Fully Convolutional One-Stage Object Detection1. introductionWe propose a fully convolutional one-stage object detec-tor (FCOS) to solve object detection in a per-pixel predic- tion fashion, analogue to semantic segmentation.作者提出了一个FCOS(全连接 单阶段原创 2020-10-04 21:56:52 · 302 阅读 · 0 评论 -
[AdelaiDet]配置安装并测试
AdelaiDet1. 前言AdelaiDet is an open source toolbox for multiple instance-level recognition tasks on top of Detectron2. All instance-level recognition works from our group are open-sourced here.2. install首先需要安装detectron2,参照install.md。注意,目前还不能和最新的版本适配。原创 2020-10-04 10:09:08 · 3583 阅读 · 13 评论 -
[python基础]基础文本操作
将jpg以偶数或者奇数结尾分开存储 问题:将RAW-VOC格式转化为COCO格式时,需要将原来的jpg文件以train和val.txt中的内容相应进行分离。1.普通文本操作#普通文本操作import osfile=open('/hdd2/wh/pascalraw/PASCALRAW/trainval/train.txt') #file=open('val.txt') file_list = [] labelMat = []for line in file.readli..原创 2020-10-02 10:32:31 · 281 阅读 · 1 评论