- 博客(11)
- 资源 (3)
- 收藏
- 关注
RSS订阅原创 语义分割VOC2012标签处理
语义分割VOC2012标签处理准备操作标签处理运行网络结语准备操作PASCAL-VOC2012数据集介绍官网： 点击VOC2012数据集分为20类，包括背景为21类，分别如下：Person: personAnimal: bird, cat, cow, dog, horse, sheepVehicle: aeroplane, bicycle, boat, bus, car, motorbike, trainIndoor: bottle, chair, dining table, potted
2021-04-10 14:07:42
2098
3
原创 论文阅读：CANet
CANet: Class-Agnostic Segmentation Networks with Iterative Refinement andAttentive Few-Shot Learning文章目录CANet: Class-Agnostic Segmentation Networks with Iterative Refinement andAttentive Few-Shot Learning初识（Abstract & Introduction & Conclusion）相知（
2020-09-29 20:02:26
1197
原创 论文阅读：Multi-Miner: Object-Adaptive Region Mining for Weakly-Supervised Semantic Segmentation
Multi-Miner: Object-Adaptive Region Mining for Weakly-Supervised Semantic Segmentation文章目录Multi-Miner: Object-Adaptive Region Mining for Weakly-Supervised Semantic Segmentation摘要Intruduction方法object-adaptive region miningmulti-scale training strategyconne
2020-09-10 16:58:16
442
原创 论文阅读：Synthesize then Compare: Detecting Failures and Anomalies for Semantic Segmentation
Synthesize then Compare: Detecting Failures and Anomalies for Semantic Segmentation文章目录Synthesize then Compare: Detecting Failures and Anomalies for Semantic Segmentation摘要主要贡献MethodologyExperiments个人总结原文下载摘要失败和异常监测能力是计算机视觉任务的基本要求，常规的作法是用模型生成的分割图和 grou
2020-08-01 19:25:01
1025
原创 论文阅读：Real-time Semantic Segmentation with Fast Attention
Real-time Semantic Segmentation with Fast Attention文章目录Real-time Semantic Segmentation with Fast Attention摘要贡献方法FA网络结构视频语义分割实验原文链接摘要对于语义分割任务，准确性的提升需要更大的感受野和更精细的空间特征，代价是计算开销的增长。为了解决这两个问题，本文提出了一个FA（快速注意力）方法，实现了速度和准确性的双赢。贡献1） 为了有效地进行语义分割，我们引入了非局部上下文聚合的
2020-07-22 22:01:06
2215
5
原创 论文阅读：Severity-Aware Semantic Segmentation with Reinforced Wasserstein Training
Severity-Aware Semantic Segmentation with Reinforced Wasserstein Training文章目录Severity-Aware Semantic Segmentation with Reinforced Wasserstein Training摘要主要贡献方法实验个人总结摘要基于交叉熵损失的像素分类在分割问题上取得成功，但是交叉熵有局限性。当使用交叉熵损失时，分割类别是独立考虑的，没有考虑成对儿误分类的不同严重程度。当发生错误预测时，不同误
2020-07-16 16:30:32
1321
原创 论文阅读：Unsupervised Intra-domain Adaptation for Semantic Segmentation through Self-Supervision
Unsupervised Intra-domain Adaptation for Semantic Segmentation through Self-Supervision原文链接 ：点击下载文章目录Unsupervised Intra-domain Adaptation for Semantic Segmentation through Self-Supervision摘要框架域间自适应阶段熵排序过程域内自适应阶段Experiments通过自监督用于语义分割的无监督域内自适应CVPR 2020.
2020-07-06 14:28:11
1862
1
原创 论文阅读：Dilated Convolutions with Lateral Inhibitions for Semantic Image Segmentation
CVPR 2020.6.5文章目录用于语义分割的带侧抑制的空洞卷积摘要论文出发点Dilated Convolutions with Lateral InhibitionsDefinitionImplementation of LI-ConvsLI-ASPP and LI-MNV2ExperimentsHow the LI layer worksWhat interests the model用于语义分割的带侧抑制的空洞卷积摘要空洞卷积可以扩大感受野，不增加而外权重和牺牲空间像素。但是空洞卷积在语义
2020-06-28 20:52:08
1844
原创 论文阅读：LRNNet:一种高效减少非局部操作的轻量级实时语义切分网络
一种高效减少非局部操作的轻量级实时语义切分网络文章目录一种高效减少非局部操作的轻量级实时语义切分网络论文的出发点文章的主要贡献METHODOLOGYPreliminaryOverview of the Network ArchitectureFactorized Convolution BlockSVN ModuleEXPERIMENTSCVPR 2020.64论文的摘要里说该文章提出了一个卷积分解模块FCB用来进行特征提取，非局部操作模块使用空间主导奇异向量来减少计算量和内存开销。最后在Citys
2020-06-25 19:54:06
796
1
空空如也
TA创建的收藏夹 TA关注的收藏夹
TA关注的人