研究方向
白天
夜间
首页
下载
阅读记录
书签管理
我的书签
添加书签
移除书签
视觉问答
浏览
86
扫码
分享
2022-07-09 04:34:23
面试笔记
VQA视觉问答
笔记
VQA数据集预处理与加载
Label Embedding for Zero Shot VQA
若有收获,就点个赞吧
0 人点赞
上一篇:
下一篇:
Video Instance Segmentation(VIS)
Transformer
Pix2Seq
Detection
分类
Transformer
Transformers in Vision: A Survey
Cell-DETR
Deeep learning基础知识
分类
Backbone
Loss Function
检测
FCOS(ICCV2019)
CondInst
EfficientDet
RetinaNet
YOLO v1-v4
R-CNN到Faster-Rcnn
SSD: Single Shot MultiBox Detector
分割
Optimizer
学习噪声(Deep Learning Noisy Labels)
Segmentation
Classification
Learning to Learn
Controlling Label-Noise
Dividemix
Confident Learning
Detection
Noise-Aware Fully Webly Supervised Object Detection
算法比赛
Journey_Competition
医学影像处理
Continuous_Blood_Pressure_Estimation
场景文本检测和识别(OCR)
Video_OCR
BOVText
VideoTextTracking
Text Retrival
auxiliary method
FET-GAN(AAAI oral)
SynthText(2015)
SwapText(CVPR2020)
VISD(ECCV2018)
GA-DAN(CVPR2019)
UnrealText(CVPR2020)
端到端
MANGO(AAAI2021)
ABCNet(2020CVRP)
文本识别
ABINet(CVPR2021oral)
GTC(AAAI2020)
文本检测
DRRG(2020CVPRoral)
小样本学习(Few-Shot)
Matching networks
Category Traversal
如何提升泛化能力?
域迁移(Domain Adaptive)
Style Transfer
Transfer_Learning
分割方向
Uncertainty Estimation IJCAI (2020)
MaximumSquaresLoss(2019ICCV)
Adversarial entropy(CVPR2019)
分类方向
Optimal Transport
Unsupervised Domain Adaptation by Backpropagation
Unknown target(ECCV2018)
目标检测方向
Graph-induced Prototype
Strong-Weak(CVPR2019)
STD-Domain
Selective Alignment(CVPR2019)
H-divergence(CVPR2018)
BSR-WST(CVPR2019)
视觉问答
面试笔记
VQA视觉问答
笔记
VQA数据集预处理与加载
Label Embedding for Zero Shot VQA
自监督学习(Self-Supervised Learning)
Segmentation
Improving Semantic Segmentation via Self-Training
Self-Supervised Semantic Segmentation(AAAI 2018 as a spotlight paper)
Object Detection
Selective Self-Training
Representation Learning
MoCo
Contrastive Multiview Coding
Data-efficient image recognition
InfoNCE
Self-Talking
About Me
暂无相关搜索结果!
让时间为你证明
分享,让知识传承更久远
×
文章二维码
×
手机扫一扫,轻松掌上读
文档下载
×
请下载您需要的格式的文档,随时随地,享受汲取知识的乐趣!
PDF
文档
EPUB
文档
MOBI
文档
书签列表
×
阅读记录
×
阅读进度:
0.00%
(
0/0
)
重置阅读进度
×
思维导图备注