投稿

[论文简析]MobileNets: Efficient CNN for Mobile Vision Applications[1704.04861]

2221

4

2021-05-01 06:59:11

未经作者授权，禁止转载

正在缓冲...

论文题目:MobileNets: Efficient Convolutional Neural Networks for Mobile Vision Applications 论文地址:http://arxiv.org/abs/1704.04861 * 本视频旨在隔离期间维持up思维清晰能说人话，受能力限制经常出现中英混杂，散装英语等现象，请见谅。涉及论文理解报道出了偏差，欢迎各位怒斥。

秋刀鱼的炼丹工坊

计算机视觉

秋刀鱼的炼丹工坊发消息

经中此篇如此高深，我确实不懂。

通识

机器人学

表征学习

多模态/语言模型

新模型

内容生成

数据增广

一包薯条

[论文速览]Token Turing Machines[2211.09119]

05:08

[论文简析]NeRF in the Wild: NeRF for Unconstrained Photo Collections[2008.02268]

17:07

[论文简析]Exploring Self-attention for Image Recognition[2004.13621]

16:31

[论文简析]FlowNet3D: Learning Scene Flow in 3D Point Clouds[1806.01411]

13:05

[论文简析]NeRV: Neural Representations for Videos[2110.13903]

08:34

[论文简析]TokenLearner: What Can 8 Learned Tokens Do for Images and vids[2106.11297]

11:15

[论文简析]BiFormer: Vision Transformer with Bi-Level Routing Attention[2303.08810]

06:47

[论文简析]When Shift Operation Meets Vision Transformer[2201.10801]

05:59

[论文简析]DeepLab V3/V3+[1706.05587/1802.02611]

10:36

[论文速览]Deformable Convolutional Networks; DCN[1703.06211]

09:53

[论文简析]DeepLab: Semantic Image Segmentation with DCN..[1606.00915]

16:28

[论文简析]DAT: Vision Transformer with Deformable Attention[2201.00520]

07:00

[论文速览]Aggregating Nested Transformers[2105.12723]

07:41

[论文简析]X3D: Expanding Architectures for Efficient Video Recognition[2004.04730]

04:07

[论文简析]CeiT: Incorporating Convolution Designs into Visual Tr[2103.11816]

05:57

[论文速览]iFormer: Inception Transformer[2205.12956]

06:25

[论文速览]Bottleneck Transformers for Visual Recognition[2101.11605]

02:10

[论文简析]NAT: Neighborhood Attention Transformer[2204.07143]

05:14

[论文简析]XCiT: Cross-Covariance Image Transformers[2106.09681]

10:17

[论文简析]DeiT: Data-efficient Image Transformers[2012.12877]

09:49

[论文简析]TNT: Transformer in Transformer[2103.00112]

07:17

[论文简析]Tokens-to-Token ViT: Training ViT from Scratch on ImageNet[2101.11986]

04:16

[论文简析]Dynamic Vision Transformers with Adaptive Sequence Length[2105.15075]

12:21

[论文简析]SlowFast Networks for Video Recognition[1812.03982]

09:35

[论文简析]MViT: Multiscale Vision Transformers[2104.11227]

12:31

[论文简析]BEVT: BERT Pretraining of Video Transformers[2112.01529]

10:23

[论文简析]Unified Transformer for Efficient Spatiotemporal...[2201.04676]

06:28

[论文简析]MLP-Mixer: An all-MLP Architecture for Vision[2105.01601]

09:25

[论文速览]EViT: Expediting Vision Transformers via Token Reorganizations[2202.07800]

04:24

[论文简析]Is Space-Time Attention All You Need for Video Understanding?[2102.05095]

04:34

[论文简析]A Laplacian Pyramid Translation Network[2105.09188]

16:12

[论文简析]Per-Pixel Classification is Not All You Need for Semantic Seg[2107.06278]

10:29

[论文速览]Masked-attention Mask Tr. for Universal Image Segmentation[2112.01527]

08:02

[论文简析]MobileNets: Efficient CNN for Mobile Vision Applications[1704.04861]

06:03

[论文简析]MobileNet V2: Inverted Residuals and Linear Bottlenecks[1801.04381]

10:30

[论文简析]Searching for MobileNet V3[1905.02244]

08:04

[论文简析]MnasNet: Platform-Aware Neural Architecture Search for Mobile[1807.11626]

07:55

[论文简析]EfficientNet V1/V2[1905.11946/2104.00298]

13:29

[论文简析]Mobile-Former: Bridging MobileNet and Transformer[2108.05895]

13:49

[论文简析]Point Transformer[2012.09164]

11:54

[论文简析]Point Transformer V2[2210.05666]

10:36

[论文速览]RetNet: A Successor to Transformer for Large Language Models[2307.08621]

24:49

[论文简析]Vision Transformers Need Registers[2309.16588]

06:57

顶部