投稿

[论文简析]MoCo: Momentum Contrast Learning[1911.05722/2003.04297]

6853

1

2021-03-26 04:35:23

未经作者授权，禁止转载

正在缓冲...

MoCo: Momentum Contrast for Unsupervised Visual Representation Learning v2: Improved baselines with momentum contrastive learning v3: https://www.bilibili.com/video/BV1UX4y1g7Dn/ * 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

非监督学习

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

[论文简析]Representation Learning with Contrastive Predictive Coding[1807.03748]

17:05

[论文速览]Data-Efficient Image Recog with Contrastive Predictive Coding[1905.09272]

06:16

[论文简析]SimCLR: A simple framework for contrastive learning[2002.05709]

03:12

[论文简析]SwAV: Swapping Assignments between multiple Views[2006.09882]

16:59

[论文简析]MoCo: Momentum Contrast Learning[1911.05722/2003.04297]

10:00

[论文简析]BYOL: Bootstrap Your Own Latent[2006.07733]

16:23

[论文简析]DINO Emerging Properties in SelfSupervised Vision Transformers[2104.14294]

09:56

[论文简析]SimSiam: Exploring Simple Siamese Representation Learning[2011.10566]

09:16

[论文简析]Barlow Twins:Self-Supervised Learning via Redundancy Reduction[2103.03230]

05:47

[论文速览]iBOT: Image BERT Pre-Training with Online Tokenizer[2111.07832]

07:15

[论文简析]Evolving Losses for Unsupervised Video Representation Learning[2002.12177]

18:33

[论文简析]Broaden Your Views for Self-Supervised Video Learning[2103.16559]

08:00

[论文速览]Self-supervised Video Transformer[2112.01514]

07:09

[论文简析]Extreme Masking for Learning Instance and Distributed Visual..[2206.04667]

05:22

[论文简析]Learning by Aligning Videos in Time[2103.17260]

11:13

[论文简析]Probabilistic Representations for Video Contrastive Learning[2204.03946]

14:47

[论文简析]Propagate Yourself: Exploring Pixel-Level Consistency...[2011.10043]

07:37

[论文简析]Location-Aware Self-Supervised Transformers for Semantic Seg.[2212.02400]

12:03

[论文简析]Rethinking Pre-training and Self-training[2006.06882]

08:21

[论文简析]Energy-Inspired Self-Supervised Pretraining for Vision Models[2302.01384]

11:08

[论文简析]Humble Teachers Teach Better Students for Semi-Supervised Object Detection

12:45

[论文简析]Towards Better Understanding of Self-Supervised Representation[2203.01881]

07:46

[论文简析]TransRank: SS Video...Ranking-based Transformation Recognition[2205.02028]

14:28

[论文速览]Object Discovery and Representation Networks[2203.08777]

05:52

[论文速览]Efficient Visual Pretraining with Contrastive Detection[2103.10957]

04:18

[论文简析]Directional SSL for Heavy Image Augmentations[2110.13555]

06:31

[论文速览]Invariant Information Clustering for Unsupervised Image...[1807.06653]

10:24

[论文速览]Video Rep. Learning by Recognizing Temporal Transformations[2007.10730]

06:34

[论文简析]β-VAE Learning basic visual concepts with a constrained variational...

12:50

[论文简析]DCLGAN/SimDCL: Dual Contrastive Learning[2104.07689]

06:01

[论文简析]Generative Scene Inference and Sampling...[1907.13052]

14:14

[论文简析]An Empirical Study of Training Self-Supervised ViT[2104.02057]

08:58

[论文速览]Multi-Object ... with Iterative Variational Inference[1903.00450]

15:29

[论文简析]MONet: Unsupervised Scene Decomposition and Representation[1901.11390]

13:43

[论文简析]Leveraging BG AUG to encourage semantic focus in SSCL[2103.12719]

04:34

[论文简析]Object-Centric Learning with Slot Attention[2006.15055]

09:18

[论文简析]Equivariant Contrastive Learning[2111.00899]

10:02

[论文简析]Big Self-Supervised Models are Strong Semi-Supervised Learners[2006.10029]

07:04

[论文简析]Keeping Your Eye on the Ball: Trajectory Attention...[2106.05392]

19:43

[论文简析]Wasserstein Contrastive Representation Distillation: WCoRD[2012.08674]

19:41

[论文速览]Masked Feature Prediction .Self-Supervised Visual Pre-Training[2112.09133]

05:17

[论文速览]AugSelf: Improving Transferability...Augmentation-Aware..[2111.09613]

04:09

[论文速览]Nearest-Neighbor Contrastive Learning of Visual Representations[2104.14548

05:34

[论文速览]Solving Inefficiency of Self-supervised Representation Learning[2104.0876]

06:17

[论文简析]VideoMoCo: ...Temporally Adversarial Examples[2103.05905]

06:43

[论文速览]Long Short View Feature Decomposition via Contrastive Video...[2109.11593]

06:09

[论文速览]Theia: Distilling Diverse Vision Foundation Models for Robot..[2407.20179]

08:04

[论文简析]Vi2CLR: Video and Image for Visual Contrastive Learning of Representation

09:12

[论文速览]Generative Modeling by Estimating Gradients of the Data Dist[1907.05600]

17:52

[论文简析]Unsupervised Learning of Object Keypoints for Perception..[1906.11883]

11:17

[论文简析]Progressive Stage-wise Learning for Unsupervised Feature.. [2106.05554]

07:39

[论文简析]Transf. Meta-learners for Implicit Neural Representations[2208.02801]

09:59

[论文速览]Jigsaw Clustering for Unsupervised Visual Representation Learn[2104.00323]

05:32

[论文速览]SS Video Representation Learning by Context&Motion Decoupling[2104.00862]

08:28

[论文简析]MixMAE & Mixed AE[2205.13137][2303.17152]

14:16

[论文速览]Finite Scalar Quantization: VQ-VAE Made Simple[2309.15505]

05:26

[论文简析]DropPos: Pre-Training ViTs by Reconstructing Dropped Positions[2309.03576]

06:22

[论文速览]SODA: Bottleneck Diffusion Models for Representation Learning[2311.17901]

13:59

[论文简析]Deconstructing Denoising Diffusion Models for SSL[2401.14404]

30:00

顶部