[论文简析]MoCo: Momentum Contrast Learning[1911.05722/2003.04297]
作者: 秋刀鱼的炼丹工坊
作者简介: 经中此篇如此高深，我确实不懂。
描述: 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。
![[论文简析]MoCo: Momentum Contrast Learning[1911.05722/2003.04297]](/image/ee79c193a72ba027e9d9364e21d43999dd178ea8.jpg)
![[论文简析]MViT: Multiscale Vision Transformers[2104.11227]](/image/76601dbb2bc4001e5c21ad930219dd7750550b12.jpg@336w_190h_!web-video-rcmd-cover.avif)
![[论文简析]DeiT: Data-efficient Image Transformers[2012.12877]](/image/dcc355c0e181bc0795eb94f32bc610c619a3644f.jpg@336w_190h_!web-video-rcmd-cover.avif)
![[论文速览]Flamingo: a Visual Language Model for Few-Shot Learning[2204.14198]](/image/a5b7b2df9b63556dec7e0bbfc59af984002df067.jpg@336w_190h_!web-video-rcmd-cover.avif)
![[论文简析]TNT: Transformer in Transformer[2103.00112]](/image/7fdd630342ba1eb8257c44e4882cb9bb4fb5a8dc.jpg@336w_190h_!web-video-rcmd-cover.avif)
![[论文速览]NeRF-RL: Reinforcement Learning with Neural Radiance Fields[2206.01634]](/image/e7657581954d0419fe11141cc9f2cb139c03ae3a.jpg@336w_190h_!web-video-rcmd-cover.avif)
![[论文简析]Barlow Twins:Self-Supervised Learning via Redundancy Reduction[2103.03230]](/image/1bcf9e12198846b6f9f3abc1d7fc23be3d4f191a.jpg@336w_190h_!web-video-rcmd-cover.avif)
![[论文简析]SimCLR: A simple framework for contrastive learning[2002.05709]](/image/968ab97132af97121231da5aab3da940bd0da79f.jpg@336w_190h_!web-video-rcmd-cover.avif)
![[论文简析]Contrastive Learning for Unpaired Image-to-Image Translation[2007.15651]](/image/7936341661ef31b2154ba4d35adddae206eee97c.jpg@336w_190h_!web-video-rcmd-cover.avif)
![[论文简析]Per-Pixel Classification is Not All You Need for Semantic Seg[2107.06278]](/image/f703f8986abdb6cd927a971469ebdeceee108491.jpg@336w_190h_!web-video-rcmd-cover.avif)
![[论文简析]SwAV: Swapping Assignments between multiple Views[2006.09882]](/image/46ce612332b214ab9730d213ab3a950b033734a3.jpg@336w_190h_!web-video-rcmd-cover.avif)
![[论文简析]BiFormer: Vision Transformer with Bi-Level Routing Attention[2303.08810]](/image/615293b2b427919f5e60e6cdc71f64c2e63ec45b.jpg@336w_190h_!web-video-rcmd-cover.avif)
![[论文速览]Open-vocabulary Object Segmentation with Diffusion Models[2301.05221]](/image/26c842e666376f43985f95db7e029f46f9a4105d.jpg@336w_190h_!web-video-rcmd-cover.avif)
![[论文简析]Robust and Generalizable Visual ... via Random Convolutions[2007.13003]](/image/ca295de99235dee3d04e2a8b377a1931c47f9d8f.jpg@336w_190h_!web-video-rcmd-cover.avif)
![[论文简析]Rainbow:Combining Improvements in Deep Reinforcement Learning[1710.02298]](/image/ccd8b86c369f1c93938c48a112302ca1f3f259de.jpg@336w_190h_!web-video-rcmd-cover.avif)
![[论文简析]Deep Unsupervised Learning using Nonequilibrium Thermodynamics[1503.03585]](/image/39562e9b6d31cccb17a568786cfcd26b70049306.jpg@336w_190h_!web-video-rcmd-cover.avif)
![[论文简析]Representation Learning with Contrastive Predictive Coding[1807.03748]](/image/5348cc68d5b6933b20c252dce6378a70ac84b3be.jpg@336w_190h_!web-video-rcmd-cover.avif)
![[论文简析]Is Space-Time Attention All You Need for Video Understanding?[2102.05095]](/image/1ce75e88aad08d86e23038a6c0ebf096592f89a7.jpg@336w_190h_!web-video-rcmd-cover.avif)
![[论文速览]LLaRA: Supercharging Robot Learning Data for VLM Policy[2406.20095]](/image/9785f9a0d0deadc1303736a7165537e65be2679b.jpg@336w_190h_!web-video-rcmd-cover.avif)
![[论文简析]FlowNet3D: Learning Scene Flow in 3D Point Clouds[1806.01411]](/image/67d2d77188a3b38fb0b77d0bb4046e080bb04bca.jpg@336w_190h_!web-video-rcmd-cover.avif)
![[论文速览]LLaMA-Adapter: Efficient Fine-tuning..Zero-init Attention[2303.16199]](/image/ff64905ff76efb4bdc968dba0fb20828d5ee895f.jpg@336w_190h_!web-video-rcmd-cover.avif)
![[论文简析]DreamBooth: Fine Tuning Text-to-Image Diffusion Models...[2208.12242]](/image/9ff69e5a2ffad89c8320f028fbe030a233705fec.jpg@336w_190h_!web-video-rcmd-cover.avif)
![[论文速览]OWL-ViT: Simple Open-Vocabulary Object Detection with ViT[2205.06230]](/image/b12d6db9c796519cb92473fcf3faeb9bfe8f8f09.jpg@336w_190h_!web-video-rcmd-cover.avif)
![[论文简析]EfficientNet V1/V2[1905.11946/2104.00298]](/image/87b2d9c1fb493d66493188547ff8882f64ed1cc4.jpg@336w_190h_!web-video-rcmd-cover.avif)
![[论文简析]Stabilizing transformers for reinforcement learning[1910.06764]](/image/8b7d2edf2c685321471d5051139d099f2c9bf67b.jpg@336w_190h_!web-video-rcmd-cover.avif)
![[论文速览]Nearest-Neighbor Contrastive Learning of Visual Representations[2104.14548](/image/46d39238c6f2a2ada2271a67e1ca2e9d4ce1226b.jpg@336w_190h_!web-video-rcmd-cover.avif)
![[论文速览]OpenVLA: An Open-Source Vision-Language-Action Model[2406.09246]](/image/97b2ad4dadd7714ad58325530a1aec7346b60b63.jpg@336w_190h_!web-video-rcmd-cover.avif)
![[论文简析]An Empirical Study of Training Self-Supervised ViT[2104.02057]](/image/c1c21e44dab686ef10a7529dc87530ba0d00e06d.jpg@336w_190h_!web-video-rcmd-cover.avif)
![[论文简析]VideoMoCo: ...Temporally Adversarial Examples[2103.05905]](/image/90b08c1ca295e02a9552e1107b7ae5f9c97d1a00.jpg@336w_190h_!web-video-rcmd-cover.avif)
![[论文速览]EViT: Expediting Vision Transformers via Token Reorganizations[2202.07800]](/image/cab99e2b1d0ddc5415d6582fd3686ff3a1b0e07d.jpg@336w_190h_!web-video-rcmd-cover.avif)
![[论文简析]Point Transformer V2[2210.05666]](/image/315ba3a4cee3b386b91b917645182e2935d121ef.jpg@336w_190h_!web-video-rcmd-cover.avif)
![[论文简析]Learning by Aligning Videos in Time[2103.17260]](/image/ce882df3fa95bdc1316f24361ba32f698bf2f50c.jpg@336w_190h_!web-video-rcmd-cover.avif)
![[论文简析]Regularized Vector Quantization for Tokenized Image Synthesis[2303.06424]](/image/1752fa577031247b5525a5b409ff253e1333078d.jpg@336w_190h_!web-video-rcmd-cover.avif)
![[论文速览]Deformable Convolutional Networks; DCN[1703.06211]](/image/7f943dee72e49231af989279937c8ab69bc58e7a.jpg@336w_190h_!web-video-rcmd-cover.avif)
![[论文速览]DDPG&TD3[1509.02971][1802.09477]](/image/1e1512d8675a6dff55aadac90b3a47a15c16e361.jpg@336w_190h_!web-video-rcmd-cover.avif)
![[论文速览]LoRA: Low-Rank Adaptation of Large Language Models[2106.09685]](/image/2f4cb362cc5e24a347a012cfa05220728950cc9a.jpg@336w_190h_!web-video-rcmd-cover.avif)
![[论文简析]SAC: Soft Actor-Critic Part 2[1812.05905]](/image/f2a00b7b7fdeb0b2741b737bb78c399cb4516db0.jpg@336w_190h_!web-video-rcmd-cover.avif)
![[论文简析]Unified Transformer for Efficient Spatiotemporal...[2201.04676]](/image/e4d64d905db33797e019cadd48765d199a7ac793.jpg@336w_190h_!web-video-rcmd-cover.avif)
![[论文简析]Leveraging BG AUG to encourage semantic focus in SSCL[2103.12719]](/image/f6f9a0ca4475f069e46f39662412c10f0e3be9b7.jpg@336w_190h_!web-video-rcmd-cover.avif)
![[论文速览]Learning to Learn with Generative Models of NN Checkpoints[2209.12892]](/image/ae47e9b9f347382b250a0bfa71800e38227f4104.jpg@336w_190h_!web-video-rcmd-cover.avif)
![[论文简析]Keeping Your Eye on the Ball: Trajectory Attention...[2106.05392]](/image/83ec732929c4867b54ce51c76ef0d86840ae1a76.jpg@336w_190h_!web-video-rcmd-cover.avif)