[论文简析]Tokens-to-Token ViT: Training ViT from Scratch on ImageNet[2101.11986]
发布人
打开封面 下载高清视频 观看高清视频 视频下载器
...
锁定重传‖运动后加速心跳声
...
[论文速览]Token Turing Machines[2211.09119]
...
新人助眠！有tian屏 自用！
...
[论文简析]PolyFormer: Referring Image Seg. as Sequential Polygon Gen [2302.07387]
...
[论文简析]DeiT: Data-efficient Image Transformers[2012.12877]
...
[论文简析]Location-Aware Self-Supervised Transformers for Semantic Seg.[2212.02400]
...
[论文速览]Theia: Distilling Diverse Vision Foundation Models for Robot..[2407.20179]
...
[论文简析]World Models[1803.10122]
...
[论文简析]Regularized Vector Quantization for Tokenized Image Synthesis[2303.06424]
...
[论文简析]Point Transformer V2[2210.05666]
...
[论文简析]BiFormer: Vision Transformer with Bi-Level Routing Attention[2303.08810]
...
数学视角下的Transformer！MIT数学系的Philippe Rigollett主讲，UCL助理教授Haitham精讲论文，自注意力机制、深度神经网络
...
[论文速览]Visual Prompt Tuning / VPT[2203.12119]
...
[论文简析]When Shift Operation Meets Vision Transformer[2201.10801]
...
[论文简析]ViT: Vision Transformer[2010.11929]
...
[论文简析]Exploring Self-attention for Image Recognition[2004.13621]
...
【对视脱敏训练】生气的可爱的阴阳怪气的女友
...
组会救星，神经网络绘图工具来了！ 组会救星，神经网络绘图工具来了！
...
【MATLAB论文复现】研一研二必看！MATLAB论文如何从代码到公式完整复现？看完这个你就彻底懂了！草履虫都能学会！
...
[论文简析]Point Transformer[2012.09164]
...
说点大实话，研究生“水”论文最实用的方法就是网络缝合模块！用上200+即插即用模块代码，大论文小论文轻松涨点！
...
【数学视角下的Transformer】不愧是MIT数学系的Philippe Rigollett——自注意力机制、深度神经网络、CV+NLP
...
[论文简析]Red Circle: Visual Prompt Engineering for VLMs[2304.06712]
...
超刺激舒服的甜耳！
...
[论文简析]TokenLearner: What Can 8 Learned Tokens Do for Images and vids[2106.11297]
...
[论文速览]OWL-ViT: Simple Open-Vocabulary Object Detection with ViT[2205.06230]
...
[论文简析]Improving fine-grained understanding in image-text pre-training[2401.0986]
...
真的超容易“搞深度学习神经网络到底怎么改代码的啊？”复旦博士教我用一本书搞定！
...
[论文简析]DAT: Vision Transformer with Deformable Attention[2201.00520]
...
《你要出轨》郭德纲 于谦（重温经典）
...
[论文简析]Keeping Your Eye on the Ball: Trajectory Attention...[2106.05392]
...
[论文速览]Open Vocab. Semantic Seg. with Patch Aligned Contrastive...[2212.04994]
...
[论文简析]VideoMoCo: ...Temporally Adversarial Examples[2103.05905]
...
[论文简析]MViT: Multiscale Vision Transformers[2104.11227]
...
70年老算法Dijkstra被证明普遍最优 斩获顶会FOCS 2024最佳论文
...
[论文速览]iFormer: Inception Transformer[2205.12956]
...
[论文简析]DINO Emerging Properties in SelfSupervised Vision Transformers[2104.14294]
...
[论文简析]Finding an Unsupervised Image Segmenter in .. Generative Model[2105.08127]
...
[论文速览]FreeU: Free Lunch in Diffusion U-Net[2309.11497]
...
[论文速览]CRG: Improving Grounding in VLM w/o training[2403.02325]