Tag: cv

Yolov5_DeepSort_Pytorch - Real-time multi-object tracker using YOLO v5 and deep sort https://t.co/zEFH2l4uuL

— Python Trending (@pythontrending) July 11, 2021

How does perception of objects arise? Objects undergo huge changes in appearance due to deformation, perspective change, & dynamic occlusion. We prove from first principles that it’s possible, without learning, to perceive invariant objects despite this. https://t.co/oTWSUmuzbk

— Doris Tsao (@doristsao) July 6, 2021

Global Filter Networks for Image Classification
pdf: https://t.co/dIeGFqtllM
abs: https://t.co/48uTA872An
project page: https://t.co/LyAIupelxl
github: https://t.co/0BcTRgg4pJ pic.twitter.com/aVds2AwhCC

— AK (@ak92501) July 2, 2021

CSWin Transformer: A General Vision Transformer Backbone with Cross-Shaped Windows
pdf: https://t.co/6KuG5MRGPM

85.4% Top-1 accuracy on ImageNet-1K without any extra training data or label, 53.9 box AP and 46.4 mask AP on the COCO detection task pic.twitter.com/pHZdSI0RBa

— AK (@ak92501) July 2, 2021

Focal Self-attention for Local-Global Interactions in
Vision Transformers
pdf: https://t.co/2mFN1OQzVG

largest Focal Transformer yields 58.7/58.9 box mAPs and 50.9/51.3 mask mAPs on COCO mini-val/test-dev, and 55.4 mIoU on ADE20K for semantic segmentation pic.twitter.com/ij7VYIbcQR

— AK (@ak92501) July 2, 2021

AutoFormer: Searching Transformers for Visual Recognition
pdf: https://t.co/BfcLzNpd2I
abs: https://t.co/pFSpFDrBOZ
github: https://t.co/SBeDmRhmET

AutoFormer-tiny/small/base achieve 74.7%/81.7%/82.4% top-1 accuracy on ImageNet with 5.7M/22.9M/53.7M parameters, respectively pic.twitter.com/kC8DykvoiM

— AK (@ak92501) July 2, 2021

Augmented Shortcuts for Vision Transformers
pdf: https://t.co/68X2iVPoQd
abs: https://t.co/bo2BI1Suoe

brings about 1% accuracy increase of the sota visual transformers without obviously increasing their parameters and FLOPs pic.twitter.com/UnaaJKvIUv

— AK (@ak92501) July 1, 2021

SCARF: Self-Supervised Contrastive Learning using Random Feature Corruption
pdf: https://t.co/YmfyNkLcC9
abs: https://t.co/m4kiQq0j5Q

technique for contrastive learning, where views are formed by corrupting a random subset of features pic.twitter.com/pP6phV9p3m

— AK (@ak92501) June 30, 2021

Early Convolutions Help Transformers See Better
pdf: https://t.co/5XTWUDzFag
abs: https://t.co/Faq0Yi18Bi

convolutional stem in ViT dramatically increases optimization stability and also improves peak performance (by ∼1-2% top-1 accuracy on ImageNet-1k) pic.twitter.com/q0gq67AyuF

— AK (@ak92501) June 29, 2021

CLIPDraw: Exploring Text-to-Drawing Synthesis through Language-Image Encoders
pdf: https://t.co/q7hsXvs6bY
abs: https://t.co/mHP3ZYCYhi
colab: https://t.co/igsVWKntOq pic.twitter.com/uEANOUp5E6

— AK (@ak92501) June 29, 2021

This tutorial will introduce compute and data-efficient transformers and provide a step-by-step to create your own Vision Transformers. Through this guide, you'll be able to train state of the art results for classification in both computer vision & NLP. https://t.co/d3bc7ijeBJ

— PyTorch (@PyTorch) June 28, 2021

Single Image Texture Translation for Data Augmentation
pdf: https://t.co/pAWU2Kn0PL
abs: https://t.co/krjNbyN8em
project page: https://t.co/h1xKObA9Do pic.twitter.com/8fya7pYEh8

— AK (@ak92501) June 28, 2021