Tag: cv

Global Tracking Transformers
abs: https://t.co/5WnYWJ828P
github: https://t.co/T6pRUuDV0H pic.twitter.com/t03qi0jKFt

— AK (@ak92501) March 25, 2022

BigDetection: A Large-scale Benchmark for Improved Object Detector Pre-training
abs: https://t.co/WiP9Y4fw9n
github: https://t.co/VP1VviW5q1 pic.twitter.com/fJ1FIQzUmi

— AK (@ak92501) March 25, 2022

GradViT: Gradient Inversion of Vision Transformers
abs: https://t.co/IlinGOlMvD pic.twitter.com/TDTKPA2Xym

— AK (@ak92501) March 23, 2022

.@Gradio demo for MMOCR, an open-source toolbox based on PyTorch and mmdetection for text detection, text recognition, and the corresponding downstream tasks including key information extraction on @huggingface Spaces
demo: https://t.co/iXutKDQcDO
github: https://t.co/2CxDTVslSJ pic.twitter.com/v5BFh8xItw

— AK (@ak92501) March 18, 2022

.@Gradio Demo for YOLOX: Exceeding YOLO Series in 2021 on @huggingface Spaces
demo: https://t.co/8iNN2Rhqea
github: https://t.co/rym6pRl10e pic.twitter.com/cBpl9T8akZ

— AK (@ak92501) March 17, 2022

On the surprising tradeoff between ImageNet
accuracy and perceptual similarity
abs: https://t.co/FAWkG1OIX5

show that an inverse-U relationship exists between accuracy and PS across a number of settings pic.twitter.com/GHnj2MJUgP

— AK (@ak92501) March 10, 2022

EdgeFormer: Improving Light-weight ConvNets by Learning from Vision Transformers
abs: https://t.co/Ju4EJMasSZ pic.twitter.com/wZSb4v8ZVv

— AK (@ak92501) March 9, 2022

The (Un)Surprising Effectiveness of Pre-Trained Vision Models for Control
abs: https://t.co/kFVZx80f2u pic.twitter.com/Tm723A7aqC

— AK (@ak92501) March 8, 2022

DiT: Self-supervised Pre-training for Document Image Transformer
abs: https://t.co/OUQ94iQ6dY

achieves sota results on downstream tasks, e.g. document image classification (91.11 → 92.69), document layout analysis (91.0 → 94.9) and table detection (94.23 → 96.55) pic.twitter.com/uZWAMGh71s

— AK (@ak92501) March 7, 2022

Paying U-Attention to Textures: Multi-Stage Hourglass Vision Transformer for Universal Texture Synthesis
abs: https://t.co/apd0do8HZH pic.twitter.com/d4zfL8wMlO

— AK (@ak92501) February 24, 2022

Self-Supervised Transformers for Unsupervised Object Discovery using Normalized Cut
abs: https://t.co/FotRPtnsBG
project page: https://t.co/ZoNZrniFcX pic.twitter.com/i3XqB53uCZ

— AK (@ak92501) February 24, 2022

Visual Attention Network
abs: https://t.co/K0tUUFx3qk
github: https://t.co/wPaXMoXVwL pic.twitter.com/rjMYHrrWgF

— AK (@ak92501) February 22, 2022