← Explore

Image Classification

cs.CV · 10 papers

cs.CV · 2024

Visual Autoregressive Modeling: Scalable Image Generation via Next-Scale Prediction

FID: 1.73

Keyu Tian, Yi Jiang +3

We present Visual AutoRegressive modeling (VAR), a new generation paradigm that redefines the autoregressive learning on images as coarse-to-fine "next-scale prediction" or…

Code· 8.7k
cs.CV · 2023

DINOv2: Learning Robust Visual Features without Supervision

ImageNet-1k: 86.5%

Maxime Oquab, Timothée Darcet +24

The recent breakthroughs in natural language processing for model pretraining on large quantities of data have opened the way for similar foundation models in computer vision.…

Code· 13k
cs.LG · 2020

Bootstrap Your Own Latent (BYOL)

ImageNet: 74.3%

Jean-Bastien Grill, Florian Strub +12

We introduce Bootstrap Your Own Latent (BYOL), a new approach to self-supervised image representation learning. BYOL relies on two neural networks, referred to as online and…

Code· 15k
cs.CV · 2019

Momentum Contrast (MoCo)

ImageNet-1M: 60.6%

Kaiming He, Haoqi Fan +3

We present Momentum Contrast (MoCo) for unsupervised visual representation learning. From a perspective on contrastive learning as dictionary look-up, we build a dynamic…

Code· 5.1k
cs.LG · 2020

SimCLR Explained: A Simple Framework for Contrastive Learning of Visual Representations

ImageNet: 76.5%

Ting Chen, Simon Kornblith +2

This paper presents SimCLR: a simple framework for contrastive learning of visual representations. We simplify recently proposed contrastive self-supervised learning algorithms…

Code· 4.5k
cs.CV · 2021

Masked Autoencoders Are Scalable Vision Learners

ImageNet-1K: 87.8%

Kaiming He, Xinlei Chen +4

This paper shows that masked autoencoders (MAE) are scalable self-supervised learners for computer vision. Our MAE approach is simple: we mask random patches of the input image…

Code· 8.3k
cs.LG · 2019

Deep Double Descent: Where Bigger Models and More Data Hurt

CIFAR-10: 15%

Preetum Nakkiran, Gal Kaplun +4

We show that a variety of modern deep learning tasks exhibit a "double-descent" phenomenon where, as we increase model size, performance first gets worse and then gets better.…

Code
cs.CV · 2021

High-Resolution Image Synthesis with Latent Diffusion Models

FID: 5.11

Robin Rombach, Andreas Blattmann +3

By decomposing the image formation process into a sequential application of denoising autoencoders, diffusion models (DMs) achieve state-of-the-art synthesis results on image…

Code· 14k
cs.CV · 2020

An Image is Worth 16x16 Words: Vision Transformers

ImageNet-1K: 88.55%

Alexey Dosovitskiy, Lucas Beyer +10

While the Transformer architecture has become the de-facto standard for natural language processing tasks, its applications to computer vision remain limited. In vision,…

Code· 13k
cs.CV · 2015

Deep Residual Learning for Image Recognition

Top-5 Error: 3.57%

Kaiming He, Xiangyu Zhang +2

Deeper neural networks are more difficult to train. We present a residual learning framework to ease the training of networks that are substantially deeper than those used…

Code· 6.7k