HyperAI

Image Classification

Image classification is a fundamental task in computer vision, aiming to understand and categorize entire images by assigning them specific labels. This task typically targets images of single objects and achieves high-precision classification through technologies such as deep learning, with broad application value including content recognition and scene understanding. When classification reaches the instance level, it becomes associated with image retrieval, which also involves finding similar images in large databases.

ImageNet
DiNAT-Base
CIFAR-10
DINOv2 (ViT-g/14, frozen model, linear eval)
CIFAR-100
EffNet-L2 (SAM)
STL-10
µ2Net+ (ViT-L/16)
ObjectNet
BiT-L (ResNet-152x4)
MNIST
Branching/Merging CNN + Homogeneous Vector Capsules
SVHN
Wide-ResNet-28-10
iNaturalist 2018
MAE (ViT-H, 448)
ImageNet ReaL
VOLO-D5
Flowers-102
CCT-14/7x2
Clothing1M
mini WebVision 1.0
Fashion-MNIST
PreAct-ResNet18 + FMix
VTAB-1k
ALIGN (50 hypers/task)
ImageNet V2
Model soups (ViT-G/14)
Kuzushiji-MNIST
KMNIST-Tiny
Stanford Cars
iNaturalist 2019
CeiT-S
OmniBenchmark
NOAH-ViTB/16
Tiny ImageNet Classification
Astroformer
EMNIST-Balanced
WaveMixLite-128/7
DF20
ViT-Large/16 (384)
DF20 - Mini
ViT-Large/16 (384)
RESISC45
iNaturalist
iSQRT-COV-Net
ColonINST-v1 (Seen)
ColonINST-v1 (Unseen)
WebVision-1000
CurriculumNet (InceptionResNet-v2)
Places205
MAE (ViT-H, 448)
EuroSAT
µ2Net+ (ViT-L/16)
DTD
NNCLR
EMNIST-Letters
VGG-5(Spinal FC)
CINIC-10
VIT-L/16 (Spinal FC, Background)
Clothing1M (using clean data)
CurriculumNet
GasHisSDB
CoAtNet-1
EMNIST-Digits
µ2Net (ViT-L/16)
Places365
InternImage-H(CNN)
smallNORB
Heinsen Routing
Tiered ImageNet 5-way (5-shot)
EGNN+Transduction
Colored-MNIST(with spurious correlation)
MLP-DecAug
Food-101
Bamboo (ViTB/16)
iWildCam2020-WILDS
COSMO
Oxford-IIIT Pets
CeiT-S (384 finetune resolution)
PlantVillage
SAG-ViT
Caltech-256
AG-Net
Oxford-IIIT Pet Dataset
TWIST (ResNet-50)
Red MiniImageNet 20% label noise
FaMUS
Red MiniImageNet 40% label noise
FaMUS
Red MiniImageNet 80% label noise
FaMUS
CIFAR-10 (with noisy labels)
SSR
CUB
Entropy-based Logic Explained Network
Food-101N
LRA-diffusion (CLIP ViT)
JFT-300M
V-MoE-H/14 (Every-2)
MAMe
EfficientNet-B3
N-MNIST
STS-ResNet
ObjectNet (Bounding Box)
BiT-L (ResNet)
Oracle-MNIST
ResNet-18 + Vision Eagle Attention
Places365-Standard
SWAG (ViT H/14)
Red MiniImageNet 60% label noise
FaMUS
Tiny-ImageNet
UPANets
Visual Wake Words
BreakHis
WaveMix
CelebA 64x64
cFlow
EarlyNSD
EuroSAT-SAR
FlickrLogos-32
Id Pattern Dataset
Claude 3 Opus
ISIC2018
Kvasir
HiFuse_Small
Malaria Dataset
kEffNet-B0 V2 16ch
N-Caltech 101
SIPaKMeD
DL+PCA+GWO
Causal3DIdent
SimCLR
Certificate Verification
ResMLP-24
CIFAR-10 (40 Labels, ImageNet-100 Unlabeled)
CIFAR-10, 40% Symmetric Noise
FaMUS
CIFAR-10, 60% Symmetric Noise
MentorMix
CIFAR-10 Image Classification
ASF-former-S
CIFAR-100, 40% Symmetric Noise
FaMUS
CLEVR/Count
SEER (RegNet10B)
CLEVR/Dist
SEER (RegNet10B)
CUB-200-2011
Sparse-CBM
Fracture/Normal Shoulder Bone X-ray Images on MURA
Our Ensemble Learning-2
Galaxy10 DECals
WaveMix
HErlev
DL+PCA+GWO
ImageNet-10
ResNet-50 + UDA+AutoDropout
ImageNet-100
SparseSwin with L2
ImageNet-Hard
EfficientNet-L2-Ns
Imagenette
Imbalanced CUB-200-2011
Intel Image Classification
ISIC 2018
Large Labelled Logo Dataset (L3D)
L3D_original_2level
LIMUC
Inception-v3
Noisy MNIST (AWGN)
Noisy MNIST (Contrast)
Noisy MNIST (Motion)
ObjectNet (ImageNet classes)
Diffusion Classifier (zero-shot)
split CIFAR-100
OFSCIL
WebVision
PropMix (Ours)
AmsterTime
AP-GeM (ResNet-101)
ArtDL
ResNet-50
CARS196
cats_vs_dogs
µ2Net+ (ViT-L/16)
Chaoyang
HSANR
CIFAR-100, 60% Symmetric Noise
MentorMix
CIFAR-100 (alpha=0, 20 clients per round)
cifar-10,4000
WRN-28-2 + UDA+AutoDropout
cifar10
cifar100
shreynet
Deep PCB
DVS128 Gesture
SNN
EMNIST-Byclass
EMNIST-Bymerge
ESC-50
SDGM-D
FEMNIST
FGVC Aircraft
TransBoost-ResNet50
FGVC-Aircraft
EnGraf-Net101 (G=4, H=1)
Flower102
Flowers (Tensorflow)
CNN+ Wilson-Cowan model RNN
FMD (materials)
GTSRB
iCassava'19
E2E-3M
ImageNet-100 (Class-IL, 5T)
MoCo + CaSSLe
imagenet-1k
BinaryViT
ImageNet-32
WRN (N=28, k=10)
ImageNet-64
WRN (N=36, k=5)
ImageNet-9
ImageNet-P
SqueezeNet + Simple Bypass
ImageNet-Sketch
µ2Net+ (ViT-L/16)
iNat2021-mini
WaveMix-256/16 (level 2)
ISBNet
ThanosNet
KITTI-Dist
SEER (RegNet10B)
KMNIST
µ2Net (ViT-L/16)
KTH-TIPS2
RADAM (ConvNeXt-XL)
LabelMe
CoNAL
WaveMixLite
MNIST-rot-12
PDO-eConv (ours)
MNIST-rot-12k (DA)
PDO-eConv (ours)
MultiMNIST
CapsNet
NCT-CRC-HE-100K
No Background RGB Arabic Alphabets Sign Language Dataset
PASCAL VOC 2007
NNCLR
Pets SAM
PlantDoc
kMobileNet V3 Large 16ch
PRImA
ResNet-152 2x (RS training)
QMNIST
Deep regularization
RGB Arabic Alphabet Sign Language (AASL) dataset
SARS-COV-2
Fuzzy rank-based fusion of CNN models using Gompertz function
So2Sat LCZ42
ResNet50
Split CIFAR-10
Split Fashion M-NIST
Split M-NIST
Model with negotiation paradigm
Sports10
Max Margin Contrastive
Stanford Online Products
SUN397
TransBoost-ResNet50
Surrey ASL
E2E-3M
Training and validation dataset of capsule vision 2024 challenge.
BiomedCLIP+PubmedBERT
VizWiz-Classification
VOLO-D5
blurry images
custom
imagefolder
ISIC 2018+Atlas Dermatology
New Plant Diseases Dataset
touchtech/fashion-images-gender-age