HyperAI

Image Classification

Bildklassifizierung ist eine grundlegende Aufgabe im Bereich der Computer Vision, die darauf abzielt, ganze Bilder zu verstehen und zu kategorisieren, indem ihnen spezifische Labels zugewiesen werden. Diese Aufgabe richtet sich in der Regel auf Bilder von einzelnen Objekten und erreicht durch Technologien wie Deep Learning eine hochpräzise Klassifizierung. Sie hat einen breiten Anwendungswert, einschließlich der Inhaltserkennung und Szenerkenntnis. Wenn die Klassifizierung auf Instanzenebene erfolgt, steht sie in Zusammenhang mit der Bildsuche, die auch das Auffinden ähnlicher Bilder in großen Datenbanken umfasst.

AmsterTime
AP-GeM (ResNet-101)
ArtDL
ResNet-50
blurry images
BreakHis
WaveMix
Caltech-256
AG-Net
CARS196
cats_vs_dogs
µ2Net+ (ViT-L/16)
Causal3DIdent
SimCLR
CelebA 64x64
cFlow
Certificate Verification
ResMLP-24
Chaoyang
HSANR
CIFAR-10
DINOv2 (ViT-g/14, frozen model, linear eval)
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-10 (with noisy labels)
SSR
CIFAR-100
Label-Ranker
CIFAR-100, 40% Symmetric Noise
FaMUS
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
CINIC-10
VIT-L/16 (Spinal FC, Background)
CLEVR/Count
SEER (RegNet10B)
CLEVR/Dist
SEER (RegNet10B)
Clothing1M
Clothing1M (using clean data)
CurriculumNet
ColonINST-v1 (Seen)
ColonINST-v1 (Unseen)
Colored-MNIST(with spurious correlation)
MLP-DecAug
CUB
Entropy-based Logic Explained Network
CUB-200-2011
Sparse-CBM
custom
Deep PCB
DF20
ViT-Large/16 (384)
DF20 - Mini
ViT-Large/16 (384)
DTD
Linear FT(ViT-L/14)
DVS128 Gesture
SNN
EarlyNSD
EMNIST-Balanced
WaveMixLite-128/7
EMNIST-Byclass
EMNIST-Bymerge
EMNIST-Digits
µ2Net (ViT-L/16)
EMNIST-Letters
VGG-5(Spinal FC)
ESC-50
SDGM-D
EuroSAT
µ2Net+ (ViT-L/16)
EuroSAT-SAR
Fashion-MNIST
Continued fraction of straight lines
FEMNIST
FGVC Aircraft
TransBoost-ResNet50
FGVC-Aircraft
EnGraf-Net101 (G=4, H=1)
FlickrLogos-32
Flower102
Flowers-102
CCT-14/7x2
Flowers (Tensorflow)
CNN+ Wilson-Cowan model RNN
FMD (materials)
Food-101
TransBoost-ResNet50
Food-101N
LRA-diffusion (CLIP ViT)
Fracture/Normal Shoulder Bone X-ray Images on MURA
Our Ensemble Learning-2
Galaxy10 DECals
WaveMix
GasHisSDB
CoAtNet-1
GTSRB
HErlev
Fuzzy Distance Ensemble
iCassava'19
E2E-3M
Id Pattern Dataset
Claude 3 Opus
imagefolder
ImageNet
GAC-SNN MS-ResNet-34
ImageNet-10
ResNet-50 + UDA+AutoDropout
ImageNet-100
SparseSwin with L2
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-Hard
EfficientNet-L2-Ns
ImageNet-P
SqueezeNet + Simple Bypass
ImageNet ReaL
ViT-H @224 (DeiT III, 21k)
ImageNet-Sketch
µ2Net+ (ViT-L/16)
ImageNet V2
Model soups (ViT-G/14)
Imagenette
Imbalanced CUB-200-2011
iNat2021-mini
WaveMix-256/16 (level 2)
iNaturalist
AIMv2-3B (448 res)
iNaturalist 2018
InternImage-H
iNaturalist 2019
Hiera-H (448px)
Intel Image Classification
ISBNet
ThanosNet
ISIC 2018
ISIC 2018+Atlas Dermatology
ISIC2018
iWildCam2020-WILDS
COSMO
JFT-300M
V-MoE-H/14 (Every-2)
KITTI-Dist
SEER (RegNet10B)
KMNIST
µ2Net (ViT-L/16)
KTH-TIPS2
RADAM (ConvNeXt-XL)
Kuzushiji-MNIST
KMNIST-Tiny
Kvasir
HiFuse_Small
LabelMe
CoNAL
Large Labelled Logo Dataset (L3D)
L3D_original_2level
LIMUC
Inception-v3
Malaria Dataset
kEffNet-B0 V2 16ch
MAMe
EfficientNet-B3
mini WebVision 1.0
MNIST
Branching/Merging CNN + Homogeneous Vector Capsules
MNIST-rot-12
PDO-eConv (ours)
MNIST-rot-12k (DA)
PDO-eConv (ours)
MultiMNIST
CapsNet
N-Caltech 101
N-MNIST
STS-ResNet
NCT-CRC-HE-100K
New Plant Diseases Dataset
No Background RGB Arabic Alphabets Sign Language Dataset
Noisy MNIST (AWGN)
Noisy MNIST (Contrast)
Noisy MNIST (Motion)
ObjectNet
CoCa
ObjectNet (Bounding Box)
BiT-L (ResNet)
ObjectNet (ImageNet classes)
Diffusion Classifier (zero-shot)
OmniBenchmark
NOAH-ViTB/16
Oracle-MNIST
ResNet-18 + Vision Eagle Attention
Oxford-IIIT Pet Dataset
TWIST (ResNet-50)
Oxford-IIIT Pets
CeiT-S (384 finetune resolution)
PASCAL VOC 2007
NNCLR
Pets SAM
Places205
MAE (ViT-H, 448)
Places365
InternImage-H(CNN)
Places365-Standard
SWAG (ViT H/14)
PlantDoc
kMobileNet V3 Large 16ch
PlantVillage
SAG-ViT
PRImA
ResNet-152 2x (RS training)
QMNIST
Deep regularization
Red MiniImageNet 20% label noise
PropMix
Red MiniImageNet 40% label noise
FaMUS
Red MiniImageNet 60% label noise
InstanceGM-SS
Red MiniImageNet 80% label noise
InstanceGM-SS
RESISC45
RGB Arabic Alphabet Sign Language (AASL) dataset
SARS-COV-2
Fuzzy rank-based fusion of CNN models using Gompertz function
SIPaKMeD
DL+PCA+GWO
smallNORB
Heinsen Routing
So2Sat LCZ42
ResNet50
Split CIFAR-10
split CIFAR-100
OFSCIL
Split Fashion M-NIST
Split M-NIST
Model with negotiation paradigm
Sports10
Max Margin Contrastive
Stanford Cars
Stanford Online Products
STL-10
µ2Net+ (ViT-L/16)
SUN397
TransBoost-ResNet50
Surrey ASL
E2E-3M
SVHN
Wide-ResNet-28-10
Tiered ImageNet 5-way (5-shot)
EGNN+Transduction
Tiny-ImageNet
UPANets
Tiny ImageNet Classification
Astroformer
touchtech/fashion-images-gender-age
Training and validation dataset of capsule vision 2024 challenge.
BiomedCLIP+PubmedBERT
Visual Wake Words
VizWiz-Classification
VOLO-D5
VTAB-1k
ALIGN (50 hypers/task)
WebVision-1000
CurriculumNet (InceptionResNet-v2)
WebVision
PropMix (Ours)
WaveMixLite