AICurious Logo

AI Glossary

Terms and concepts in the field of AI and Machine Learning.
Powered by Papers with Code.

GeGLU

Activation-Functions

FSAF

Feature-Extractors

Pix2Pix

Generative-Models
Generative-Adversarial-Networks
Conditional-Image-to-Image-Translation-Models

PipeDream-2BW

Distributed-Methods
Model-Parallel-Methods
Asynchronous-Pipeline-Parallel

TaxoExpan

Graph-Models
Taxonomy-Expansion-Models

YOLOX

One-Stage-Object-Detection-Models

PP-OCR

Convolutions
OCR-Models

SEED RL

Distributed-Methods
Distributed-Reinforcement-Learning

MPNet

Language-Model-Pre-Training

StyleGAN

Generative-Models
Generative-Adversarial-Networks

LayoutReader

Sequence-To-Sequence-Models
Reading-Order-Detection-Models

RevNet

Convolutional-Neural-Networks

DetNAS

Neural-Architecture-Search

PrivacyNet

Face-Privacy
Generative-Adversarial-Networks

SRU++

Recurrent-Neural-Networks

TSDAE

Sentence-Embeddings

1-bit Adam

Stochastic-Optimization
Large-Batch-Optimization

OPT

Language-Models

mBARTHez

Language-Models
Sequence-To-Sequence-Models

ReGLU

Activation-Functions

Voxel R-CNN

3D-Object-Detection-Models
Point-Cloud-Models

PipeTransformer

Distributed-Methods
Hybrid-Parallel-Methods
2D-Parallel-Distributed-Methods

XLM

Transformers
Autoencoding-Transformers

DBlock

Audio-Model-Blocks
Skip-Connection-Blocks

ELMo

Word-Embeddings
Contextualized-Word-Embeddings
Language-Models

Hamburger

Image-Feature-Extractors
Global-Context-Modules

CS-GAN

Generative-Models
Generative-Adversarial-Networks

SERLU

Activation-Functions

FixMatch

Semi-Supervised-Learning-Methods

LipGAN

Generative-Adversarial-Networks
Conditional-Image-to-Image-Translation-Models
Face-to-Face-Translation

LARS

Large-Batch-Optimization

fastText

Word-Embeddings
Static-Word-Embeddings

mT5

Language-Models
Autoencoding-Transformers

A2C

Policy-Gradient-Methods

mT0

Language-Models

Blender

Attention-Modules
Instance-Segmentation-Modules

DynaBERT

Language-Models
Autoencoding-Transformers

XGPT

Vision-and-Language-Pre-Trained-Models

Serf

Activation-Functions

SqueezeNet

Convolutional-Neural-Networks
Light-weight-neural-networks

I-BERT

Transformers
Autoencoding-Transformers

Nouveau VAE

Likelihood-Based-Generative-Models
Generative-Models

Hopfield Layer

Pooling-Operations
Recurrent-Neural-Networks
Attention-Modules

Parrot

Cache-Replacement-Models
Imitation-Learning-Methods

ClassSR

Image-Super-Resolution-Models

ConvBERT

Transformers
Autoencoding-Transformers

DVD-GAN

Generative-Models
Generative-Adversarial-Networks
Generative-Video-Models

RoBERTa

Transformers
Autoencoding-Transformers

VoVNet

Convolutional-Neural-Networks

MT-PET

Exaggeration-Detection-Models

OFA

Vision-and-Language-Pre-Trained-Models

PipeMare

Distributed-Methods
Model-Parallel-Methods
Asynchronous-Pipeline-Parallel

DU-GAN

Generative-Adversarial-Networks
Image-Denoising-Models

SPP-Net

Convolutional-Neural-Networks

context2vec

Word-Embeddings
Contextualized-Word-Embeddings

UNet++

Semantic-Segmentation-Models

SGDW

Stochastic-Optimization

DeepLab

Semantic-Segmentation-Models

MNN

Inference-Engines

LightGCN

Recommendation-Systems
Graph-Models

EvoNorms

Normalization
Activation-Functions

SKEP

Semi-Supervised-Learning-Methods

ALDEN

Text-Classification-Models
Active-Learning

ZeRO-Offload

Distributed-Methods
Data-Parallel-Methods
Sharded-Data-Parallel-Methods

LAPGAN

Generative-Models
Generative-Adversarial-Networks

VOS

Video-Object-Segmentation-Models

PULSE

Image-Super-Resolution-Models

OSCAR

Vision-and-Language-Pre-Trained-Models

GRLIA

Incident-Aggregation-Models

Tacotron

Text-to-Speech-Models
Sequence-To-Sequence-Models

VATT

Vision-Transformers
Multi-Modal-Methods

BLANC

Document-Summary-Evaluation

YOLOv1

Object-Detection-Models
One-Stage-Object-Detection-Models

GPT

Transformers
Autoregressive-Transformers

MacBERT

Transformers
Autoencoding-Transformers

NPID++

Self-Supervised-Learning

ConvMLP

Convolutional-Neural-Networks
Image-Models

NPID

Self-Supervised-Learning

CPC v2

Self-Supervised-Learning
Semi-Supervised-Learning-Methods

ScanSSD

Object-Detection-Models
Math-Formula-Detection-Models

SENet

Convolutional-Neural-Networks

TrIVD-GAN

Generative-Models
Generative-Adversarial-Networks
Generative-Video-Models

PSANet

Semantic-Segmentation-Models

BiFPN

Feature-Extractors
Feature-Pyramid-Blocks

BAGUA

Distributed-Methods
Data-Parallel-Methods
Replicated-Data-Parallel

MUSIQ

Vision-Transformers
Image-Quality-Models

WaveRNN

Generative-Audio-Models
Recurrent-Neural-Networks

U-Net

Semantic-Segmentation-Models

MobileNetV1

Convolutional-Neural-Networks
Light-weight-neural-networks

Smish

Activation-Functions

SimCLR

Self-Supervised-Learning

Electric

Language-Models
Transformers
Autoencoding-Transformers

OASIS

Conditional-Image-to-Image-Translation-Models

MEUZZ

Hybrid-Optimization
Hybrid-Fuzzing

CycleGAN

Generative-Models
Generative-Adversarial-Networks
Unpaired-Image-to-Image-Translation

MobileNetV2

Image-Models
Convolutional-Neural-Networks
Light-weight-neural-networks

ACER

Policy-Gradient-Methods

modReLU

Activation-Functions
Adaptive-Activation-Functions

ENIGMA

Dialog-System-Evaluation

ShuffleNet

Convolutional-Neural-Networks
Light-weight-neural-networks

PRNet+

Position-Recovery-Models

MaxUp

Adversarial-Image-Data-Augmentation

YOLOv3

Object-Detection-Models
One-Stage-Object-Detection-Models

RegNetY

Convolutional-Neural-Networks

RevSilo

Reversible-Image-Conversion-Models

LSGAN

Generative-Models
Generative-Adversarial-Networks

ALBEF

Vision-and-Language-Pre-Trained-Models

CBHG

Speech-Synthesis-Blocks
Sequential-Blocks
Skip-Connection-Blocks

GAN-TTS

Text-to-Speech-Models
Sequence-To-Sequence-Models

BiDet

Binary-Neural-Networks

CodeBERT

Transformers
Code-Generation-Transformers

ALIGN

Vision-and-Language-Pre-Trained-Models

BERT

Language-Models
Transformers
Autoencoding-Transformers

RFB Net

Object-Detection-Models
One-Stage-Object-Detection-Models

Bi3D

Stereo-Depth-Estimation-Models

FMix

Image-Data-Augmentation

ByteScheduler

Distributed-Methods
Data-Parallel-Methods
Replicated-Data-Parallel

Parallax

Distributed-Methods
Hybrid-Parallel-Methods
Parameter-Server-Methods

VocGAN

Generative-Audio-Models

YOLOP

One-Stage-Object-Detection-Models
Object-Detection-Models
Semantic-Segmentation-Models
Lane-Detection-Models

MoCo v2

Self-Supervised-Learning
Semi-Supervised-Learning-Methods

Swish

Activation-Functions
Adaptive-Activation-Functions

XLNet

Transformers
Autoregressive-Transformers

ALDA

Unpaired-Image-to-Image-Translation

BTmPG

Paraphrase-Generation-Models

STAC

Semi-Supervised-Learning-Methods

YOLOv4

Object-Detection-Models
One-Stage-Object-Detection-Models

MADDPG

Policy-Gradient-Methods

R-CNN

Object-Detection-Models

BigGAN-deep

Generative-Models
Generative-Adversarial-Networks

K-Net

Semantic-Segmentation-Models
Instance-Segmentation-Models

PixelCNN

Generative-Models
Likelihood-Based-Generative-Models

SNIP

Multi-Scale-Training

AltCLIP

Vision-and-Language-Pre-Trained-Models

LV-ViT

Vision-Transformers
Image-Models

SCARLET

Convolutional-Neural-Networks

HRNet

Convolutional-Neural-Networks

CTAB-GAN

Generative-Adversarial-Networks
Tabular-Data-Generation

RPDet

Object-Detection-Models

VQ-VAE

Generative-Models
Likelihood-Based-Generative-Models

UCNet

RGB-D-Saliency-Detection-Models

MelGAN

Generative-Audio-Models

uNetXST

Convolutional-Neural-Networks

KungFu

Distributed-Methods
Auto-Parallel-Methods

AlexNet

Convolutional-Neural-Networks

DiffAugment

Adversarial-Training
Adversarial-Image-Data-Augmentation

ELECTRA

Transformers
Autoencoding-Transformers

XCiT

Vision-Transformers

DELU

Activation-Functions
Adaptive-Activation-Functions

PAUSE

Sentence-Embeddings

FLAVR

Video-Interpolation-Models

BigBiGAN

Generative-Models
Generative-Adversarial-Networks
Self-Supervised-Learning

PANet

Instance-Segmentation-Models
Object-Detection-Models

ClariNet

Text-to-Speech-Models
Sequence-To-Sequence-Models

ParamCrop

Generative-Video-Models
Self-Supervised-Learning

RIFE

Video-Frame-Interpolation

HetPipe

Distributed-Methods
Hybrid-Parallel-Methods
Parameter-Server-Methods

MODNet

Portrait-Matting-Models

Cutout

Image-Data-Augmentation

Accordion

Distributed-Methods
Data-Parallel-Methods

PixLoc

6D-Pose-Estimation-Models

TorchBeast

Distributed-Methods
Distributed-Reinforcement-Learning

SSD

Object-Detection-Models
One-Stage-Object-Detection-Models

Mirror-BERT

Self-Supervised-Learning
Sentence-Embeddings
Word-Embeddings
Contextualized-Word-Embeddings
Static-Word-Embeddings

ResNeXt

Convolutional-Neural-Networks

GhostNet

Convolutional-Neural-Networks
Light-weight-neural-networks

MoViNet

Video-Recognition-Models
Light-weight-neural-networks

CrossViT

Vision-Transformers
Image-Models

Macaw

Question-Answering-Models

WideResNet

Image-Models
Convolutional-Neural-Networks

ASLFeat

Convolutional-Neural-Networks

Mixup

Image-Data-Augmentation

MoGA-A

Convolutional-Neural-Networks
Light-weight-neural-networks

GFP-GAN

Face-Restoration-Models
Generative-Adversarial-Networks

Adafactor

Stochastic-Optimization
Large-Batch-Optimization

InfoGAN

Generative-Models
Generative-Adversarial-Networks

MixText

Semi-Supervised-Learning-Methods
Text-Classification-Models
Text-Augmentation

RetinaNet-RS

One-Stage-Object-Detection-Models
Object-Detection-Models

A3C

Policy-Gradient-Methods

RetinaMask

Object-Detection-Models
One-Stage-Object-Detection-Models

ECA-Net

Convolutional-Neural-Networks

EdgeFlow

Semantic-Segmentation-Models
Interactive-Semantic-Segmentation-Models

MLFPN

Feature-Extractors
Feature-Pyramid-Blocks

BigBird

Transformers
Attention-Patterns

SegNet

Semantic-Segmentation-Models

PnP

Image-Model-Blocks

VisTR

Instance-Segmentation-Models
Video-Instance-Segmentation-Models

CodeT5

Code-Generation-Transformers
Autoencoding-Transformers
Transformers

LeNet

Convolutional-Neural-Networks

SM3

Stochastic-Optimization
Large-Batch-Optimization

FCOS

Object-Detection-Models
One-Stage-Object-Detection-Models

G3D

Action-Recognition-Blocks

FixRes

Image-Scaling-Strategies

Bidirectional GAN

Generative-Models
Generative-Adversarial-Networks
Self-Supervised-Learning

Fisher-BRC

Policy-Gradient-Methods
Offline-Reinforcement-Learning-Methods

ALBERT

Transformers
Autoencoding-Transformers

TResNet

Convolutional-Neural-Networks

CAMoE

Video-Text-Retrieval-Models

Bort

Language-Models
Autoencoding-Transformers

Mish

Activation-Functions

PowerSGD

Stochastic-Optimization
Optimization
Distributed-Methods
Data-Parallel-Methods

RetinaNet

Object-Detection-Models
One-Stage-Object-Detection-Models

PIRL

Self-Supervised-Learning

AdaMax

Stochastic-Optimization

TSRUs

Recurrent-Neural-Networks

CutMix

Image-Data-Augmentation

MCKERNEL

Convolutional-Neural-Networks
Feature-Extractors
Fourier-related-Transforms

ResNeSt

Image-Models
Convolutional-Neural-Networks

FLAVA

Vision-and-Language-Pre-Trained-Models

DeepViT

Vision-Transformers
Image-Models

ESPNet

Semantic-Segmentation-Models
Light-weight-neural-networks

Adam

Stochastic-Optimization
Optimization
Large-Batch-Optimization

DeBERTa

Transformers
Autoencoding-Transformers

RepVGG

Convolutional-Neural-Networks

SOHO

Vision-and-Language-Pre-Trained-Models

LiteSeg

Semantic-Segmentation-Models

MoBY

Self-Supervised-Learning

AdaMod

Stochastic-Optimization

GLOW

Generative-Models
Likelihood-Based-Generative-Models

NADAM

Stochastic-Optimization
Large-Batch-Optimization

Hydra

Knowledge-Distillation

XLSR

Speech-Recognition

DeeBERT

Transformers
Autoencoding-Transformers

GBlock

Audio-Model-Blocks
Skip-Connection-Blocks

RegNetX

Convolutional-Neural-Networks

CTAL

Generative-Audio-Models
Multi-Modal-Methods

EsViT

Vision-Transformers

BART

Transformers
Sequence-To-Sequence-Models

ZeRO-Infinity

Distributed-Methods
Data-Parallel-Methods
Sharded-Data-Parallel-Methods

ReLU6

Activation-Functions

Grab

Cashier-Free-Shopping

Herring

Distributed-Methods
Hybrid-Parallel-Methods
Parameter-Server-Methods