paper-with-me

Methods

Rendezvous 6 Static Word Embeddings 5 Vision Transformers 5 Data Parallel Methods 4 Data Parallel Methods 4 Data Parallel Methods 4 Fine-Tuning 4 Lane Detection Models 4 Output Functions 4 Replicated Data Parallel 4 Topic Embeddings 4 3D Face Mesh Models 3 3D Object Detection Models 3 Asynchronous Data Parallel 3 Asynchronous Data Parallel 3 Asynchronous Pipeline Parallel 3 Asynchronous Pipeline Parallel 3 Asynchronous Pipeline Parallel 3 Attention Mechanisms 3 Attention Modules 3 Autoencoding Transformers 3 Autoencoding Transformers 3 Autoencoding Transformers 3 Autoregressive Transformers 3

BASE

Balanced Selection
2000년 · 논문 5,784편
Active Learning

1x1 Convolution

2000년 · 논문 5,641편
Convolutions

ALIGN

2000년 · 논문 5,527편
Vision and Language Pre-Trained Models

LSTM

Long Short-Term Memory
1997년 · 논문 5,448편
Recurrent Neural Networks

Global Average Pooling

2000년 · 논문 4,076편
Pooling Operations

Cosine Annealing

2000년 · 논문 3,965편
Learning Rate Schedules

Pruning

2000년 · 논문 3,874편
Model Compression

Concatenated Skip Connection

2000년 · 논문 3,337편
Skip Connections

CLIP

Contrastive Language-Image Pre-training
2000년 · 논문 3,094편
Vision and Language Pre-Trained ModelsImage Representations

Knowledge Distillation

2000년 · 논문 3,071편
Knowledge Distillation

GPT-4

2000년 · 논문 2,871편
Language Models

SGD

Stochastic Gradient Descent
1951년 · 논문 2,021편
Stochastic Optimization

Discriminative Fine-Tuning

2000년 · 논문 1,990편
Fine-Tuning
← 이전 다음 →