Linear-Probe Classification
9 papers with code • 1 benchmarks • 1 datasets
Libraries
Use these libraries to find Linear-Probe Classification models and implementationsMost implemented papers
BERT: Pre-training of Deep Bidirectional Transformers for Language Understanding
We introduce a new language representation model called BERT, which stands for Bidirectional Encoder Representations from Transformers.
Sentence-BERT: Sentence Embeddings using Siamese BERT-Networks
However, it requires that both sentences are fed into the network, which causes a massive computational overhead: Finding the most similar pair in a collection of 10, 000 sentences requires about 50 million inference computations (~65 hours) with BERT.
SimCSE: Simple Contrastive Learning of Sentence Embeddings
This paper presents SimCSE, a simple contrastive learning framework that greatly advances state-of-the-art sentence embeddings.
DeCLUTR: Deep Contrastive Learning for Unsupervised Textual Representations
Inspired by recent advances in deep metric learning (DML), we carefully design a self-supervised objective for learning universal sentence embeddings that does not require labelled training data.
Text and Code Embeddings by Contrastive Pre-Training
Similarly to text embeddings, we train code embedding models on (text, code) pairs, obtaining a 20. 8% relative improvement over prior best work on code search.
Neural Eigenfunctions Are Structured Representation Learners
Unlike prior spectral methods such as Laplacian Eigenmap that operate in a nonparametric manner, Neural Eigenmap leverages NeuralEF to parametrically model eigenfunctions using a neural network.
Scaling Vision Transformers to 22 Billion Parameters
The scaling of Transformers has driven breakthrough capabilities for language models.
Extending global-local view alignment for self-supervised learning with remote sensing imagery
While prior studies have explored multiple self-supervised learning techniques in remote sensing domain, pretext tasks based on local-global view alignment remain underexplored, despite achieving state-of-the-art results on natural imagery.
SODA: Bottleneck Diffusion Models for Representation Learning
We introduce SODA, a self-supervised diffusion model, designed for representation learning.