naver / tldr
TLDR is an unsupervised dimensionality reduction method that combines neighborhood embedding learning with the simplicity and effectiveness of recent self-supervised learning losses
☆124Updated 2 years ago
Related projects ⓘ
Alternatives and complementary repositories for tldr
- Code for paper "Can contrastive learning avoid shortcut solutions?" NeurIPS 2021.☆47Updated 2 years ago
- ☆96Updated 2 years ago
- A Domain-Agnostic Benchmark for Self-Supervised Learning☆107Updated last year
- ☆58Updated 2 years ago
- ☆41Updated last year
- Code for the CVPR 2021 paper: Understanding Failures of Deep Networks via Robust Feature Extraction☆35Updated 2 years ago
- Differentiable Top-k Classification Learning☆76Updated last year
- Framework code with wandb, checkpointing, logging, configs, experimental protocols. Useful for fine-tuning models or training from scratc…☆146Updated last year
- Natural Language Descriptions of Deep Visual Features, ICLR 2022☆62Updated last year
- ☆29Updated 2 years ago
- Data for "Datamodels: Predicting Predictions with Training Data"☆90Updated last year
- This repository contains the code for our paper "Probabilistic Contrastive Learning Recovers the Correct Aleatoric Uncertainty of Ambiguo…☆37Updated last year
- ☆51Updated 5 months ago
- MetaShift: A Dataset of Datasets for Evaluating Contextual Distribution Shifts and Training Conflicts (ICLR 2022)☆108Updated 2 years ago
- Official implementation of the paper "Provable Stochastic Optimization for Global Contrastive Learning: Small Batch Does Not Harm Perform…☆19Updated last year
- codebase for the SIMAT dataset and evaluation☆38Updated 2 years ago
- Visual Representation Learning Benchmark for Self-Supervised Models☆35Updated 7 months ago
- Implementation of Discrete Key / Value Bottleneck, in Pytorch☆87Updated last year
- Patching open-vocabulary models by interpolating weights☆90Updated last year
- understanding model mistakes with human annotations☆105Updated last year
- Github code for the paper Maximum Class Separation as Inductive Bias in One Matrix. Arxiv link: https://arxiv.org/abs/2206.08704☆27Updated last year
- Large-scale Self-supervised Pre-training Across Tasks, Languages, and Modalities☆78Updated 2 years ago
- Uncertainty-aware representation learning (URL) benchmark☆98Updated 8 months ago
- The official repository for "Intermediate Layers Matter in Momentum Contrastive Self Supervised Learning" paper.☆40Updated 2 years ago
- Personal implementation of ASIF by Antonio Norelli☆24Updated 5 months ago
- (ICML 2021) Implementation for S2SD - Simultaneous Similarity-based Self-Distillation for Deep Metric Learning. Paper Link: https://arxiv…☆41Updated 4 years ago
- Code for "SAM as an Optimal Relaxation of Bayes", ICLR 2023.☆23Updated last year
- Implementation of Gated State Spaces, from the paper "Long Range Language Modeling via Gated State Spaces", in Pytorch☆95Updated last year
- Making Heads or Tails Towards Semantically Consistent Visual Counterfactuals☆30Updated 2 years ago
- Code for the paper PermuteFormer☆42Updated 3 years ago