halixness / understanding-CLIP
Repo from the "Learning with limited labeled data" seminar @ Uni of Tuebingen. A collection of notes, notebooks and slideshows to understand CLIP and Natural language supervision.
β15Updated last year
Related projects: β
- π° Computing the information content of trained neural networksβ16Updated 2 years ago
- Adversarial examples to the new ConvNeXt architectureβ20Updated 2 years ago
- Official code for the paper: "Metadata Archaeology"β18Updated last year
- We investigated corruption robustness across different architectures including Convolutional Neural Networks, Vision Transformers, and thβ¦β15Updated 2 years ago
- Implementation of Metaformer, but in an autoregressive mannerβ22Updated 2 years ago
- Repository for the PopulAtion Parameter Averaging (PAPA) paperβ26Updated 5 months ago
- Code for reproducing the results in "How Well do Sparse Imagenet Models Transfer?", presented at CVPR 2022β8Updated 2 years ago
- β21Updated this week
- β12Updated 3 weeks ago
- Includes additional materials for the following keras.io blog post.β12Updated 3 years ago
- Shows how to do parameter ensembling using differential evolution.β10Updated 2 years ago
- β11Updated 2 weeks ago
- Official repository for the paper "Images as Weight Matrices: Sequential Image Generation Through Synaptic Learning Rules" (ICLR 2023)β12Updated last year
- Library for the Test-based Calibration Error (TCE) metric to quantify the degree to classifier calibration.β13Updated last year
- A project to improve out-of-distribution detection (open set recognition) and uncertainty estimation by changing a few lines of code in yβ¦β45Updated last year
- DiWA: Diverse Weight Averaging for Out-of-Distribution Generalizationβ27Updated last year
- Implementation for ACProp ( Momentum centering and asynchronous update for adaptive gradient methdos, NeurIPS 2021)β15Updated 2 years ago
- β11Updated 2 years ago
- PyTorch Implementation of the paper "MM1: Methods, Analysis & Insights from Multimodal LLM Pre-training"β21Updated last week
- β13Updated last year
- Directed masked autoencodersβ13Updated last year
- β17Updated this week
- Repository for the paper Do SSL Models Have DΓ©jΓ Vu? A Case of Unintended Memorization in Self-supervised Learningβ37Updated last year
- [CVPR'23 Highlight] Heterogeneous Continual Learning.β15Updated 9 months ago
- Official code and data for NeurIPS 2023 paper "ImageNet-Hard: The Hardest Images Remaining from a Study of the Power of Zoom and Spatial β¦β36Updated 9 months ago
- Code for paper: "Privately generating tabular data using language models".β14Updated last year
- Anytime Learning At Macroscaleβ9Updated 2 years ago
- Code for the Paper Learning Hierarchy Aware Features for Reducing Mistake Severity, accepted in ECCV 2022β14Updated last year
- Developing adversarial examples and showing their semantic generalization for the OpenAI CLIP model (https://github.com/openai/CLIP)β26Updated 3 years ago
- β17Updated last year