Distilling Model Failures as Directions in Latent Space
☆49Feb 8, 2023Updated 3 years ago
Alternatives and similar repositories for failure-directions
Users that are interested in failure-directions are comparing it to the libraries listed below. We may earn a commission when you buy through links labeled 'Ad' on this page.
Sorting:
- Spurious Features Everywhere - Large-Scale Detection of Harmful Spurious Features in ImageNet☆32Aug 22, 2023Updated 3 years ago
- ☆13Jun 23, 2022Updated 4 years ago
- ModelDiff: A Framework for Comparing Learning Algorithms☆59Aug 15, 2023Updated 3 years ago
- Dataset Interfaces: Diagnosing Model Failures Using Controllable Counterfactual Generation☆45Feb 27, 2023Updated 3 years ago
- Provable Worst Case Guarantees for the Detection of Out-of-Distribution Data☆13Sep 20, 2022Updated 4 years ago
- Deploy on Railway without the complexity - Free Credits Offer • AdConnect your repo and Railway handles the rest with instant previews. Quickly provision container image services, databases, and storage volumes.
- This repository contains the implementation of Concept Activation Regions, a new framework to explain deep neural networks with human con…☆17Oct 7, 2022Updated 4 years ago
- DiG-IN: Diffusion Guidance for Investigating Networks - Uncovering Classifier Differences, Neuron Visualisations, and Visual Counterfactu…☆11Oct 9, 2024Updated 2 years ago
- ☆15Jul 24, 2022Updated 4 years ago
- Data for "Datamodels: Predicting Predictions with Training Data"☆97May 25, 2023Updated 3 years ago
- ☆37Jun 10, 2021Updated 5 years ago
- ☆16Nov 30, 2022Updated 3 years ago
- Code relative to "Adversarial robustness against multiple and single $l_p$-threat models via quick fine-tuning of robust classifiers"☆20Nov 30, 2022Updated 3 years ago
- ☆12Oct 23, 2022Updated 4 years ago
- On the effectiveness of adversarial training against common corruptions [UAI 2022]☆30May 16, 2022Updated 4 years ago
- Deploy on Railway without the complexity - Free Credits Offer • AdConnect your repo and Railway handles the rest with instant previews. Quickly provision container image services, databases, and storage volumes.
- ☆35Sep 23, 2022Updated 4 years ago
- ☆46May 8, 2024Updated 2 years ago
- ☆13Feb 12, 2023Updated 3 years ago
- ☆96Oct 27, 2022Updated 4 years ago
- Code for the ICLR'24 paper: "Visual Data-Type Understanding does not emerge from Scaling Vision-Language Models"☆13Jan 17, 2024Updated 2 years ago
- Code for ICLR 2022 Paper, "Controlling Directions Orthogonal to a Classifier"☆35Jun 6, 2023Updated 3 years ago
- Code for the paper "Evading Black-box Classifiers Without Breaking Eggs" [SaTML 2024]☆21Apr 15, 2024Updated 2 years ago
- Relabeling of the POPE benchmark☆14May 16, 2025Updated last year
- [Re] Don't Judge an Object by Its Context: Learning to Overcome Contextual Bias (ML Reproducibility Challenge 2020)☆19Jun 1, 2021Updated 5 years ago
- Deploy to Railway using AI coding agents - Free Credits Offer • AdUse Claude Code, Codex, OpenCode, and more. Autonomous software development now has the infrastructure to match with Railway.
- Towards Understanding Sharpness-Aware Minimization [ICML 2022]☆38Jun 14, 2022Updated 4 years ago
- Code for the paper "A Light Recipe to Train Robust Vision Transformers" [SaTML 2023]☆54Feb 6, 2023Updated 3 years ago
- ☆12Feb 19, 2025Updated last year
- DASH: Detection and Assessment of Systematic Hallucinations of VLMs☆16Jul 2, 2025Updated last year
- Mitigating Spurious Correlations in Multi-modal Models during Fine-tuning (ICML 2023)☆19Dec 15, 2023Updated 2 years ago
- Augmenting with Language-guided Image Augmentation (ALIA)☆78Oct 30, 2023Updated 3 years ago
- ☆143Oct 30, 2023Updated 3 years ago
- MetaShift: A Dataset of Datasets for Evaluating Contextual Distribution Shifts and Training Conflicts (ICLR 2022)☆110Aug 29, 2022Updated 4 years ago
- ☆28Oct 18, 2022Updated 4 years ago
- Managed hosting for WordPress and PHP on Cloudways • AdManaged hosting for WordPress, Magento, Laravel, or PHP apps, on multiple cloud providers. Deploy in minutes on Cloudways by DigitalOcean.
- Balancing the Picture: Debiasing Vision-Language Datasets with Synthetic Contrast Sets☆12May 25, 2023Updated 3 years ago
- On the Loss Landscape of Adversarial Training: Identifying Challenges and How to Overcome Them [NeurIPS 2020]☆36Jul 3, 2021Updated 5 years ago
- ☆13Aug 6, 2026Updated 3 months ago
- Code for T-MARS data filtering☆35Aug 23, 2023Updated 3 years ago
- [NeurIPS 2021] Better Safe Than Sorry: Preventing Delusive Adversaries with Adversarial Training☆32Jan 9, 2022Updated 4 years ago
- Active Learning Helps Pretrained Models Learn the Intended Task (https://arxiv.org/abs/2204.08491) by Alex Tamkin, Dat Nguyen, Salil Desh…☆11Nov 22, 2022Updated 3 years ago
- Procedural Image Programs for Representation Learning - NeurIPS 2022☆43Feb 4, 2026Updated 9 months ago
Are these results useful?