paulgavrikov / vlm_shapebias
Official code for "Are Vision Language Models Texture or Shape Biased and Can We Steer Them?".
☆13Updated 10 months ago
Alternatives and similar repositories for vlm_shapebias:
Users that are interested in vlm_shapebias are comparing it to the libraries listed below
- ☆16Updated 7 months ago
- Code for Continuously Changing Corruptions (CCC) benchmark + evaluation☆32Updated 4 months ago
- [NeurIPS '24] Frustratingly easy Test-Time Adaptation of VLMs!!☆35Updated 2 months ago
- ☆107Updated last year
- Official repository for the ICCV 2023 paper: "Waffling around for Performance: Visual Classification with Random Words and Broad Concepts…☆56Updated last year
- Code for the paper "A Whac-A-Mole Dilemma Shortcuts Come in Multiples Where Mitigating One Amplifies Others"☆47Updated 6 months ago
- This repo implements the CVPR23 paper Trainable Projected Gradient Method for Robust Fine-tuning☆24Updated last year
- Test-Time Adaptation via Conjugate Pseudo-Labels☆39Updated last year
- Code and data for the paper "In or Out? Fixing ImageNet Out-of-Distribution Detection Evaluation"☆24Updated last year
- Code for the NeurIPS 2023 paper "Spatial-frequency channels, shape bias, and adversarial robustness"☆12Updated last year
- FunnyBirds: A Synthetic Vision Dataset for a Part-Based Analysis of Explainable AI Methods (ICCV 2023)☆20Updated last month
- Natural Language Descriptions of Deep Visual Features, ICLR 2022☆62Updated last year
- The example of correspondence between fine classes and superclass (coarse class) in ImageNet.☆12Updated last month
- LANCE: Stress-testing Visual Models by Generating Language-guided Counterfactual Images☆28Updated last year
- Augmenting with Language-guided Image Augmentation (ALIA)☆70Updated last year
- Create generated datasets and train robust classifiers☆33Updated last year
- Crowdsourcing metrics and test datasets beyond ImageNet (ICML 2022 workshop)☆37Updated 8 months ago
- This repository provides code for "On Interaction Between Augmentations and Corruptions in Natural Corruption Robustness".☆45Updated 2 years ago
- source code for NeurIPS'24 paper "Towards Calibrated Robust Fine-Tuning of Vision-Language Models"☆11Updated 3 months ago
- Learning Bottleneck Concepts in Image Classification (CVPR 2023)☆35Updated last year
- LaFTer: Label-Free Tuning of Zero-shot Classifier using Language and Unlabeled Image Collections (NeurIPS 2023)☆27Updated last year
- Robustness and adaptation of ImageNet scale models. Pre-Release, stay tuned for updates.☆132Updated last year
- Code release for paper Extremely Simple Activation Shaping for Out-of-Distribution Detection☆49Updated 4 months ago
- 🔥 🔥 [ECCV 2024 Oral ] Official code for "Weighted Ensemble Models Are Strong Continual Learners"☆21Updated last month
- GCPR 2023 - DeViL: Decoding Vision features into Language☆11Updated last year
- Visual Representation Learning Benchmark for Self-Supervised Models☆35Updated 9 months ago
- ☆42Updated last year
- Official code for the CVPR 2024 Paper "Can Biases in ImageNet Models Explain Generalization?".☆11Updated 6 months ago
- Official implementation for CVPR'23 paper "BlackVIP: Black-Box Visual Prompting for Robust Transfer Learning"☆106Updated last year
- Code and data for the paper "Emergent Visual-Semantic Hierarchies in Image-Text Representations" (ECCV 2024)☆25Updated 5 months ago