princetonvisualai / OverlookedFactors
Overlooked Factors in Concept-based Explanations: Dataset Choice, Concept Learnability, and Human Capability (CVPR 2023)
☆9Updated last year
Related projects: ⓘ
- DISSECT: Disentangled Simultaneous Explanations via Concept Traversals☆12Updated 7 months ago
- [ICLR'22] Self-supervised learning optimally robust representations for domain shift.☆23Updated 2 years ago
- DiWA: Diverse Weight Averaging for Out-of-Distribution Generalization☆27Updated last year
- Source code for the Nature Machine Intelligence paper: When and how convolutional neural networks generalize to out-of-distribution categ…☆21Updated 2 years ago
- Code for the ICCV 2023 paper "Benchmarking Low-Shot Robustness to Natural Distribution Shifts"☆11Updated 7 months ago
- ☆34Updated last year
- Code for the paper "A Whac-A-Mole Dilemma Shortcuts Come in Multiples Where Mitigating One Amplifies Others"☆41Updated 2 months ago
- Implementation of the paper "A Framework for Learning Ante-hoc Explainable Models via Concepts" (CVPR 2022).☆8Updated 2 months ago
- ☆40Updated last year
- Code release for paper Extremely Simple Activation Shaping for Out-of-Distribution Detection☆47Updated 3 weeks ago
- ☆15Updated 3 months ago
- [CVPR 2022] HINT: Hierarchical Neuron Concept Explainer☆20Updated 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
- This repository contains the code for our ECCV 2022 paper on our "Non-isotropic Probabilistic Take on Proxy-based Deep Metric Learning".☆12Updated last year
- ☆34Updated 4 months ago
- ☆13Updated 3 years ago
- Implementation of Concept-level Debugging of Part-Prototype Networks☆11Updated last year
- Improving Transformation Invariance in Contrastive Representation Learning☆13Updated 3 years ago
- ☆13Updated last year
- HIVE: Evaluating the Human Interpretability of Visual Explanations (ECCV 2022)☆18Updated last year
- This repository contains the implementation of Concept Activation Regions, a new framework to explain deep neural networks with human con…☆9Updated last year
- ☆12Updated 2 years ago
- Robust Contrastive Learning Using Negative Samples with Diminished Semantics (NeurIPS 2021)☆39Updated 2 years ago
- Code for paper "Can contrastive learning avoid shortcut solutions?" NeurIPS 2021.☆47Updated 2 years ago
- Code for the CVPR 2021 paper: Understanding Failures of Deep Networks via Robust Feature Extraction☆35Updated 2 years ago
- Visual Representation Learning Benchmark for Self-Supervised Models☆35Updated 5 months ago
- ☆21Updated last year
- 'Robust Semantic Interpretability: Revisiting Concept Activation Vectors' Official Implementation☆11Updated 4 years ago
- ProtoPFormer: Concentrating on Prototypical Parts in Vision Transformers for Interpretable Image Recognition☆32Updated last year
- This is a code repository for paper OODformer: Out-Of-Distribution Detection Transformer☆38Updated 2 years ago