cdancette / detect-shortcutsLinks
Repo for ICCV 2021 paper: Beyond Question-Based Biases: Assessing Multimodal Shortcut Learning in Visual Question Answering
☆27Updated last year
Alternatives and similar repositories for detect-shortcuts
Users that are interested in detect-shortcuts are comparing it to the libraries listed below
Sorting:
- A collections of papers about VQA-CP datasets and their results☆41Updated 3 years ago
- ☆13Updated 3 years ago
- Counterfactual Samples Synthesizing for Robust VQA☆79Updated 3 years ago
- ☆12Updated 5 years ago
- ☆20Updated 3 years ago
- PyTorch implementation of "Debiased Visual Question Answering from Feature and Sample Perspectives" (NeurIPS 2021)☆27Updated 3 years ago
- Implementation for CVPR 2020 Paper "Two Causal Principles for Improving Visual Dialog"☆31Updated 2 years ago
- [CVPR 2021] Counterfactual VQA: A Cause-Effect Look at Language Bias☆126Updated 3 years ago
- ☆27Updated 4 years ago
- CVPR 2022 (Oral) Pytorch Code for Unsupervised Vision-and-Language Pre-training via Retrieval-based Multi-Granular Alignment☆22Updated 3 years ago
- Official implementation of our EMNLP 2022 paper "CPL: Counterfactual Prompt Learning for Vision and Language Models"☆34Updated 3 years ago
- ☆79Updated 3 years ago
- NeurIPS 2019 Paper: RUBi : Reducing Unimodal Biases for Visual Question Answering☆65Updated 4 years ago
- ☆40Updated 3 years ago
- Code for Greedy Gradient Ensemble for Visual Question Answering （ICCV 2021, Oral）☆27Updated 3 years ago
- A pytorch implemetation of data augmentation method for visual question answering☆21Updated 2 years ago
- [NeurIPS 2021] Introspective Distillation for Robust Question Answering☆13Updated 3 years ago
- Code for WACV 2021 Paper "Meta Module Network for Compositional Visual Reasoning"☆43Updated 4 years ago
- Data Release for VALUE Benchmark☆30Updated 3 years ago
- This repo contains code for Invariant Grounding for Video Question Answering☆27Updated 2 years ago
- GQA-OOD is a new dataset and benchmark for the evaluation of VQA models in OOD (out of distribution) settings.☆31Updated 4 years ago
- An Empirical Study of GPT-3 for Few-Shot Knowledge-Based VQA, AAAI 2022 (Oral)☆86Updated 3 years ago
- ☆18Updated last year
- [ECCV2022] Rethinking Data Augmentation for Robust Visual Question Answering☆13Updated 3 years ago
- Human-like Controllable Image Captioning with Verb-specific Semantic Roles.☆36Updated 3 years ago
- ☆85Updated 6 years ago
- The SVO-Probes Dataset for Verb Understanding☆31Updated 3 years ago
- Unpaired Image Captioning☆36Updated 4 years ago
- Dataset and starting code for visual entailment dataset☆118Updated 3 years ago
- This repo contains codes and instructions for baselines in the VLUE benchmark.☆41Updated 3 years ago