Ecosyste.ms: Awesome
An open API service indexing awesome lists of open source software.
awesome-vision-language-bias
Recent Advances about Bias in Vision and Language
https://github.com/jingjing12110/awesome-vision-language-bias
- Estimating semantic structure for the VQA answer space
- Counterfactual VQA: A Cause-Effect Look at Language Bias
- Unshuffling Data for Improved Generalization
- Roses are Red, Violets are Blue... But Should VQA expect Them To? - OOD?utm_source=catalyzex.com)]
- Counterfactual Samples Synthesizing for Robust Visual Question Answering - VQA?utm_source=catalyzex.com)]
- Towards Causal VQA: Revealing and Reducing Spurious Correlations by Invariant and Covariant Semantic Editing
- Reducing Language Biases in Visual Question Answering with Visually-Grounded Question Encoder
- Learning to Model and Ignore Dataset Bias with Mixed Capacity Ensembles
- MUTANT: A Training Paradigm for Out-of-Distribution Generalization in Visual Question Answering
- Learning to Contrast the Counterfactual Samples for Robust Visual Question Answering
- Linguistically Driven Graph Capsule Network for Visual Question Reasoning
- Overcoming Language Priors with Self-supervised Learning for Visual Question Answering - VQA)]
- A negative case analysis of visual grounding methods for VQA
- Removing Bias in Multi-modal Classifiers: Regularization by Maximizing Functional Entropies - bias-in-multi-modal-classifiers)]
- RUBi: Reducing unimodal biases for visual question answering
- Quantifying and Alleviating the Language Prior Problem in Visual Question Answering - prior?utm_source=catalyzex.com)]
- Don’t Take the Easy Way Out: Ensemble Based Methods for Avoiding Known Dataset Biases
- Answer Them All! Toward Universal Visual Question Answering Models
- Explicit Bias Discovery in Visual Question Answering Models
- Question-Conditioned Counterfactual Image Generation for VQA
- Overcoming Language Priors in Visual Question Answering with Adversarial Regularization
- iVQA: Inverse Visual Question Answering
- Learning Answer Embeddings for Visual Question Answering - hu/answer_embedding)]
- Cross-Dataset Adaptation for Visual Question Answering
- Don't Just Assume; Look and Answer: Overcoming Priors for Visual Question Answering
- Making the V in VQA Matter: Elevating the Role of Image Understanding in Visual Question Answering - ml/SNLI-VE?utm_source=catalyzex.com)], [[project](https://visualqa.org/)]
- Yin and yang: Balancing and answering binary visual questions
- Deconfounded image captioning: A causal retrospect
- Mitigating Gender Bias in Captioning Systems
- Off-Policy Self-Critical Training for Transformer in Visual Paragraph Generation
- Understanding Image Captioning Models beyond Visualizing Attention
- Towards Fairness in Visual Recognition: Effective Strategies for Bias Mitigation
- Improving Image Captioning with Better Use of Captions - Captioning?utm_source=catalyzex.com)]
- Learning to Collocate Neural Modules for Image Captioning
- Women Also Snowboard: Overcoming Bias in Captioning Models - independence-public?utm_source=catalyzex.com)]
- Visual Referring Expression Recognition: What Do Systems Actually Learn? - sieves-refexp?utm_source=catalyzex.com)]
- CLEVR-Ref+: Diagnosing Visual Reasoning With Referring Expressions - grounding?utm_source=catalyzex.com)]
- CogTree: Cognition Tree Loss for Unbiased Scene Graph Generation
- Tackling the Unannotated: Scene Graph Generation with Bias-Reduced Models
- Unbiased Scene Graph Generation via Rich and Fair Semantic Extraction
- PCPL: Predicate-Correlation Perception Learning for Unbiased Scene Graph Generation
- Unbiased Scene Graph Generation from Biased Training - Graph-Benchmark.pytorch)]
- GPS-Net: Graph Property Sensing Network for Scene Graph Generation - Net)]
- Counterfactual Vision and Language Learning
- Diagnosing the Environment Bias in Vision-and-Language Navigation
- Adversarial Filters of Dataset Biases
- Contrast and Classify: Alternate Training for Robust VQA - vqa)], [[project](https://yashkant.github.io/projects/concat-vqa.html)]
- DeVLBert: Learning Deconfounded Visio-Linguistic Representations
- CVLP: Contrastive Visual Linguistic Pretraining - )]
- Oscar: Object-Semantics Aligned Pre-training for Vision-Language Tasks
- Large-Scale Adversarial Training for Vision-and-Language Representation Learning
- 12-in-1: Multi-Task Vision and Language Representation Learning - multi-task)]
- UNITER: UNiversal Image-TExt Representation Learning
- VL-BERT: Pre-training of Generic Visual-Linguistic Representations - BERT)]
- Unified Vision-Language Pre-Training for Image Captioning and VQA
- ViLBERT: Pretraining Task-Agnostic Visiolinguistic Representations for Vision-and-Language Tasks - multi-task)]
- VisualBERT: A Simple and Performant Baseline for Vision and Language
- LXMERT: Learning Cross-Modality Encoder Representations from Transformers