Transparency by Design: Closing the Gap Between Performance and Interpretability in Visual Reasoning
Explore this paper's citation graph
- Type
- preprint
- Published
- 2018-03-14
- Cited by
- 225
- References
- 43
- Access
- Open access
- OpenAlex
- https://openalex.org/W2793546384
- Semantic Scholar
- https://api.semanticscholar.org/CorpusID:3863856
Keywords
Interpretability, Computer science, Visual reasoning, Transparency (behavior), Artificial intelligence
References
- Show, Attend and Tell: Neural Image Caption Generation with Visual Attention
- Delving Deep into Rectifiers: Surpassing Human-Level Performance on ImageNet Classification
- SALICON: Saliency in Context
- Matplotlib: A 2D Graphics Environment
- Cross-Domain Image Retrieval with a Dual Attribute-Aware Ranking Network
- ABC-CNN: An Attention Based Convolutional Neural Network for Visual Question Answering
- Where to Look: Focus Regions for Visual Question Answering
- Deep Residual Learning for Image Recognition
- Deep Compositional Question Answering with Neural Module Networks
- The mythos of model interpretability
- Diversified Visual Attention Networks for Fine-Grained Object Classification
- Hierarchical Question-Image Co-Attention for Visual Question Answering
- CLEVR: A Diagnostic Dataset for Compositional Language and Elementary Visual Reasoning
- Residual Attention Network for Image Classification
- Inferring and Executing Programs for Visual Reasoning
- Grad-CAM: Visual Explanations from Deep Networks via Gradient-Based Localization
- A simple neural network module for relational reasoning
- Bottom-Up and Top-Down Attention for Image Captioning and VQA
- Person re-identification using visual attention
- Sensor Transformation Attention Networks
Cited by
- Automatic Documentation of ICD Codes with Far-Field Speech Recognition
- Interpretable Visual Question Answering by Reasoning on Dependency Trees
- A Corpus for Reasoning about Natural Language Grounded in Photographs
- VQA With No Questions-Answers Training
- On transfer learning using a MAC model variant
- Generating Diverse Programs with Instruction Conditioned Reinforced Adversarial Learning
- Explainable and Explicit Visual Reasoning Over Scene Graphs
- Interaction Design for Explainable AI: Workshop Proceedings
- An Active Information Seeking Model for Goal-oriented Vision-and-Language Tasks
- CLEVR-Ref+: Diagnosing Visual Reasoning With Referring Expressions
- Neural Logic Machines
- Probabilistic Neural-symbolic Models for Interpretable Visual Question Answering
- Viewpoint Invariant Change Captioning
- The Neuro-Symbolic Concept Learner: Interpreting Scenes, Words, and Sentences From Natural Supervision
- Reproducing Machine Learning Research on Binder
- MUREL: Multimodal Relational Reasoning for Visual Question Answering
- RAVEN: A Dataset for Relational and Analogical Visual REasoNing
- Analyzing machine learning models to accelerate generation of fundamental materials insights
- Question Guided Modular Routing Networks for Visual Question Answering
- Robust Change Captioning
Related papers
- Two-stage Rule-induction visual reasoning on RPMs with an application to video prediction
- A research for visual reasoning
- Shape Understanding System: The Visual Reasoning Process
- From Pixels to Explanations: Uncovering the Reasoning Process in Visual Question Answering
- Disentangling Reasoning Capabilities from Language Models with Compositional Reasoning Transformers
- Tableau reasoning method based on logical reinforcement learning
- Disentangling Reasoning Capabilities from Language Models with Compositional Reasoning Transformers