Search Results for author:
Found 9 papers, 4 papers with code
Evaluating Text-to-Image Synthesis: Survey and Taxonomy of Image Quality Metrics
Recent advances in text-to-image synthesis enabled through a combination of language and vision foundation models have led to a proliferation of the tools available and an increased attention to the field.
An In-depth Look at Gemini's Language Abilities
The recently released Google Gemini class of models are the first to comprehensively report results that rival the OpenAI GPT series across a wide variety of tasks.
Neural Activation Patterns (NAPs): Visual Explainability of Learned Concepts
Promising methods for discovering learned features are based on analyzing activation values, whereby current techniques focus on analyzing high activation values to reveal interesting features on a neuron level.
Symphony: Composing Interactive Interfaces for Machine Learning
Interfaces for machine learning (ML), information and visualizations about models or data, can help practitioners build robust and responsible ML systems.
Visual Identification of Problematic Bias in Large Label Spaces
With our approach, different models and datasets for large label spaces can be systematically and visually analyzed and compared to make informed fairness assessments tackling problematic bias.
Measuring Model Biases in the Absence of Ground Truth
By treating a classification model's predictions for a given image as a set of labels analogous to a bag of words, we rank the biases that a model has learned with respect to different identity labels.
exploRNN: Understanding Recurrent Neural Networks through Visual Exploration
In an empirical study, we assessed 37 subjects in a between-subjects design to investigate the learning outcomes and cognitive load of exploRNN compared to a classic text-based learning environment.
Net2Vis -- A Visual Grammar for Automatically Generating Publication-Tailored CNN Architecture Visualizations
To convey neural network architectures in publications, appropriate visualizations are of great importance.
Classifier-Guided Visual Correction of Noisy Labels for Image Classification Tasks
We thus propose a novel approach that uses the power of pretrained classifiers to visually guide users to noisy labels, and let them interactively check error candidates, to iteratively improve the training data set.
