The paper evaluates and compares dimensionality reduction quality metrics without tuning.
problem Evaluating the quality of nonlinear dimensionality reduction visualizations is challenging.
method Comparison of dimensionality reduction quality metrics on datasets with known ground truth manifolds.
result A few methods consistently perform well, with one proposed as a benchmark.
Paper establishes baselines for offline RL from visual observations.
problem Challenges in offline reinforcement learning from visual observations with continuous action spaces.
method Simple baselines and benchmarking tasks for offline RL from visual observations.
result Simple modifications to existing online RL algorithms outperform existing offline RL methods.
Visual system compares and evaluates machine learning models for clinical data predictions.
problem Challenges in comparing and evaluating different machine learning models for medical predictions.
method Developed a visual analytics system to compare and evaluate multiple models' prediction criteria and consistency.
result Demonstrated the effectiveness of the visual analytics system in assisting clinicians and researchers.
New method to evaluate visual explanations from neural networks.
problem Lack of consensus on measuring effectiveness of visual explanations.
method Proposed a new procedure for evaluating explanations using a range of sources.
result Demonstrated the benefit of combining different sources and the impact of bias parameters.
New method evaluates text-to-image synthesis for realism, variety, and semantic accuracy.
problem Lack of metrics revealing semantic accuracy in text-to-image synthesis.
method Uses Inception network representations and t-SNE visualization for semantic evaluation.
result Classification accuracy of generated images to real images' visual concepts correlates with semantic accuracy.
This paper gives a review and synthesis of methods of evaluating dimensionality reduction techniques. Particular attention is paid to rank-order neighborhood evaluation metrics. A framework is created for exploring dimensionality reduction quality through visualization. An associated toolkit is implemented in R. The to…
Proposes a spectral method to assess and combine multiple data visualizations.
problem Evaluating and combining the strengths of different data visualization algorithms.
method Spectral method for assessing and combining multiple visualizations.
result Proposes a visualization eigenscore to quantify relative performance and a consensus visualization.
Paper proposes a deep learning architecture for generating long stories from images.
problem Maintaining context in long event sequences for visual storytelling.
method Hierarchical deep learning architecture with encoder-decoder networks and natural language descriptions.
result Our method outperforms state-of-the-art techniques on automatic evaluation metrics.
Regshock visualizes financial risks to help regulators manage systemic shocks.
problem Managing systemic risks in financial networks.
method Risk-island visualization algorithm and regshock visual exploration approach.
result Demonstrated improved risk management and control capabilities.
New method evaluates visual explanations of deep models using adversarial perturbations.
problem Lack of objective evaluation of visual explanations of deep models.
method Proposes an adversarial perturbation approach to evaluate visual explanations of deep models.
result Demonstrates the effectiveness of the proposed approach through comparisons with existing methods.
A framework isolates VQA reasoning from perception for better model evaluation.
problem Improper separation of visual perception and reasoning in VQA models.
method Introducing a framework and a top-down calibration technique to decouple reasoning from perception.
result Improved evaluation of VQA models by separating reasoning from perception.
Study evaluates interpretability of time series foundation models' latent spaces.
problem Improving interpretability of latent spaces in time series models for visual analytics.
method Evaluated MOMENT family of transformer-based models on five datasets, fine-tuning for performance.
result Fine-tuning improved latent space clarity but limited interpretability remained.
Bayesian framework evaluates predictors of subjective visual tasks.
problem Evaluating uncertainty in machine learning predictors for tasks with subjective annotations.
method Bayesian framework to estimate epistemic uncertainty from human labels.
result Framework successfully applied to four image classification tasks.
Visualizes deep generative models for drug design.
problem Limited visualization tools for deep generative models in drug discovery.
method Proposes a visualization framework for deep graph generative models.
result Interactive visualization and molecular optimization tools.
As machine learning becomes more pervasive, there is an urgent need for interpretable explanations of predictive models. Prior work has developed effective methods for visualizing global model behavior, as well as generating local (instance-specific) explanations. However, relatively little work has addressed regional …
Deep Reinforcement Learning (DRL) is a trending field of research, showing great promise in many challenging problems such as playing Atari, solving Go and controlling robots. While DRL agents perform well in practice we are still missing the tools to analayze their performance and visualize the temporal abstractions t…
To convey neural network architectures in publications, appropriate visualizations are of great importance. While most current deep learning papers contain such visualizations, these are usually handcrafted just before publication, which results in a lack of a common visual grammar, significant time investment, errors,…
New dataset and analysis improve evaluation of visual representation models.
problem Insufficient evaluation methods for visual representation models.
method Analyzed five representations and developed a new dataset.
result Models with poor linear classification performance can still perform well on complex tasks.
Visual attention serves as a means of feature selection mechanism in the perceptual system. Motivated by Broadbent's leaky filter model of selective attention, we evaluate how such mechanism could be implemented and affect the learning process of deep reinforcement learning. We visualize and analyze the feature maps of…
We present GraphTSNE, a novel visualization technique for graph-structured data based on t-SNE. The growing interest in graph-structured data increases the importance of gaining human insight into such datasets by means of visualization. Among the most popular visualization techniques, classical t-SNE is not suitable o…
The paper evaluates integrals of planes and their relation to convex set angles.
problem Integrals of invariant measures of pairs of planes in E3. method Expressing integrals in terms of visual angle functions of convex sets.
result Evaluation of a Crofton-type inequality deficit.
We propose a technique for making Convolutional Neural Network (CNN)-based models more transparent by visualizing input regions that are 'important' for predictions -- or visual explanations. Our approach, called Gradient-weighted Class Activation Mapping (Grad-CAM), uses class-specific gradient information to localize…
A method to visualize multidimensional local subspaces using implicit differentiation.
problem Understanding the effect of multidimensional projection on local subspaces.
method Implicit function differentiation to analyze local subspaces shaped by multidimensional ellipses.
result Visualization of local subspaces provides insights into the global structure of data.
Different layouts can characterize different aspects of the same graph. Finding a "good" layout of a graph is thus an important task for graph visualization. In practice, users often visualize a graph in multiple layouts by using different methods and varying parameter settings until they find a layout that best suits …
ConfusionFlow visualizes classifier confusion over time for model comparison.
problem Insufficient performance analysis of classifiers.
method Interactive, model-agnostic visualization tool combining confusion matrices and temporal analysis.
result ConfusionFlow facilitates detailed, comparative analysis of classifier performance over time.
MetaStackVis aids in choosing better metamodels for stacking ensembles.
problem Difficulty in selecting optimal metamodels for stacking ensembles.
method Interactive visualization tool to explore and compare different metamodels.
result Alternative metamodels significantly improve stacking ensemble performance.
Proposes a neural network method to improve consistencies in high dimensional data analysis.
problem Inconsistencies among dimensionality reduction, clustering, and visualization tasks in high dimensional data analysis.
method Consistent Representation Learning (CRL) neural network that performs NLDR transformations to satisfy LGP constraints.
result Improves consistencies in data interpretation through end-to-end task execution.
The paper explains knowledge distillation by analyzing visual concepts in DNNs.
problem Understanding how knowledge distillation affects the learning of visual concepts in deep neural networks.
method The paper proposes three hypotheses and designs mathematical metrics to evaluate feature representations of DNNs.
result The hypotheses were verified through experiments on various DNNs.
The paper uses deep learning to speed up spatial and visual connectivity analysis.
problem Slow calculation of spatial and visual connectivity metrics.
method Investigates machine learning models and a pipeline for training them on spatial and visual connectivity analysis.
result Deep learning models significantly speed up the analysis process.
Interpretation and explanation of deep models is critical towards wide adoption of systems that rely on them. In this paper, we propose a novel scheme for both interpretation as well as explanation in which, given a pretrained model, we automatically identify internal features relevant for the set of classes considered…
ViewFool identifies adversarial viewpoints to test image recognition robustness.
problem Lack of robustness to viewpoint changes in visual recognition models.
method Neural Radiance Fields (NeRF) and entropic regularizer to find adversarial viewpoints.
result Common image classifiers are highly vulnerable to generated adversarial viewpoints.
In this work, we ask the following question: Can visual analogies, learned in an unsupervised way, be used in order to transfer knowledge between pairs of games and even play one game using an agent trained for another game? We attempt to answer this research question by creating visual analogies between a pair of game…
The aim of this paper is to present a new method for visual place recognition. Our system combines global image characterization and visual words, which allows to use efficient Bayesian filtering methods to integrate several images. More precisely, we extend the classical HMM model with techniques inspired by the field…
There is a growing interest in learning data representations that work well for many different types of problems and data. In this paper, we look in particular at the task of learning a single visual representation that can be successfully utilized in the analysis of very different types of images, from dog breeds to s…
VCML learns concepts and metaconcepts from images and questions.
problem Learning concepts and metaconcepts from visual data.
method Bidirectional connection between visual concepts and metaconcepts.
result VCML can generalize from limited data and noisy inputs.
InstanceFlow visualizes classifier confusion over training epochs.
problem Limited model interpretability through aggregate performance measures.
method Dual-view visualization tool showing instance-level learning behavior.
result Allows temporal analysis of training process and instance-level performance.
Speech enhancement (SE) aims to reduce noise in speech signals. Most SE techniques focus only on addressing audio information. In this work, inspired by multimodal learning, which utilizes data from different modalities, and the recent success of convolutional neural networks (CNNs) in SE, we propose an audio-visual de…
Speech enhancement (SE) aims to reduce noise in speech signals. Most SE techniques focus only on addressing audio information. In this work, inspired by multimodal learning, which utilizes data from different modalities, and the recent success of convolutional neural networks (CNNs) in SE, we propose an audio-visual de…
Spring-electrical models predict network links based on node proximity.
problem Predicting links in networks.
method Spring-electrical models applied to network layouts.
result The Euclidean distance in network layouts correlates with link probabilities.
VTAB benchmarks diverse visual tasks to assess representation learning effectiveness.
problem Lack of a unified evaluation for general visual representations.
method Developed VTAB, a benchmark for diverse visual tasks, and evaluated many representation learning algorithms.
result VTAB revealed insights into the effectiveness of various representation learning methods.
Relational Mimic improves visual imitation learning from video demonstrations.
problem Improving robustness and sample efficiency in visual imitation learning.
method Combines generative adversarial networks and relational learning.
result Improves agent performance in challenging locomotion tasks.
Boosts neural network performance by improving weight separability.
problem Improving the separability of weight vectors in neural networks.
method Proposes a new evaluation metric and feed-backward reconstruction loss to encourage weight separability.
result Improves visual recognition performance across various tasks.
The paper tackles entity induction and reference in visual storytelling.
problem Coherence in visual storytelling through proper entity introduction and reference.
method Building an entity skeleton, using an encoder-decoder framework, and proposing a glocal hierarchical attention model.
result The proposed models outperform the baseline in automatic evaluation metrics and human preference.
Evaluation often aims to reduce the correctness or error characteristics of a system down to a single number, but that always involves trade-offs. Another way of dealing with this is to quote two numbers, such as Recall and Precision, or Sensitivity and Specificity. But it can also be useful to see more than this, and …
Associating image regions with text queries has been recently explored as a new way to bridge visual and linguistic representations. A few pioneering approaches have been proposed based on recurrent neural language models trained generatively (e.g., generating captions), but achieving somewhat limited localization accu…
A new visualization tool MD plot discovers interesting structures in continuous features.
problem Identifying interesting structures in data distributions, especially with skewed, clipped, or multimodal distributions.
method Proposes a new visualization tool called the mirrored density plot (MD plot) that does not require adjusting density estimation parameters.
result The MD plot outperforms conventional methods in identifying structures in complex distributions.
A visualization aids in comparing regression models by highlighting errors and correlations.
problem Comparing regression models is difficult due to varying hyper-parameters and metrics.
method Introduces a novel visualization approach using 2D residual space, Mahalanobis distance, and colormaps.
result Enhanced understanding of regression model performance differences and error distributions.
Study evaluates self-supervised representations in interactive environments.
problem Unclear which self-supervised methods best capture meaningful features of diverse environments.
method Quantitative evaluation of representations in two visual environments: Flappy Bird and Sonic The Hedgehog.
result Representations' utility depends on the visuals and dynamics of the environment.