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.
PerceptNet mimics human vision to estimate image quality.
problem Estimating perceptual distance between images and their perturbations.
method Inspired by human visual system, PerceptNet uses convolutional neural network architecture.
result PerceptNet outperforms traditional image quality metrics and deep learning methods.
We propose a new equilibrium enforcing method paired with a loss derived from the Wasserstein distance for training auto-encoder based Generative Adversarial Networks. This method balances the generator and discriminator during training. Additionally, it provides a new approximate convergence measure, fast and stable t…
DSM improves visual quality of fetoscopic videos by mosaicking.
problem Challenges in identifying all vascular connections during fetoscopy due to low visual quality and drift.
method Proposes a Deep Sequential Mosaicking (DSM) framework using deep learning techniques to handle visual variations and reduce drift.
result DSM framework reduces accumulated drift and improves visual quality of fetoscopic videos.
New method makes quality metrics scale-invariant for high-dimensional data.
problem Scale sensitivity in quality metrics affects the accuracy of data projections.
method Analytical and empirical investigation of stress and KL divergence; introduction of a scale-invariant technique.
result The proposed technique accurately captures expected behavior and makes metrics scale-invariant.
BlosSOM improves data visualization for large datasets.
problem Insufficient performance of dimensionality reduction methods for large datasets.
method GPU-accelerated semi-supervised EmbedSOM algorithm.
result Produces high-quality visualizations with user control.
Study finds visual explanations do not significantly improve human accuracy or trust in model predictions.
problem Measuring the impact of visual explanations on human accuracy and trust in model predictions.
method Randomized controlled trial with image-based age prediction task, varying levels of explanation quality.
result Visual explanations do not significantly alter human accuracy or trust in the model.
Cluster analysis is widely used in the areas of machine learning and data mining. Fuzzy clustering is a particular method that considers that a data point can belong to more than one cluster. Fuzzy clustering helps obtain flexible clusters, as needed in such applications as text categorization. The performance of a clu…
In this short article I introduce the knotR package, which creates two dimensional knot diagrams optimized for visual appearance using the R programming language. The knotR package is a systematic R-centric suite of software for the creation of production-quality artwork of knot diagrams, released under GPL2.
Proposes a new method for evaluating and constructing hierarchical topic models.
problem Evaluation and construction of hierarchical topic models.
method Represent HTM as layers and edges, introduce quality measures, and develop a heterogeneous algorithm.
result The proposed heterogeneous algorithm significantly outperforms baseline approaches.
Generative adversarial network synthesizes sketches into realistic images.
problem Improving the quality and realism of facial sketches.
method Hybrid GAN with quality guided encoder and identity preserving network.
result Synthesized images are more realistic and maintain identity.
ivhd tool efficiently visualizes large high-dimensional data.
problem Interactive visualization of large high-dimensional datasets.
method Minimal memory and computational time requirements for nearest neighbor visualization.
result Significantly reduces computational and memory loads.
Large-scale eye-tracking dataset for Atari games.
problem Improving AI decision-making through human eye-tracking data.
method Recorded 117 hours of gameplay with eye movements from 20 Atari games.
result Human gameplay decisions and scores comparable to human records.
It is commonly believed that increasing the interpretability of a machine learning model may decrease its predictive power. However, inspecting input-output relationships of those models using visual analytics, while treating them as black-box, can help to understand the reasoning behind outcomes without sacrificing pr…
Paper reviews and synthesizes methods for evaluating dimensionality reduction techniques.
problem Evaluating and comparing dimensionality reduction techniques.
method Framework and toolkit in R for exploring and evaluating dimensionality reduction quality through visual insights.
result Helps researchers compare and select dimensionality reduction techniques using visual insights.
The paper improves CNN visualization for safer reinforcement learning.
problem Safety risks in reinforcement learning control systems.
method Extensions of CNN visualization algorithms for reinforcement learning.
result Visualization aids in understanding and improving reinforcement learning policies.
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.
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.
Time-agnostic predictors predict frames without fixed time intervals.
problem Predicting events in the future or between waypoints is difficult.
method Decouple visual prediction from a rigid notion of time, discovering predictable 'bottleneck' frames.
result Predictions are of higher visual quality and correspond to coherent semantic subgoals.
In order to be useful, visualizations need to be interpretable. This paper uses a user-based approach to combine and assess quality measures in order to better model user preferences. Results show that cluster separability measures are outperformed by a neighborhood conservation measure, even though the former are usua…
Enhances supervised visualization for unseen data using autoencoders and random forest.
problem Lack of generalization to unseen test sets in supervised dimensionality reduction.
method Combines autoencoder and random forest proximities for out-of-sample extension.
result 40% reduction in training time with 10% of training data, achieving consistent quality.
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.
IsUMap improves data visualization of complex geometries.
problem Accurately representing complex, locally distorted metric spaces.
method Integrates UMAP and Isomap with Vietoris-Rips filtrations.
result Significant improvements in data representation quality.
New technique hides adversarial attacks in complex images, making them imperceptible.
problem Lack of interpretability in Convolutional Neural Networks (CNNs) and vulnerability to adversarial attacks.
method Developed a technique that hides adversarial attacks in regions of high complexity, making them imperceptible to human observers.
result Significant evidence of concealment of adversarial attacks in images, making them imperceptible to human observers.
Super-resolution methods form high-resolution images from low-resolution images. In this paper, we develop a new Bayesian nonparametric model for super-resolution. Our method uses a beta-Bernoulli process to learn a set of recurring visual patterns, called dictionary elements, from the data. Because it is nonparametric…
New research highlights flaws in evaluating clustering algorithms using classification datasets.
problem Flaws in evaluating clustering algorithms using classification datasets.
method Advanced visualization and dimension reduction techniques to expose flaws.
result Current practice of evaluating clustering algorithms may produce misleading results.
PrototypeML simplifies neural network design and development.
problem Error-prone code and time-consuming model design.
method Visual interface for neural networks, abstracting PyTorch.
result Reduces model design and development time, easier debugging.
Efficient auto-tuning for DR hyperparameters with BO.
problem Hyperparameter selection in DR for large-scale datasets.
method Bayesian optimization with surrogate model, normalization, subsampling.
result Robust and efficient hyperparameter selection for DR algorithms.
Improved StyleGAN model enhances image quality and invertibility.
problem Characteristics artifacts in StyleGAN's image quality.
method Redesigned generator normalization, revisited progressive growing, and introduced a capacity problem.
result Improved image quality and easier inversion of generated images.
A novel method automates quality control of fMRI scans, improving accuracy and generalizability.
problem Lack of automated QC for fMRI scans limits clinical neuroscience research.
method Train machine learning classifiers using runtime log features to predict scan quality.
result Classifiers trained on FLAG-QC features outperform previous methods (AUC=0.79 vs AUC=0.56).
A method merges two pretrained diffusion experts to improve image quality and likelihood.
problem Trade-off between image quality and data likelihood in diffusion models.
method Combining two pretrained diffusion experts by switching between them along the denoising trajectory.
result The merged model consistently matches or outperforms its base components, improving or preserving both likelihood and sample quality.
NCVis speeds up data visualization for large datasets.
problem Performance issues in t-SNE for large datasets.
method Noise contrastive estimation for scalable visualization.
result NCVis outperforms state-of-the-art techniques in speed and quality.
New metric for video generation models, addressing quality, coherence, and diversity.
problem Lack of metrics for evaluating generative models of video.
method Proposed Fréchet Video Distance (FVD) and StarCraft 2 Videos (SCV) benchmark.
result FVD correlates well with human judgment of generated videos.
Study shows bottlenecks improve image segmentation quality.
problem Robust object discovery in real-world images remains challenging.
method Empirical investigation of reconstruction bottlenecks in GENESIS model.
result Reconstruction bottlenecks determine reconstruction and segmentation quality.
Identifies open problems in quality assurance of safety-critical ML systems.
problem Quality assurance for safety-critical ML systems, especially in automated driving.
method Identified and classified open problems using automated-driving vehicles as an example.
result Open problems require interdisciplinary knowledge from various fields.
Graph embedding techniques are useful to characterize spectral signature relations for hyperspectral images. However, such images consists of disjoint classes due to spatial details that are often ignored by existing graph computing tools. Robust parameter estimation is a challenge for kernel functions that compute suc…
Generative Adversarial Network purifies images from steganography without degrading quality.
problem Destruction of image steganography while maintaining visual quality.
method Generative Adversarial Network (GAN) optimized for steganography destruction.
result High rate of steganographic content destruction with minimal visual quality degradation.
Visualizing high-dimensional data has been a focus in data analysis communities for decades, which has led to the design of many algorithms, some of which are now considered references (such as t-SNE for example). In our era of overwhelming data volumes, the scalability of such methods have become more and more importa…
SLAM-net learns to navigate visually in challenging indoor environments.
problem Challenges in SLAM for visual robot navigation, especially in noisy conditions.
method Differentiable SLAM Network (SLAM-net) that encodes a particle filter SLAM algorithm in a differentiable graph and learns components through backpropagation.
result Significantly outperforms ORB-SLAM in noisy conditions and improves the Habitat Challenge 2020 PointNav task.
CARP speeds up convex clustering by 100x and offers better visualization.
problem Computational intensity and lack of compelling visualizations in convex clustering.
method Algorithmic Regularization for iterative approximation of regularization paths.
result CARP delivers over 100-fold speed-up and finer approximation grid.
ShapeVis visualizes high-dimensional data efficiently.
problem Scalability issues with Mapper in high-dimensional data.
method Landmarks, weighted witness-graph, induced maps, modularity-based pruning.
result ShapeVis scales to millions of data points while preserving visualization quality.
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.
New study shows tradeoffs between compression quality, distortion, and perception.
problem Optimizing compression for low distortion often sacrifices perceptual quality.
method Adopted Blau & Michaeli's perceptual quality definition and studied the rate-distortion-perception tradeoff.
result Restricting perceptual quality to high generally requires a trade-off between rate and distortion.
Improves manifold learning by identifying and fixing stuck points.
problem Local minima in nonlinear embedding methods lead to poor data structure visualization.
method Introduces a method to temporarily allow pressured points to use an extra dimension in the embedding space.
result Significantly improves the objective function value of existing methods even after getting stuck in a poor local minimum.
CDSSL improves representation quality by integrating linear and nonlinear dependencies.
problem Scarcity of labeled data and neglect of nonlinear dependencies in SSL.
method CDSSL combines linear correlations and nonlinear dependencies using HSIC in RKHS.
result CDSSL enhances representation quality on diverse benchmarks.
ClusterGraph visualizes and simplifies multidimensional data clusters for better understanding.
problem Lack of global structure information in clustering results.
method Combining clustering with Topological Data Analysis to provide global structure.
result ClusterGraph provides global layout information about clusters.
SDM Policy accelerates inference for robotic tasks while maintaining high action quality.
problem Prolonged inference times in diffusion-based policies for high-frequency control tasks.
method Two-stage optimization: score matching and distribution matching; dual-teacher mechanism.
result 6x inference speedup with state-of-the-art action quality.
A simple framework improves visual representation learning.
problem Efficiently learning useful visual representations from unlabeled data.
method Contrastive learning with simplified framework and systematic study of components.
result Significant improvement in accuracy compared to previous methods.