Embeddings are ubiquitous in machine learning, appearing in recommender systems, NLP, and many other applications. Researchers and developers often need to explore the properties of a specific embedding, and one way to analyze embeddings is to visualize them. We present the Embedding Projector, a tool for interactive v…
On-device research index
arXiv research
A locally-built, LLM-digested index of recent arXiv papers in quant finance, geometry/topology, and statistical ML — keyword search served straight from SQLite on this machine.
168,657 papers · 148 categories
Trend · papers per month
48 results for “Visual Embeddings”
A framework visualizes embedding spaces of neural survival analysis models using anchor directions.
problem Visualizing complex embeddings in neural survival analysis models.
method Estimating anchor directions through clustering or user-supplied concepts, revealing relationships with raw inputs and survival times.
result Visualization strategies reveal how anchor directions relate to raw clinical features and survival time distributions.
Proposes MR-SNE for multimodal data visualization.
problem Visualizing data from multiple domains with relations across them.
method Extends t-SNE to compute augmented relations and jointly embed them in a low-dimensional space.
result Demonstrates promising performance in visualizing Flickr and Animal with Attributes 2 datasets.
Assessing and improving reliability of neighbor embedding methods: a map-continuity perspectivestat.ME
Improves visualization of high-dimensional data by correcting misleading artifacts in neighbor embedding methods.
problem Misleading visual artifacts in t-SNE and UMAP due to lack of data-independent manifold learning interpretations.
method LOO-map framework that extends embedding maps to the entire input space, identifying and correcting map discontinuities.
result Developed point-wise diagnostic scores to detect unreliable embedding points and improve hyperparameter selection.
This paper finds a linear relationship between t-SNE perplexity and data set size.
problem Choosing the right perplexity for t-SNE embeddings.
method Analyzed the relationship between perplexity and data set size.
result Embeddings remain structurally consistent when perplexity is adjusted accordingly.
Modern datasets and models are notoriously difficult to explore and analyze due to their inherent high dimensionality and massive numbers of samples. Existing visualization methods which employ dimensionality reduction to two or three dimensions are often inefficient and/or ineffective for these datasets. This paper in…
ViCE uses superpixels to enhance self-supervised learning for better dense visual embeddings.
problem Lack of high-resolution feature maps from self-supervised models.
method Superpixels for dense representation learning, contrasting over regions.
result Improves unsupervised semantic segmentation on benchmarks like Cityscapes and COCO.
Proposes QQE for transforming and embedding data distributions.
problem Transforming and embedding data distributions for better representation or visualization.
method Quantile-Quantile Embedding (QQE) using quantile-quantile plot concept.
result QQE allows for better discrimination of classes in some cases.
DSNE visualizes data velocity in lower dimensions.
problem Understanding movement patterns in high-dimensional data.
method DSNE is a variation of Stochastic Neighbor Embedding that learns velocity embeddings using Euclidean distances on a unit sphere.
result DSNE enables visualization of data movement in lower dimensions.
Low dimensional embeddings that capture the main variations of interest in collections of data are important for many applications. One way to construct these embeddings is to acquire estimates of similarity from the crowd. However, similarity is a multi-dimensional concept that varies from individual to individual. Ex…
Deep learning enhances art market valuation by incorporating visual data.
problem Improving valuation accuracy in the art market, especially for first-time sales.
method Benchmarked classical and modern deep learning models using a large auction dataset.
result Visual embeddings add distinct economic value for first-time art sales.
Visual rendering of graphs is a key task in the mapping of complex network data. Although most graph drawing algorithms emphasize aesthetic appeal, certain applications such as travel-time maps place more importance on visualization of structural network properties. The present paper advocates two graph embedding appro…
A new approach clusters data first, then embeds each cluster, improving transparency.
problem Visualizing data with latent clusters while preserving global geometry.
method First cluster, then embed each cluster, aligning the clusters.
result The approach is competitive with existing methods and more transparent.
Deep metric learning is often used to learn an embedding function that captures the semantic differences within a dataset. A key factor in many problem domains is how this embedding generalizes to new classes of data. In observing many triplet selection strategies for Metric Learning, we find that the best performance …
Kernelized Taylor diagram visualizes data populations with fewer assumptions.
problem Limitations of Taylor diagram in capturing non-linear relationships and sensitivity to outliers.
method Proposes a kernelized version of the Taylor diagram that uses maximum mean discrepancy and kernel mean embedding.
result Kernelized Taylor diagram visualizes data populations with minimal assumptions of data distributions.
DEN creates interpretable visualizations using Siamese networks.
problem Creating interpretable visualizations of complex datasets.
method Differentiating Embedding Networks (DEN) using Siamese neural networks and loss functions.
result DEN outperforms existing techniques on FashionMNIST and interpretable features are identified.
Neighbor embeddings balance attraction and repulsion to visualize data.
problem Visualizing high-dimensional datasets with trade-offs between continuous and discrete structures.
method Neighbor embeddings combine attractive and repulsive forces to visualize data.
result Changing the exaggeration parameter in t-SNE yields a spectrum of embeddings with a trade-off between continuous and discrete structures.
Unified view of SOMs and SNE from a common framework.
problem Comparing and understanding SOMs and SNE.
method Unified mathematical framework, quantitative comparison on datasets.
result SOMs and SNE can be derived from a common framework.
Euclidean embeddings of data are fundamentally limited in their ability to capture latent semantic structures, which need not conform to Euclidean spatial assumptions. Here we consider an alternative, which embeds data as discrete probability distributions in a Wasserstein space, endowed with an optimal transport metri…
For applications in computing, Bezier curves are pervasive and are defined by a piecewise linear curve L which is embedded in R^3 and yields a smooth polynomial curve C embedded in R^3. It is of interest to understand when L and C have the same embeddings. One class of counterexamples is shown for L being unknotted, wh…
We introduce the isoperimetric loss as a regularization criterion for learning the map from a visual representation to a semantic embedding, to be used to transfer knowledge to unknown classes in a zero-shot learning setting. We use a pre-trained deep neural network model as a visual representation of image data, a Wor…
An important goal of computer vision is to build systems that learn visual representations over time that can be applied to many tasks. In this paper, we investigate a vision-language embedding as a core representation and show that it leads to better cross-task transfer than standard multi-task learning. In particular…
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…
Visualizing high-dimensional data is an essential task in Data Science and Machine Learning. The Centroid-Encoder (CE) method is similar to the autoencoder but incorporates label information to keep objects of a class close together in the reduced visualization space. CE exploits nonlinearity and labels to encode high …
We present numerical visualizations of Ricci Flow of surfaces and 3-dimensional manifolds of revolution. Ricci_rot is an educational tool which visualizes surfaces of revolution moving under Ricci flow. That these surfaces tend to remain embedded in R3 is what makes direct visualization possible. The numerical lessons …
In the advent of big data era, interactive visualization of large data sets consisting of M*10^5+ high-dimensional feature vectors of length N (N ~ 10^3+), is an indispensable tool for data exploratory analysis. The state-of-the-art data embedding (DE) methods of N-D data into 2-D (3-D) visually perceptible space (e.g.…
We introduce a nonlinear method for directly embedding large, sparse, stochastic graphs into low-dimensional spaces, without requiring vertex features to reside in, or be transformed into, a metric space. Graph data and models are prevalent in real-world applications. Direct graph embedding is fundamental to many graph…
Two methods factor out prior knowledge from low-dimensional embeddings.
problem Visualizing data without considering background knowledge.
method JEDI for tSNE and CONFETTI for any embedding.
result Embeddings reveal meaningful structure hidden by prior knowledge.
Topological surgery in dimension is intrinsically connected with the classification of -manifolds and with patterns of natural phenomena. In this expository paper, we present two different approaches for understanding and visualizing the process of -dimensional surgery. In the first approach, we view the proc…
We prove that every visual Gromov hyperbolic space X whose boundary at infinity has the finite capacity dimension n admits a quasi-isometric embedding into (n+1)-fold product of metric trees.
Theoretical analysis of t-SNE for visualizing clustered data.
problem Understanding t-SNE for visualizing high-dimensional clustered data.
method Gradient descent approach and power iterations based on graph Laplacian.
result Asymptotic equivalence and limiting behavior of t-SNE's early exaggeration stage.
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,…
Deep Neural Mapscs.LG
We introduce a new unsupervised representation learning and visualization using deep convolutional networks and self organizing maps called Deep Neural Maps (DNM). DNM jointly learns an embedding of the input data and a mapping from the embedding space to a two-dimensional lattice. We compare visualizations of DNM with…
The complexity of a learning task is increased by transformations in the input space that preserve class identity. Visual object recognition for example is affected by changes in viewpoint, scale, illumination or planar transformations. While drastically altering the visual appearance, these changes are orthogonal to r…
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.
This research converts visual information into audio for users to perceive.
problem Brevity in conveying visual information through spoken language.
method Pretrained image embedding network, GAN for metric space mapping, human subject testing.
result Users can accurately classify audio sonifications of faces.
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…
Uncovering Locally Low-dimensional Structure in Networks by Locally Optimal Spectral Embeddingstat.ML
LASE improves local network structure visualization by targeting locally low-dimensional regions.
problem Global spectral embedding fails to capture local geometric features in sparse, transitive networks.
method Local Adjacency Spectral Embedding (LASE) using weighted spectral decomposition.
result LASE reveals locally low-dimensional structure, improving local reconstruction and visualization.
We introduce a multimodal visual-textual search refinement method for fashion garments. Existing search engines do not enable intuitive, interactive, refinement of retrieved results based on the properties of a particular product. We propose a method to retrieve similar items, based on a query item image and textual re…
The visual systems of many mammals, including humans, is able to integrate the geometric information of visual stimuli and to perform cognitive tasks already at the first stages of the cortical processing. This is thought to be the result of a combination of mechanisms, which include feature extraction at single cell l…
In this paper, we examined the zero-shot activity recognition task with the usage of videos. We introduce an auto-encoder based model to construct a multimodal joint embedding space between the visual and textual manifolds. On the visual side, we used activity videos and a state-of-the-art 3D convolutional action recog…
Selecting the most appropriate data examples to present a deep neural network (DNN) at different stages of training is an unsolved challenge. Though practitioners typically ignore this problem, a non-trivial data scheduling method may result in a significant improvement in both convergence and generalization performanc…
Models use embeddings and attention for better claim severity prediction.
problem Improving predictive modeling of claim severity with categorical data.
method Developed neural networks and attention-based architectures with embeddings.
result Attention-based models enhance predictive performance with contextual augmentation.
cGAP visualizes high-dimensional categorical data with interpretable geometric structure.
problem Lack of visualization tools for high-dimensional categorical data.
method cGAP uses Homogeneity Analysis (HOMALS) to embed data in a 3D space and maps it to colors.
result cGAP reveals coherent clusters, outliers, and local-to-global structure in categorical data.
cGAP visualizes high-dimensional categorical data with interpretable geometric structure.
problem Lack of visualization tools for high-dimensional categorical data.
method cGAP uses Homogeneity Analysis (HOMALS) to embed data in a 3D space and maps it to colors for visualization.
result cGAP reveals coherent clusters, outliers, and local-to-global structure in categorical data.
Visual summarization of clinical data collected on patients contained within the electronic health record (EHR) may enable precise and rapid triage at the time of patient presentation to an emergency department (ED). The triage process is critical in the appropriate allocation of resources and in anticipating eventual …
This work proves the continuum limit of t-SNE for data visualization.
problem Understanding the theoretical basis of t-SNE from a continuum limit perspective.
method Proving the Kullback-Leibler divergence consistency as for t-SNE.
result The continuum variational problem involving non-convex gradient regularization and penalty on probability density function magnitude.
This paper extends boundary embedding results to coarsely convex spaces.
problem Generalizing boundary embedding results to coarsely convex spaces.
method Generalizing Dydak and Virk's work on Gromov hyperbolic spaces to coarsely convex spaces.
result Maps between coarsely convex spaces induce continuous maps between their boundaries.