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.
Proposes Population Difference Criterion for visually observed subpopulation differences.
Paper establishes baselines for offline RL from visual observations.
Proposes MR-SNE for multimodal data visualization.
Adversarial attacks can manipulate ML-aided visualizations, tricking analysts.
Helps visually impaired users make better decisions by adjusting their observations.
The paper addresses bias in visual recognition models by reweighting observations.
The paper corrects biases in estimating intrinsic dimension and differential entropy.
In recent years, a large amount of model-agnostic methods to improve the transparency, trustability and interpretability of machine learning models have been developed. We introduce local feature importance as a local version of a recent model-agnostic global feature importance method. Based on local feature importance…
Clouds frequently cover the Earth's surface and pose an omnipresent challenge to optical Earth observation methods. The vast majority of remote sensing approaches either selectively choose single cloud-free observations or employ a pre-classification strategy to identify and mask cloudy pixels. We follow a different st…
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 …
The abstract discusses how humans use visualizations in machine learning.
DPFRL uses particle filters for decision making with complex visual observations.
Neural model predicts object states and physical parameters from visual observations.
CVRL tackles complex visual observations in reinforcement learning.
The paper offers a checklist for comparing human and machine visual perception.
New dataset tests mental rotation from single images, improving model understanding of 3D scenes.
Consensus dimension reduction combines multiple visualizations to identify shared patterns.
Classically, imitation learning algorithms have been developed for idealized situations, e.g., the demonstrations are often required to be collected in the exact same environment and usually include the demonstrator's actions. Recently, however, the research community has begun to address some of these shortcomings by …
This paper investigates uncertainty calibration in multimodal large language models.
AVH scores measure sample hardness, improving model calibration.
A framework disentangles controllable objects from visual signals for improved RL.
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…
Algorithm improves imitation learning from visual data in partially observable environments.
Paper speeds up visualization of uncertain data.
New method clusters multimodal data with consistency.
A neural network visualizes data structure and concepts.
Visual system compares and evaluates machine learning models for clinical data predictions.
Interpretation and diagnosis of machine learning models have gained renewed interest in recent years with breakthroughs in new approaches. We present Manifold, a framework that utilizes visual analysis techniques to support interpretation, debugging, and comparison of machine learning models in a more transparent and i…
The paper uses deep learning to speed up spatial and visual connectivity analysis.
A framework for measuring differences in categorical data.
Convolutional neural networks have been successfully applied to various NLP tasks. However, it is not obvious whether they model different linguistic patterns such as negation, intensification, and clause compositionality to help the decision-making process. In this paper, we apply visualization techniques to observe h…
In recent years, deep generative models have been shown to 'imagine' convincing high-dimensional observations such as images, audio, and even video, learning directly from raw data. In this work, we ask how to imagine goal-directed visual plans -- a plausible sequence of observations that transition a dynamical system …
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…
Visual spoofing bypasses spam filters and plagiarism detection.
New visual tool detects financial market changes using multiscaling analysis.
Using different methods for laying out a graph can lead to very different visual appearances, with which the viewer perceives different information. Selecting a "good" layout method is thus important for visualizing a graph. The selection can be highly subjective and dependent on the given task. A common approach to se…
Visual relationship detection can bridge the gap between computer vision and natural language for scene understanding of images. Different from pure object recognition tasks, the relation triplets of subject-predicate-object lie on an extreme diversity space, such as \textit{person-behind-person} and \textit{car-behind…
There are many statistical tests that verify the null hypothesis: the variable of interest has the same distribution among k-groups. But once the null hypothesis is rejected, how to present the structure of dissimilarity between groups? In this article, we introduce The Merging Path Plot - a methodology, and factorMerg…
Visualizes deep generative models for drug design.
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 …
Temporal observations such as videos contain essential information about the dynamics of the underlying scene, but they are often interleaved with inessential, predictable details. One way of dealing with this problem is by focusing on the most informative moments in a sequence. We propose a model that learns to discov…
Imitation from observation (IfO) is the problem of learning directly from state-only demonstrations without having access to the demonstrator's actions. The lack of action information both distinguishes IfO from most of the literature in imitation learning, and also sets it apart as a method that may enable agents to l…
This research reverses feature visualization in neural networks to optimize for specific feature objectives.
Human visual object recognition is typically rapid and seemingly effortless, as well as largely independent of viewpoint and object orientation. Until very recently, animate visual systems were the only ones capable of this remarkable computational feat. This has changed with the rise of a class of computer vision algo…
Sensor data has been playing an important role in machine learning tasks, complementary to the human-annotated data that is usually rather costly. However, due to systematic or accidental mis-operations, sensor data comes very often with a variety of missing values, resulting in considerable difficulties in the follow-…
One of the primary challenges of visual storytelling is developing techniques that can maintain the context of the story over long event sequences to generate human-like stories. In this paper, we propose a hierarchical deep learning architecture based on encoder-decoder networks to address this problem. To better help…
This work tackles long-term visual planning by goal-conditioned hierarchical predictors.
Person re-identification (re-id), an emerging problem in visual surveillance, deals with maintaining entities of individuals whilst they traverse various locations surveilled by a camera network. From a visual perspective re-id is challenging due to significant changes in visual appearance of individuals in cameras wit…