Visual design improves financial data classification accuracy.
problem Improving financial decision-making through better data representation.
method Comparing numeric vs visual data representations in supervised classification.
result Visual transformation of numeric data leads to higher predictability.
Simple method disentangles content and style from pre-trained vision models.
problem Learning interpretable features in visual representations.
method Probabilistic linear entanglement model and simple disentanglement algorithm.
result Method provably disentangles content and style features.
This work explores how XAI methods can visualize the diversity of feature representations in Bayesian Neural Networks.
problem Explaining the diversity of feature representations learned by Bayesian Neural Networks.
method Application of global XAI methods to visualize and quantify the diversity of feature representations.
result The diversity of learned feature representations correlates with uncertainty estimates and network width.
Understanding how images of objects and scenes behave in response to specific ego-motions is a crucial aspect of proper visual development, yet existing visual learning methods are conspicuously disconnected from the physical source of their images. We propose to exploit proprioceptive motor signals to provide unsuperv…
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.
Improved video and movie description using multitask learning.
problem Lack of training data and poor generalization in video captioning.
method Multitask learning encoder-decoder framework for video sequences.
result Improved performance on multi-caption and single-caption datasets.
Deep neural networks have been developed drawing inspiration from the brain visual pathway, implementing an end-to-end approach: from image data to video object classes. However building an fMRI decoder with the typical structure of Convolutional Neural Network (CNN), i.e. learning multiple level of representations, se…
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.
A new method for tracking objects using diverse templates.
problem Improving visual tracking performance and robustness.
method Proposes a framework that uses additional object templates and a new diversity measure in siamese feature space.
result Achieves strong empirical results on tracking benchmarks, improving performance and robustness.
We present an autoencoder that leverages learned representations to better measure similarities in data space. By combining a variational autoencoder with a generative adversarial network we can use learned feature representations in the GAN discriminator as basis for the VAE reconstruction objective. Thereby, we repla…
Study shows agents benefit from hearing in addition to vision.
problem Limited effectiveness of vision-only reinforcement learning agents.
method Used audio as complementary information to visual cues in state representation.
result Agents perform better when hearing is added to vision.
This paper presents a novel yet intuitive approach to unsupervised feature learning. Inspired by the human visual system, we explore whether low-level motion-based grouping cues can be used to learn an effective visual representation. Specifically, we use unsupervised motion-based segmentation on videos to obtain segme…
Improved visual representation learning with conditional negative sampling.
problem Learning strong unsupervised visual representations using contrastive learning.
method Introduce a family of mutual information estimators that sample negatives conditionally.
result Improves accuracy by 2-5% points on four standard image datasets.
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.
Robust optimization improves deep learning feature representations.
problem Deep learning feature representations lack versatility and high-level encoding.
method Robust optimization as a prior for feature learning.
result Robust models learn approximately invertible, salient feature representations.
In this paper, we present a technique for unsupervised learning of visual representations. Specifically, we train a model for foreground and background classification task, in the process of which it learns visual representations. Foreground and background patches for training come af- ter mining for such patches from …
Adaptive cross-modal few-shot learning improves performance in image classification.
problem Few-shot classification with limited data.
method Adaptive combination of visual and semantic features.
result Model outperforms uni-modality and modality-alignment methods.
AV-ASR system improves speech recognition with visual context.
problem Improving speech recognition accuracy with visual information.
method Transformer-based architecture with multiresolution and multimodal training.
result Multiresolution training speeds up convergence and improves WER by 18%.
A new ZSL algorithm uses shared sparse representations for unseen classes.
problem Classifying images from unseen classes using only semantic information.
method Coupled dictionary learning to represent visual and semantic features in an intermediate space.
result The proposed method outperforms state-of-the-art ZSL algorithms on benchmark datasets.
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.
SAFE detects fake news by analyzing text and image similarities.
problem Detecting fake news with less focus on text-image similarity.
method SAFE uses neural networks to extract text and visual features, then learns their relationship to predict fake news.
result SAFE effectively recognizes fake news based on text, images, or mismatches.
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 VAE models reveal hierarchical visual cortex computations.
problem Capturing hierarchical visual cortex computations in generative models.
method Sparse coding hierarchical VAEs trained on natural images with varied generative and recognition components.
result Representations similar to those in visual cortex emerge under inductive biases.
New method for visualizing high-level concepts in generative models.
problem Challenges in evaluating and visualizing concepts in generative models.
method Introduces a method to compute concept saliency maps for latent representations of known or novel high-level concepts.
result Concept saliency maps highlight input features important for high-level concepts.
Paper improves video feature learning for better downstream tasks.
problem Improving video feature learning for better performance on downstream tasks.
method Self-supervised learning approach using contrastive bidirectional transformer, extending BERT for real-valued feature vectors.
result Significantly improved performance on video classification, captioning, and segmentation tasks.
Enhances visual localization using graph smoothing.
problem Inferring camera pose from a single image.
method Constructs a graph based on GPS coordinates and temporal information, then smooths feature representations.
result Significantly improves localization accuracy on large datasets.
DHRL learns interpretable features from visual data.
problem Limited use of deep learning in basic research for interpretable features.
method Generative model chaining, ladder network architecture, latent space regularization.
result DHRL generates disentangled hierarchical features from small datasets.
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.
Human-in-the-loop data analysis applications necessitate greater transparency in machine learning models for experts to understand and trust their decisions. To this end, we propose a visual analytics workflow to help data scientists and domain experts explore, diagnose, and understand the decisions made by a binary cl…
Self-supervised learning of visual semantics in image games.
problem Learning visual semantics in referential emergent language games.
method Investigating the impact of feature extractor weights and tasks on visual semantics, using various image augmentations and additional tasks.
result Communication systems can learn visual semantics in a self-supervised manner by playing the right types of games.
BERT captures linguistic features in separate semantic and syntactic subspaces.
problem Understanding how transformer models like BERT represent linguistic features internally.
method Qualitative and quantitative investigations of BERT's internal representations.
result Evidence of a fine-grained geometric representation of word senses and syntactic representations.
This research reverses feature visualization in neural networks to optimize for specific feature objectives.
problem The invertibility of feature visualization in neural networks is not well understood.
method The approach involves optimizing for the feature objective that generates the input used in feature visualization, using the gradient of a specific objective function.
result A closed-form solution is found to minimize the gradient, providing an alternative view on network sensitivity.
We present a novel, log-radius profile representation for convex curves and define a new operation for combining the shape features of curves. Unlike the standard, angle profile-based methods, this operation accurately combines the shape features in a visually intuitive manner. This method have implications in shape an…
Vision Transformers show different internal representations compared to CNNs.
problem Understanding how Vision Transformers solve image classification tasks.
method Comparative analysis of ViT and CNN architectures on image classification benchmarks.
result ViT has more uniform representations across all layers, while CNNs have more varied representations.
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.
Methodology for visualizing labeled datasets with mixed features.
problem Visualization of labeled mixed-featured datasets.
method Developed a Max-Ratio Projection (MRP) method for continuous features and extended it to datasets with discrete and continuous features using Gaussianized distributional transforms and copula models.
result Visualization of labeled mixed-featured datasets using Max-Ratio Projection and Gaussianized distributional transforms.
DEMUD-VIS detects novel image content and explains it visually.
problem Detecting and explaining novel image content in large datasets.
method Uses CNN for feature extraction, reconstruction error for novelty detection, and up-convolutional networks for image reconstruction.
result Demonstrates visual explanations of novel image content on diverse datasets.
This paper discusses the role of risk communication in macroprudential oversight and of visualization in risk communication. Beyond the soar in data availability and precision, the transition from firm-centric to system-wide supervision imposes vast data needs. Moreover, except for internal communication as in any orga…
Improved visual speech synthesis using adapted ASR acoustic models.
problem Lack of synchronized audio, video, and depth data for speaker-independent speech-driven visual speech synthesis.
method Adapted an ASR acoustic model trained on audio-only data to the visual speech synthesis domain.
result Viewers significantly prefer animations generated from the adapted ASR acoustic model.
Modeling curvature-sensitive cells in visual cortex using manifold geometry.
problem Understanding how curvature influences cell function in the visual cortex.
method Developed a 4D manifold with canonical Engel structure to represent orientation, position, curvature, and scale.
result Characterized curvature-sensitive receptive profiles using left-invariant generators of the Engel structure.
Task2Vec creates task embeddings for meta-learning.
problem Creating a framework for selecting feature extractors for new tasks.
method Process images through a probe network to compute task embeddings based on Fisher information matrix.
result Task embeddings predict task similarities and feature extractor performance.
Visual observations of dynamic phenomena, such as human actions, are often represented as sequences of smoothly-varying features . In cases where the feature spaces can be structured as Riemannian manifolds, the corresponding representations become trajectories on manifolds. Analysis of these trajectories is challengin…
New method visualizes tabular feature semantics for better model understanding.
problem Lack of feature interaction interpretation in tabular ML models.
method Feature Vectors method for global tabular dataset interpretability.
result Visualizes semantic relationships among tabular features.
Convolutional neural networks provide visual features that perform remarkably well in many computer vision applications. However, training these networks requires significant amounts of supervision. This paper introduces a generic framework to train deep networks, end-to-end, with no supervision. We propose to fix a se…
GraphTSNE visualizes graph data by integrating graph structure and node features.
problem Lack of suitable visualization techniques for graph-structured data.
method GraphTSNE combines t-SNE with graph convolutional networks to visualize graph data.
result GraphTSNE produces better visualizations of graph data compared to existing methods.
The quality of data representation in deep learning methods is directly related to the prior model imposed on the representations; however, generally used fixed priors are not capable of adjusting to the context in the data. To address this issue, we propose deep predictive coding networks, a hierarchical generative mo…
WAPPO optimizes feature distributions for better visual transfer in RL.
problem Improving visual transfer in reinforcement learning.
method WAPPO uses Wasserstein Confusion to minimize feature distribution distance.
result WAPPO outperforms previous methods in visual transfer across different environments.
A new method integrates autoencoders with geometry regularization for manifold learning.
problem Extracting simplified low-dimensional representations that capture intrinsic geometry in data.
method Integrates autoencoders with a geometric regularization term based on diffusion potential distances.
result The method preserves intrinsic structure, enables out-of-sample extension, and faithful reconstruction.