Study extends cognitive modeling to natural images, revealing the importance of image representation.
problem Extending cognitive modeling to natural images and understanding human categorization.
method Conducted a large-scale study with over 500,000 human judgments. Used deep and shallow machine learning methods to represent images. Applied psychological models of categorization to natural images.
result Simple models with abstract prototypes outperform complex exemplar accounts when using expressive, data-driven image representations.
Paper introduces new methods for modeling categorical data.
problem Training generative models on categorical data like text and segmentation.
method Argmax Flows and Multinomial Diffusion models.
result Models outperform existing methods in log-likelihood.
Deep neural network features model human image categorization.
problem Modeling human categorization using natural images.
method Used convolutional neural network features to model human behavior.
result Representations from deep neural networks can model human natural image classifications.
Generative model for high-dimensional categorical data using Gaussian-Dirichlet fields.
problem Efficiently modeling and predicting high-dimensional categorical data.
method Combines Dirichlet and Gaussian processes for spatio-temporal modeling.
result Model accurately approximates categorical data in unobserved locations.
AdaCat improves density estimation and planning in autoregressive models.
problem Efficiently modeling sharp density changes in continuous data.
method Adaptive Categorical Discretization (AdaCat) for autoregressive models.
result Improves density estimation and planning in various data types.
New method learns disentangled discrete representations using categorical variational autoencoders.
problem Learning disentangled representations from discrete latent spaces.
method Replaced standard Gaussian VAE with a categorical VAE to mitigate rotational invariance.
result Categorical distributions improve learning of disentangled representations.
Discrete-AIR model identifies objects in images with interpretable latent codes.
problem Identifying objects in images without labeled data.
method Recurrent Auto-Encoder with structured latent distributions for discrete, continuous, and spatial attention.
result Discrete-AIR model uses minimal latent variables for efficient inference.
Paper improves video categorization using temporal coherence.
problem Video categorization in multiple modalities.
method Temporal coherence-based regularization for multimodal models.
result Models with temporal coherence outperform state-of-the-art.
A statistical algorithm for categorizing different types of matches and fraud in image databases is presented. The approach is based on a generative model of a graph representing images and connections between pairs of identities, trained using properties of a matching algorithm between images.
Study improves product categorization on Amazon using multi-modal fusion.
problem Multi-label product categorization in e-commerce.
method Late fusion of image, description, and title modalities using modified CNN and ResNet-50 models.
result Tri-modal late fusion model achieved an F1 score of 88.2%, significantly better than single modal models. New model uses attention for in-context learning of categorical data.
problem Learning from categorical data in context.
method Attention-based network with self-attention and cross-attention layers, using functional gradient descent.
result Model can perform multi-step inference for categorical observations.
Atlas dataset categorizes clothing products with high accuracy.
problem Lack of real-world datasets for e-commerce clothing product categorization.
method Collected and labeled a dataset of 186,150 images, established a benchmark for image classification and sequence models.
result Benchmark model achieved a micro f-score of 0.92.
CatSIM measures image similarity robustly to small changes.
problem Measuring similarity between images, especially with small perturbations.
method Uses structural similarity image quality paradigm, robust to small location changes.
result Structural similarity between images rated higher when not entirely overlapping.
Deep learning outperforms classical methods in categorizing BIM images.
problem Classifying building designs from BIM models.
method Used classical machine learning (HOG + SVM) and deep learning models (pre-trained and custom-designed networks).
result Deep learning models achieve significantly higher accuracy (above 89%) compared to classical methods (57%).
Teaches categories with visual explanations to improve learning.
problem Challenges of traditional machine teaching methods in providing clear explanations.
method Proposes a teaching framework that provides interpretable explanations as feedback.
result Participants achieve better test set performance with interpretable explanations.
A method for diffusion on probability simplex for generative models.
problem Tension between continuous and discrete data in diffusion models.
method Proposes using softmax function applied to Ornstein-Uhlenbeck Process on probability simplex.
result Method extends to bounded image generation.
New approach predicts under latent shifts using high-dimensional images.
problem Prediction under latent subgroup shifts with high-dimensional observations.
method Recognition-parametrised model (RPM) for identifying causal latent structure.
result Successfully adapts predictions for high-dimensional image data.
New methods tackle adversarial attacks on categorical sequences, improving model security.
problem Adversarial attacks on categorical sequence models, especially for money transactions and medical fraud.
method Two black-box adversarial attacks: Monte-Carlo and continuous relaxation methods.
result Generated adversarial sequences fool machine learning models but remain close to original ones.
Convolutional neural network (CNN) is a neural network that can make use of the internal structure of data such as the 2D structure of image data. This paper studies CNN on text categorization to exploit the 1D structure (namely, word order) of text data for accurate prediction. Instead of using low-dimensional word ve…
L*ReLU improves deep learning for fine-grained image classification.
problem Fine-grained image classification requires specific AFs.
method Proposes L*ReLU, piece-wise linear AFs for deep learning.
result L*ReLU achieves superior results on FGVC datasets.
In this paper we present a method for learning a discriminative classifier from unlabeled or partially labeled data. Our approach is based on an objective function that trades-off mutual information between observed examples and their predicted categorical class distribution, against robustness of the classifier to an …
Differentiable language model attacks improve adversarial examples for categorical sequence classifiers.
problem Challenges in adversarial attacks for categorical sequence models due to non-differentiability.
method Fine-tuning a language model as a generator of adversarial examples, using a differentiable loss function that combines a surrogate classifier score and approximate edit distance.
result Semantically better and more resistant adversarial examples.
Logistic LDA applies LDA to non-categorical data.
problem Applying LDA to non-categorical data is challenging.
method Logistic LDA, a discriminative variant of LDA.
result Logistic LDA can learn from unlabeled data.
Deep learning improves medical ultrasound image segmentation accuracy.
problem Improving accuracy in medical ultrasound image segmentation.
method Categorizes deep learning methods into six groups and analyzes current representative algorithms.
result Current methods show significant improvement in image segmentation accuracy.
Adaptive correlated MC improves sequence generation stability.
problem High gradient variance in reinforcement learning for sequence generation.
method Adapts policy gradient estimator using correlated Monte Carlo rollouts.
result Reduces gradient variance and improves model performance.
New near-metrics capture similarity for diverse data types.
problem Measuring similarity across different data types and forms.
method Local graph diffusion to create quasi-metrics without metric axioms.
result Near-metrics perform well for various data types, especially for categorical and continuous data.
This paper addresses image classification through learning a compact and discriminative dictionary efficiently. Given a structured dictionary with each atom (columns in the dictionary matrix) related to some label, we propose cross-label suppression constraint to enlarge the difference among representations for differe…
A new method measures heterogeneity without needing categorical partitioning or distance measurement.
problem Measuring heterogeneity in non-categorical data requires categorical partitioning and distance measurement, limiting applicability.
method Representational Rényi heterogeneity (RRH) transforms data into a latent space where heterogeneity can be measured without these requirements.
result RRH can generalize existing indices and better responds to changes in mixture component separation and weighting.
Deep learning solves imaging inverse problems without ground truth.
problem Solving imaging problems without perfect data.
method Taxonomy of deep learning approaches for imaging inverse problems.
result Trade-offs and failure modes identified for different methods.
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.
Image classification system identifies bumble bee species from images.
problem Manual identification of bumble bee species is time-consuming and requires expert knowledge.
method Transfer learning using Inception, VGG16, VGG19, and ResNet models.
result Inception and VGG classifiers achieved up to 23% accuracy for single species identification.
A neural model samples arbitrary features conditioned on some inputs.
problem Sampling arbitrary features conditioned on some inputs.
method Variational autoencoder with stochastic variational Bayes training.
result Effectiveness and diversity of generated samples on synthetic data and feature problems.
GANs improve medical image analysis through de-noising, segmentation, and data synthesis.
problem Chronic scarcity of labeled medical images.
method Generative Adversarial Networks (GANs) and their extensions.
result GANs can synthesize realistic medical images to address data scarcity.
In this article, we give a survey of Geometric Invariant Theory for Toric Varieties, and present an application to the Einstein-Weyl Geometry. We compute the image of the Minitwistor space of the Honda metrics as a categorical quotient according to the most efficient linearization. The result is the complex weighted pr…
Project uses GANs to recognize facial expressions and emotions from-the-wild with dual model approach.
problem Facial expression and emotion recognition in real-world scenarios.
method Created a dual GAN model architecture for Action Units and Valence Arousal annotations.
result Dual GAN model achieved better results than single model for emotion recognition.
A new text classification method using separable convolution reduces memory consumption.
problem Manual categorization of documents is inefficient and resource-intensive.
method Introducing a new architecture based on separable convolution for text classification.
result Achieved a drastic reduction in trainable parameters without compromising accuracy.
FIGR generates novel images with minimal data using meta-learning.
problem GANs require large datasets for generating realistic images.
method Meta-trained GAN (Reptile) on few images.
result Generates novel images with as few as 4 images per class.
New method uses GAN to efficiently simulate geologic media.
problem Computational infeasibility of probabilistic inversion for high-dimensional problems.
method Spatial Generative Adversarial Network (SGAN) for geostatistical simulation.
result SGAN enables fast generation of geostatistical realizations for efficient inversion.
StructureBoost improves gradient boosting for complex categorical variables efficiently.
problem Efficiently handling complex categorical variables with known structure.
method Two methods to overcome computational obstacles in SCDT enumeration for structured categorical variables.
result StructureBoost outperforms existing packages on complex categorical problems.
SimLoss improves classification by considering class similarities.
problem Equal punishment of all misclassifications in CCE.
method Integrates class similarities into Categorical Cross Entropy using matrices constructed from task-specific knowledge.
result Significant improvements over CCE on Age Estimation and Image Classification.
Categorical bundles provide a natural framework for gauge theories involving multiple gauge groups. Unlike the case of traditional bundles there are distinct notions of triviality, and hence also of local triviality, for categorical bundles. We study categorical principal bundles that are product bundles in the categor…
Bayesian model improves categorization of explosions from sparse data.
problem Challenges in categorizing explosions from limited data.
method Bayesian update to Event Categorization Matrix model with Bayesian Decision Theory.
result Consistent gains in overall accuracy and lower false negative rates.
Bayesian deep learning uses function-space priors to improve model uncertainty and robustness.
problem Bayesian deep learning struggles with model-specific weight-space priors that are hard to interpret and specify.
method Apply a Dirichlet prior in predictive space and perform approximate function-space variational inference.
result The approach improves uncertainty quantification, scalability, and adversarial robustness in large-scale image classification.
FigureNet learns to answer questions about scientific plots.
problem Addressing reasoning tasks in question-answering on scientific plots.
method Introduces FigureNet, a deep learning model that identifies plot elements, quantifies values, and determines relative ordering.
result FigureNet outperforms state-of-the-art models by 7% on the FigureQA dataset.
SFM matches flows on statistical manifolds for better discrete generation.
problem Discrete generation on statistical manifolds with strong prior assumptions.
method Statistical Flow Matching (SFM) on manifold of categorical distributions using Fisher information metric.
result SFM achieves higher sampling quality and likelihood than other models.
UNTIE learns representations of coupled categorical data.
problem Challenges in learning from unlabeled categorical data with complex couplings.
method UNTIE approach for unsupervised representation learning of heterogeneous couplings.
result UNTIE significantly improves categorical data representations on 25 diverse datasets.
Paper introduces Categorical Normalizing Flows for better handling of categorical data.
problem Limited application of normalizing flows on categorical data due to lack of intrinsic order.
method Categorical Normalizing Flows use continuous transformations to model latent relations in categorical data, optimizing both continuous representation and model likelihood.
result GraphCNF, a permutation-invariant generative model, outperforms state-of-the-art on molecule generation.
Authors conjecture categorically diagonalizable complex for full twists.
problem Categorically diagonalizing the complex of Soergel bimodules for full twists.
method Utilizes categorical diagonalization theory.
result Proves conjecture in type A, categorifies Young idempotents.