Traditional nearest points methods use all the samples in an image set to construct a single convex or affine hull model for classification. However, strong artificial features and noisy data may be generated from combinations of training samples when significant intra-class variations and/or noise occur in the image s…
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.
169,291 papers · 148 categories
Trend · papers per month
48 results for “image-set classification”
A method classifies image-sets using convex cones based on CNN features.
problem Image-set classification using CNN features.
method Modeling CNN features as convex cones and measuring geometric similarity.
result Enhanced classification through discriminant space maximization of between-class variance.
Modeling videos and image-sets as linear subspaces has proven beneficial for many visual recognition tasks. However, it also incurs challenges arising from the fact that linear subspaces do not obey Euclidean geometry, but lie on a special type of Riemannian manifolds known as Grassmannian. To leverage the techniques d…
Proposes a general deep neural network method for digital watermarking.
problem Protecting intellectual content in a massive, IoT-acquired image dataset.
method Train a neural network on an image set and use it to protect distinct test images in bulk.
result Demonstrates the robustness and practicality of the proposed method.
This study investigates how much knowledge from natural images can be transferred to pathology images.
problem Quantifying how much knowledge from natural images can be transferred to pathology images.
method Proposes a framework to quantify knowledge gain by a particular layer, conducts empirical investigation in pathology image centered transfer learning.
result Early layers of deep models can transfer knowledge to pathology image classification tasks.
Generative model learns to autoencode and generate sets of images.
problem Learning to represent and generate sets of images with unknown number of sets.
method Set Distribution Networks (SDNs) learn set encoder, discriminator, generator, and prior.
result SDNs can reconstruct and generate sets of images with preserved attributes.
We present a new, fully generative model of optical telescope image sets, along with a variational procedure for inference. Each pixel intensity is treated as a Poisson random variable, with a rate parameter dependent on latent properties of stars and galaxies. Key latent properties are themselves random, with scientif…
A new method compares image classifiers using adaptive sampling of natural images.
problem Evaluation of image classifiers on small, fixed test sets may not generalize to real-world images.
method Adaptive sampling from a large corpus of unlabeled images to maximize classifier discrepancies measured by WordNet hierarchy.
result Human labeling of model-dependent image sets reveals relative classifier performance.
Randomized fiber projections enhance neural network accuracy.
problem Improving neural network performance with limited resources.
method Training neural networks on randomized speckled images from multi-mode fiber projectors.
result Classification accuracy is higher with randomized fiber data than with direct images.
FlowScan models exchangeable data sets with flexible flow transformations.
problem Density estimation for exchangeable, non-i.i.d. data.
method Combines invertible flow transformations with a sorted scan.
result Achieves new state-of-the-art performance on point cloud and image set modeling.
Independent component analysis (ICA), as an approach to the blind source-separation (BSS) problem, has become the de-facto standard in many medical imaging settings. Despite successes and a large ongoing research effort, the limitation of ICA to square linear transformations have not been overcome, so that general INFO…
System optimizes product images for e-commerce, enhancing customer engagement.
problem Optimizing product images for e-commerce to improve customer engagement.
method Machine learning, deep learning, and computer vision techniques applied to large e-commerce catalogs.
result System produces superior image sets tailored to customer preferences.
Automates malaria diagnosis with a motorized microscope and clustering algorithm.
problem Late or inaccurate diagnosis of malaria leading to high mortality.
method Developed a motorized microscope and a patch-based unsupervised clustering algorithm.
result The method provides better robustness against different imaging conditions and comparable accuracy to supervised systems.
The paper uses CNNs to classify road conditions in real-time.
problem Classifying road conditions in real-time using images from cameras across North America.
method Used state-of-the-art convolutional neural networks (VGG-16, ResNet50, Xception, InceptionResNetV2, EfficientNet-B0 and EfficientNet-B4) to classify images by road condition.
result EfficientNet-B4 framework achieved validation accuracy of 90.6% in real-time map building.
Unified deep learning predicts Parkinson's disease from medical images.
problem Diagnosing Parkinson's disease accurately from medical images.
method Transfer learning and domain adaptation using deep convolutional and recurrent neural networks.
result The approach effectively predicts Parkinson's disease across different medical environments.
Study on unimodality of plucking polynomial with delay function.
problem Exploring unimodality of plucking polynomial with delay function.
method Presented a formula for the plucking polynomial of hedgehog rooted trees and explored unimodality with specific delay functions.
result Found interesting examples and speculations on unimodality of plucking polynomials with delay functions.
New model constructs astronomical catalogs from images efficiently.
problem Building accurate catalogs from large image datasets.
method Generative model with MCMC and VI for inference.
result Variational inference is 1000x faster with similar accuracy.
New spectral signatures help detect and remove backdoor attacks.
problem Backdoor attacks that evade typical detection.
method Identified spectral signatures and used robust statistics.
result Demonstrated effectiveness in removing poisoned examples.
Universal MLPs with a single hidden layer can learn any function.
problem Learning on various data structures like sequences, images, sets, and graphs.
method Using group theory, the paper proves the universality of a broad class of equivariant MLPs with a single hidden layer.
result Having a hidden layer on which the group acts regularly is sufficient for universal equivariance (invariance).
An Infinite Parade of Giraffes: Expressive Augmentation and Complexity Layers for Cartoon Drawingcs.GR
Paper generates cartoon giraffes from few original drawings.
problem Creating consistent cartoon sketches with limited data.
method Expressive augmentations and GANs trained on complexity layers.
result Generated sketches are consistent with designer's style.
Distributed Robust Learningstat.ML
We propose a framework for distributed robust statistical learning on {\em big contaminated data}. The Distributed Robust Learning (DRL) framework can reduce the computational time of traditional robust learning methods by several orders of magnitude. We analyze the robustness property of DRL, showing that DRL not only…
Develops a method for manifold learning with small sample size datasets.
problem Improving manifold learning performance for multiple tasks with limited samples.
method Uses instance and model transfer to integrate manifold models from similar tasks.
result Successfully estimates manifolds with tiny sample sizes across multiple tasks.
Develops spatial uncertainty guarantees for image segmentation models.
problem Ensuring reliable segmentation predictions for biomedical images.
method Adapting conformal inference to imaging, using transformed logit scores and calibration datasets.
result Confidence sets provide spatial uncertainty guarantees with desired probability.
MAGIC generates image collages from set templates using attention and set representations.
problem Generating image collages from set templates is challenging for classical models.
method Memory Attentive Generation of Image Collages (MAGIC) using Set-Transformer layers and set-pooling.
result MAGIC can generate image collages from set templates in one forward pass.
CrossNet uses cross-consistency to improve unpaired image translation.
problem Image-to-image translation without paired data.
method Introduced a novel architecture with cross-translators and latent cross-consistency constraints.
result CrossNet outperforms state-of-the-art on various image translation tasks.
Method learns to synthesize eye fundus images from vessel trees.
problem Synthesizing images of the eye fundus is challenging.
method Adversarial learning technique to map vessel trees to retinal images.
result Synthetic images retain high quality of true images.
Few-Shot Diffusion Models generate new samples from small image sets.
problem Generating new samples from a few images.
method Conditional Denoising Diffusion Probabilistic Models (DDPM) with patch-based input set information.
result FSDM can generate samples from previously unseen classes conditioned on as few as 5 samples.
In this paper we establish the basic tools to develop the "Calculus" associated with group-valued continuously Pansu differentiable mappings. We develop the technical machinery on which all of our results rely. In particular, the linearization of addends appearing in the Baker-Campbell-Hausdorff formula is one of the m…
This paper proposes a technique to prioritize examples based on their noise sensitivity for generating adversarial examples.
problem Generating effective adversarial examples requires careful consideration of noise sensitivity.
method The paper introduces a noise-sensitivity-analysis-based test prioritization technique to identify examples sensitive to noise.
result The method effectively picks out examples by their noise sensitivity, improving the effectiveness of adversarial examples.
Improved SVMs learn from few samples with composition and multiple scales.
problem Learning with small sample sizes.
method Transformation-invariant SVMs with composition and locality at multiple scales.
result Kernels based on maximum similarity are positive definite and yield superior accuracy.
Exact inversion of deep ReLU models is possible for single layers and with high probability for deep models.
problem Inverting deep generative models with ReLU activations.
method Theoretical analysis and algorithms for exact inversion of single and multiple layers of deep generative models.
result Exact recovery of latent codes is possible for single layers and with high probability for deep models, under certain conditions.
A new method learns continuous guidance weights to improve diffusion model quality and distributional alignment.
problem Improving perceptual quality and distributional alignment of samples from conditional diffusion models.
method Learned continuous guidance weights are used to minimize distributional mismatch and reward guided sampling.
result Improvements in Fréchet inception distance (FID) for image generation and better image-prompt alignment in text-to-image applications.
Characterizes invariant and equivariant linear layers for graphs.
problem Maximal collection of invariant and equivariant linear layers for graphs.
method Characterization of all permutation invariant and equivariant linear layers for graphs.
result Dimension of linear layers for edge-value graph data is 2 and for k-tuples of nodes, it is the k-th and 2k-th Bell numbers.
SUPER learning combines supervised and unsupervised methods for LDCT image reconstruction.
problem Low-dose CT image reconstruction challenges.
method Combines supervised and unsupervised learning methods.
result SUPER learning dramatically outperforms constituent methods.
A novel generative encoder model for imaging and image processing.
problem Efficiently processing and recovering images with noise.
method A pre-training phase with a GAN and an AE, followed by an optimization phase.
result The GE model outperforms state-of-the-art algorithms in image recovery.
New criteria for ideal circle patterns on surfaces.
problem Determining when a surface supports ideal circle patterns.
method Introducing a character and using combinatorial Ricci flows.
result Simpler and more easily verifiable criteria for ideal circle patterns.
Experiments that study neural encoding of stimuli at the level of individual neurons typically choose a small set of features present in the world --- contrast and luminance for vision, pitch and intensity for sound --- and assemble a stimulus set that systematically varies along these dimensions. Subsequent analysis o…
New approach corrects image bias without labels.
problem Image search results skew towards majority groups.
method Uses visibly diverse control set to select images.
result Significantly improves visible diversity of results.
Paper presents a new framework for sequence classification.
problem Sequence classification in real-world applications.
method Reference-based sequence classification framework.
result New sequence classification algorithms achieve comparable accuracy.
Dual-stage sEMG classification improves gesture recognition accuracy.
problem Improving accuracy in hand gesture recognition from sEMG signals.
method Dual-stage classification approach: first stage groups similar activities, second stage classifies within groups.
result Dual-stage classification yields significantly higher accuracy than single-stage approach.
A novel method for classification with rejection using ensemble of cost-sensitive classifiers.
problem Avoid risky misclassification in error-critical applications.
method Learning an ensemble of cost-sensitive classifiers.
result Improved classification accuracy and flexibility in loss selection.
Multi-borders classificationstat.ML
The number of possible methods of generalizing binary classification to multi-class classification increases exponentially with the number of class labels. Often, the best method of doing so will be highly problem dependent. Here we present classification software in which the partitioning of multi-class classification…
Few-shot image classification is improved by correcting CNNs' texture bias.
problem Few-shot image classification performance is hindered by CNNs' texture bias.
method Corrected CNNs' texture bias using a simpler method than state-of-the-art approaches.
result State-of-the-art performance on miniImageNet task achieved.
Paper introduces LPCs for robust classification with performance bounds.
problem Conventional classification techniques constrain rules and use surrogate losses.
method Robust risk minimization (RRM) for unconstrained classification rules, optimizing 0-1 loss.
result LPCs provide performance bounds and competitive performance with state-of-the-art techniques.
New NHCAs improve multi-category classification efficiency.
problem Efficient multi-category classification for real-world problems.
method Twin SVM (TWSVM), Generalized eigenvalue proximal SVM (GEPSVM), Regularized GEPSVM (RegGEPSVM), and Improved GEPSVM (IGEPSVM) with OAA, BT, and TDS approaches.
result TDS-TWSVM outperforms other methods in classification accuracy.
Paper compares XGB and BPNN for music style classification.
problem Efficient music style classification using different methods.
method Feature extraction for timbral texture, rhythmic content, and pitch content; comparative evaluation of XGB and BPNN.
result XGB outperforms BPNN for small datasets in music classification.
Deep reinforcement learning improves classification accuracy for imbalanced datasets.
problem Imbalanced datasets challenge conventional classification algorithms.
method Formulated as a sequential decision-making process, solved using deep Q-learning network.
result Proposed model outperforms other imbalanced classification algorithms.
Classifies Lie algebra realizations by vector fields.
problem Classifying Lie algebra realizations by vector fields.
method Generalized correspondence between classification of transitive local realizations and subalgebras, formulated a reasonable classification problem, presented an algorithm for construction.
result Algorithm for constructing classification of general realizations.