Research
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.

169,181 papers · 148 categories

Trend · papers per month

36811 · Jul 201919922001200920182026
48 results for deconvolutional capsules

New γγ-capsule networks improve adversarial robustness and explainability of capsule networks.

problem Improving the robustness and explainability of capsule networks.
method Introducing γγ-capsule networks with a new routing algorithm and training method.
result Experimental results show γγ-capsule networks are more robust and transparent.

A method improves capsule networks by reducing information dilution and enhancing performance.

problem Capsule networks struggle with datasets containing background and complex objects.
method Restrict the activation values of primary capsule layers to highlight discriminative capsules.
result The method achieves better performance on various datasets.

An unsupervised learning algorithm trains capsule networks for generating realistic images.

problem Training capsule networks for generating realistic images without labeled data.
method Developed an unsupervised learning algorithm using dynamic routing and an energy function for capsule networks.
result The algorithm successfully generates realistic looking images from a learned distribution.

Capsule networks can only represent symmetric functions due to routing limitations.

problem Capsule networks' expressivity is limited to symmetric functions.
method Proved and empirically demonstrated that EM-routing and routing-by-agreement prevent capsule networks from distinguishing inputs and their negative counterpart.
result Capsule networks are not universal approximators due to the limitation of expressivity.

A new capsule routing algorithm derived from Variational Bayes improves performance in neural networks.

problem Improving performance of capsule networks in recognizing objects and their parts.
method Proposed a new capsule routing algorithm derived from Variational Bayes to fit a mixture of transforming gaussians.
result Significant improvement in MNIST to affNIST generalization over previous works.

Capsule networks improve on traditional neural networks by using vector activations.

problem Comparing capsule networks to traditional neural networks to validate their benefits.
method Deep visualization analysis, feature encoding across vector components, and instantiation parameter encoding.
result Capsule features encode information differently and provide benefits in computer vision applications.

Capsule networks are vulnerable to adversarial attacks, similar to convolutional neural networks.

problem Vulnerability of capsule networks to adversarial attacks.
method Compared capsule networks to convolutional neural networks using various adversarial attacks.
result Capsule networks are vulnerable to adversarial attacks, similar to convolutional neural networks.

Researchers share pitfalls and improvements in implementing Hinton's capsule network.

problem Implementation pitfalls in Hinton's capsule network hindered progress in the field.
method Identifying and addressing common mistakes in capsule network implementations.
result Improved implementation of Hinton's capsule network outperforms existing open-source implementations.

Capsule Networks classify RAS protein structures with GPU acceleration.

problem Classifying RAS protein structures accurately and interpretably.
method Implemented Capsule Network architecture trained on 2D and 3D structural encodings.
result Capsule Network outperforms traditional CNNs in accuracy and interpretability.

A new capsule network framework that preserves input transformations.

problem Inefficiency in learning part-whole relationships and lack of equivariance guarantees in capsule networks.
method Proposes a new capsule network framework that learns to projectively encode pose-variations for every capsule-type of each layer using a trainable, equivariant function over a grid of group-transformations.
result The proposed framework is equivariant and preserves the compositional representation of an input under transformations.

Capsule networks improve performance on image classification tasks with fewer parameters.

problem Improving performance of capsule networks with fewer parameters.
method Inverted dot-product attention routing, Layer Normalization, concurrent iterative routing.
result Improves performance on benchmark datasets CIFAR-10 and CIFAR-100, and performs at-par with ResNet-18.

Capsule networks improve temporal data understanding, achieving 96.21% ECG accuracy.

problem Improving temporal data understanding with capsule networks.
method Generated capsules along temporal and channel dimensions, learning contrasting relationships.
result Achieved 96.21% accuracy on ECG signal beat categories, surpassing state-of-the-art.

Capsule models detect adversarial images by reconstructing from top-level capsules.

problem Detecting adversarial images that look like a typical member of the predicted class.
method Capsule models trained to reconstruct images from pose parameters and identity of the correct top-level capsule.
result Setting a threshold on reconstruction error effectively detects adversarial images.

Stacked Capsule Autoencoders reconstruct objects from images using part relationships.

problem Reconstructing objects from images with robustness to viewpoint changes.
method Two-stage unsupervised capsule autoencoder that predicts part templates and object capsules.
result State-of-the-art results for unsupervised classification on SVHN and MNIST.

CapsAttacks study imperceptible adversarial attacks on Capsule Networks, showing they can fool these networks.

problem Vulnerability of Capsule Networks to imperceptible adversarial attacks.
method Proposed a greedy algorithm for generating targeted imperceptible adversarial examples.
result Capsule Networks can be fooled by imperceptible adversarial attacks, similar to CNNs.

Project learns to model Capsule Networks' routing procedures for better expressiveness.

problem Limited expressiveness of Capsule Networks' inner routing procedures.
method Proposes two ways to learn the routing procedure as a network parameter.
result Improved expressiveness of Capsule Networks through learned routing procedures.

Capsule network improves handwriting recognition of historical graffiti.

problem Recognizing historical graffiti letters carved on stone walls.
method Used capsule deep neural network on a challenging dataset of 4000 images of 34 letters.
result Validation accuracy and AUC values were significantly higher for capsule network than for CNN.

CapsuleGAN uses capsule networks in GANs for better image data modeling.

problem Improving image data modeling in GANs.
method CapsuleGAN uses capsule networks as discriminators in GANs, with a new objective function incorporating margin loss.
result CapsuleGAN outperforms standard GANs on image data modeling and semi-supervised classification.

Capsule models enforce object pose relationships for robustness, explored with probabilistic generative and variational methods.

problem Enforcing object pose relationships for robustness to viewpoint changes.
method Probabilistic generative model with variational bound, exploring capsule assumptions and inference mechanisms.
result Unified objective and test time optimisation demonstrated for capsule models.

X-Caps improves medical diagnosis explainability by encoding visual attributes in capsules.

problem Uninterpretable predictions from deep neural networks in healthcare.
method Teaches a novel multi-task capsule network to encode high-level visual attributes and malignancy scores.
result X-Caps outperforms state-of-the-art deep dense 3D CNNs in capturing visually interpretable attributes and malignancy prediction.

Capsule networks improve at detecting changes in compositionality with routing.

problem Capsule networks struggle with detecting changes in compositionality.
method Introduced a loss function based on routing entropy to improve compositionality.
result Capsule networks with the new loss function better detect changes in compositionality.

Method screens similar capsule endoscopic images, reducing doctor workload and improving accuracy.

problem Time-consuming and high error rate in manual inspection of large numbers of similar capsule endoscopic images.
method Structural similarity analysis of visually salient areas and hierarchical clustering.
result 76% reduction in similar images, 100% lesion recall, 18-minute average play time.

PathCapsNet improves CapsNet by reducing parameters and enhancing performance.

problem Limitations of CapsNet, including excessive parameters and shallow architecture.
method Introducing a deep parallel multi-path version of CapsNet, incorporating depth, max-pooling, regularization, and new routing techniques.
result Better or comparable results to CapsNet with significantly reduced parameter count.

Paper proposes a capsule attention mechanism for EEG-EOG vigilance estimation.

problem Driver vigilance estimation for safer transportation.
method Capsule attention mechanism following LSTM network for multimodal EEG-EOG analysis.
result Capsule attention improves vigilance estimation robustness and accuracy.

Proposes GANs using Capsule Networks for faster image synthesis.

problem Faster image synthesis with fewer training samples and epochs.
method Capsule Networks for image synthesis using GAN architectures.
result Learn data manifold faster and synthesize visually accurate images.

Capsule networks improve classification accuracy on complex data.

problem CNN's failure to account for spatial hierarchies and lack of rotational invariance.
method Dynamic routing and reconstruction regularization to create capsules that are both rotation invariant and spatially aware.
result Capsule networks achieve a state-of-the-art 0.25% test error on MNIST without data augmentation.

Deconvolutional layers have been widely used in a variety of deep models for up-sampling, including encoder-decoder networks for semantic segmentation and deep generative models for unsupervised learning. One of the key limitations of deconvolutional operations is that they result in the so-called checkerboard problem.…

2017-05-18abs ↗pdf ↗

Bayesian framework integrates spectral deconvolution with expert reasoning for robust peak estimation.

problem Challenges in extracting meaningful peaks from noisy or complex spectra.
method Bayesian spectral deconvolution coupled with a physical-property regression layer.
result Recovery of weak peaks in poly(lactic acid) IR spectra related to degradation rates.