Tricks improve retail product image classification accuracy.
problem Retail Product Image Classification
method Various tricks including a new LCA layer, Instagram-pretrained Convnet, and Maximum Entropy loss.
result Increased accuracy of fine-tuned convnets by a large margin.
Examines how irreducibility and rigidity affect digital images.
problem Understanding interactions between irreducibility and rigidity in digital images.
method Analyzes Cartesian products, wedges, and cold and freezing sets.
result Interactions between irreducibility and rigidity in digital images.
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.
Proves elliptic operator images are closed on Hilbert bundles.
problem Closedness of images of elliptic operators on Hilbert bundles.
method Analyzes tensor product of elliptic operators and compares images.
result Establishes closedness of images with respect to natural topology.
A parallel algorithm learns efficient Kronecker product dictionaries.
problem Sparse representation of 2D signals like images and hyperspectral data.
method Highly parallelizable algorithm for learning separable dictionaries.
result Competitive sparse representations at lower computational cost.
Large dataset of e-retailer images for improving visual search and product classification.
problem Improving the relevancy of visual search and product recommendation systems.
method Sharing a large dataset of 12M images from an online store classified into 5K categories.
result Demonstrates the effectiveness of deep learning in image classification.
Digital trees have approximate fixed point property, and conditions for products are explored.
problem Conditions for the approximate fixed point property in digital tree products.
method Analyzes digital trees and their products, explores conditions for the AFPP.
result Conditions are found for the AFPP in digital tree products.
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.
We study properties of Cartesian products of digital images, using a variety of adjacencies that have appeared in the literature.
DGC-SPNs improve SPNs for image data by combining CNNs and SPNs.
problem SPNs struggle with complex spatial relationships in images.
method Integrates CNNs with SPNs, using novel parameterization for dilations and strides.
result Significantly improved feature coverage and resolution compared to existing SPN architectures.
New model uses PEPS for image classification, outperforming tree-like networks.
problem Efficiently modeling and classifying 2D data like images.
method Feature map followed by PEPS contraction with trainable parameters.
result Significantly superior to tree-like networks on MNIST and Fashion-MNIST.
Paper proposes a new method to optimize feature coordinates for better image classification.
problem Improving feature extraction for better machine learning classification.
method Mutual-energy inner product optimization method.
result The method enhances low-frequency features and suppresses high-frequency noise, leading to better classification results.
Paper develops SKPD framework for signal region detection in image regression.
problem Limited research on image region detection in high-resolution image regression.
method Sparse Kronecker Product Decomposition (SKPD) framework for matrices and tensors.
result Computed solutions converge to truth with guaranteed consistency.
A new tensor network method for image classification reduces computation cost.
problem Efficiently classifying images in high-dimensional spaces.
method Proposes a multi-layered tensor network (MLTN) that performs one MPS operation per layer, reducing computation cost.
result Reduces computation cost without degrading performance.
TensorNetwork boosts image classification accuracy.
problem Improving image classification accuracy.
method Encoding images into matrix product states and using tensor network contraction.
result 98% and 88% accuracy on MNIST and Fashion-MNIST datasets respectively.
Unified product embeddings improve cross-task performance in e-commerce.
problem Training product embeddings in isolation limits cross-task performance.
method Combining text, clickstream, and image data using denoising auto-encoders, BPR, and Siamese neural networks.
result Unified product embeddings uniformly outperform isolated embeddings across three e-commerce tasks.
Quaternion CNN outperforms traditional CNN in color image reconstruction.
problem Efficient image processing with small or heterogeneous datasets.
method Introducing quaternion-valued convolutional neural networks (QCNN) to learn internal and external relations.
result QCAE outperforms CAE in reconstructing unseen color images.
PoGDiff improves diffusion models on imbalanced datasets.
problem Diffusion models struggle with imbalanced text-image pairs.
method PoGDiff replaces ground-truth with a Product of Gaussians.
result PoGDiff enhances generation accuracy and quality on imbalanced datasets.
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. We present Fashion-MNIST, a new dataset comprising of 28x28 grayscale images of 70,000 fashion products from 10 categories, with 7,000 images per category. The training set has 60,000 images and the test set has 10,000 images. Fashion-MNIST is intended to serve as a direct drop-in replacement for the original MNIST dat…
We show that a compact n-polyhedron PL embeds in a product of n trees if and only if it collapses onto an (n-1)-polyhedron. If the n-polyhedron is contractible and n\ne 3 (or n=3 and the Andrews-Curtis Conjecture holds), the product of trees may be assumed to collapse onto the image of the embedding. In contrast, there…
Unified sampling approach for Bayesian imaging problems.
problem Sampling from complex prior and posterior distributions in Bayesian imaging.
method Gaussian latent machine model for efficient prior and posterior sampling.
result Unified and generalized sampling algorithms for various imaging problems.
Personalizes query completion in digital commerce with image-based vectors.
problem High bounce rate and low recurring users in query completion.
method Injects dense vectors from product images into a noisy channel model.
result Image-based personalization improves query completion and user experience.
Study mean curvature flow solitons in warped products and Riemannian manifolds.
problem Properties of mean curvature flow solitons in warped products and Riemannian manifolds.
method Analysis of splitting and rigidity results under various geometric conditions.
result Rigidity results for solitons in constant curvature and Schwarzschild type spaces.
Malware authors have always been at an advantage of being able to adversarially test and augment their malicious code, before deploying the payload, using anti-malware products at their disposal. The anti-malware developers and threat experts, on the other hand, do not have such a privilege of tuning anti-malware produ…
Additive decoders tackle latent variables and image generation.
problem Latent variables identification and out-of-support image generation in representation learning.
method Additive decoders that can identify latent variables up to permutation and block-wise invertible transformations, and generate novel images by recombining observed factors.
result Additive decoders provide a new setting for nonlinear independent component analysis and can generate novel images by recombining observed factors.
Study embeddings of free group products into automorphism groups.
problem Embeddings of direct products of free groups into automorphism groups.
method Proved existence of canonical fixed points in the boundary of Outer space.
result Complete description of embeddings of direct products of free groups.
Classifies smooth manifolds homotopy equivalent to sphere products
problem Classifying smooth manifolds homotopy equivalent to sphere products
method Using normal-invariant map and explicit families of manifolds
result Classifies smooth manifolds up to almost diffeomorphism
ProductNet curates high-quality product datasets for better product understanding.
problem Lack of high-quality product datasets for product representation learning.
method Curated high-quality product datasets with a multi-modal deep neural network and active learning.
result Master model yields high categorization accuracy (94.7% top-1 accuracy for 1240 classes).
Author defines products of elements in cobordism-like modules induced from generic maps.
problem Generalizing cobordism modules for negative codimension generic maps.
method Defining products for pairs of elements in cobordism-like modules.
result Suitable elements for products defined in cobordism-like modules.
We study smooth complex hypersurfaces in direct products of closed hyperbolic Riemann surfaces and give a classification in terms of their fundamental groups. This answers a question of Delzant and Gromov on subvarieties of products of Riemann surfaces in the smooth codimension one case. We also answer Delzant and Grom…
Tensor networks improve generative modeling of natural images.
problem Exponential decay of correlation in Matrix Product States limits their use for complex data.
method Introduced Tree Tensor Networks (TTN) for 2D data, developed efficient learning and sampling algorithms.
result TTN outperforms Matrix Product States in keeping pixel correlations and log-likelihood scores.
Ano-SuPs detects anomalies in images of manufactured products by identifying suspected patches.
problem Challenges in detecting anomalies in image-based manufacturing systems, including complexity of background and various anomaly patterns.
method Two-stage strategy anomaly detection method: first, remove suspected patches; second, refine anomaly identification using normal patches.
result Demonstrated effectiveness through simulation and case studies, identifying key parameters and steps impacting model performance and efficiency.
In this paper, we tackle the problem of explanations in a deep-learning based model for recommendations by leveraging the technique of layer-wise relevance propagation. We use a Deep Convolutional Neural Network to extract relevant features from the input images before identifying similarity between the images in featu…
Method retrieves similar fashion items from images and text, enabling style refinement.
problem Lack of intuitive, interactive refinement in search engines for fashion items.
method Joint visual-textual embedding training, Mini-Batch Match Retrieval, attribute extraction.
result Improved performance in multimodal style search, demonstrated through benchmark.
Vector-valued neural learning has emerged as a promising direction in deep learning recently. Traditionally, training data for neural networks (NNs) are formulated as a vector of scalars; however, its performance may not be optimal since associations among adjacent scalars are not modeled. In this paper, we propose a n…
Generative Adversarial Networks optimize model parameters for image matching.
problem Optimizing model parameters for accurate image matching.
method Model-Assisted Generative Adversarial Network (GAN) to produce fake images matching true images.
result Best match model parameter values can minimize bias in image recognition.
Johnson has defined a surjective homomorphism from the Torelli subgroup of the mapping class group of the surface of genus g with one boundary component to ∧3H, the third exterior product of the homology of the surface. Morita then extended Johnson's homomorphism to a homomorphism from the entire mapping cla…
Active learning improves inspection systems by using weakly labeled data.
problem Rapidly updating machine vision inspection systems in evolving manufacturing processes.
method Developed a methodology for active learning from weakly labeled data, addressing covariate shift with domain-adversarial training.
result Demonstrated that active learning can accelerate the annotation process and reduce false positives.
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.
Product Kanerva Machines dynamically combine smaller models for better memory organization.
problem Limited organization in the Kanerva Machine.
method Introducing Product Kanerva Machines that dynamically combine multiple smaller Kanerva Machines.
result Product Kanerva Machines can discover spatial tunings that approximately factorize simple images by object.
Study curvature of direct image bundles in deformations of maps.
problem Understanding curvature in deformations of maps with fixed targets.
method Analyzing curvature of direct image bundles related to deformation data.
result Proved seminegativity for a vector bundle of relative forms.
GANs predict injection molding parts geometry from hot parts images.
problem Predicting final part geometry from early-stage measurements in injection molding.
method Used pix2pix GAN architecture to translate thermographic images to geometry.
result DMD analysis of GAN predictions reveals geometrical parameters.
LMConv improves autoregressive models for image generation and completion.
problem Limited generation order in autoregressive models restricts their applicability.
method Introduces LMConv, a modified 2D convolution that allows arbitrary masks to be applied to weights.
result LMConv achieves improved performance on image density estimation and coherent completions.
DKN adapts to medical imaging data with limited samples and interpretable models.
problem Medical imaging data's unique nature makes general methods like CNN unsuitable.
method DKN uses a Kronecker product structure to adapt to low sample size and provide interpretable models.
result DKN achieves prediction power comparable to CNN and provides model interpretability.
AI-enhanced product embeddings boost demand analysis accuracy.
problem Traditional demand analysis struggles with nuanced product attributes.
method Combining text, images, and tabular data with transformer embeddings for causal inference.
result AI-enhanced embeddings improve sales rank and price predictions.
Researchers enhance hyperspherical latent representations for higher-dimensional data.
problem Limited expressivity of hyperspherical vMF distribution in high dimensions.
method Use a product-space to extend hyperspherical parameterizations to higher dimensions.
result Improved results on image datasets compared to traditional methods.
Linear classifiers in product space forms improve scRNA-seq data classification.
problem Linear classification in products of Euclidean, spherical, and hyperbolic spaces.
method Novel formulations of linear classifiers on Riemannian manifolds, proving expressive power, and formalizing perceptron and SVM classifiers.
result Linear classifiers in product space forms have the same expressive power as in Euclidean space of the same dimension.