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.

168,786 papers · 148 categories

Trend · papers per month

156312468624 · Jun 202019922001200920172026
48 results for vision datasets

ViWi dataset framework tackles wireless communication problems with visual data.

problem Leveraging visual sensory information in wireless communications.
method Developed a parametric, systematic, and scalable data generation framework using 3D modeling and ray-tracing.
result Offers a way to generate training and testing datasets for assessing machine learning solutions.

Top 8 robotic vision systems tackled lifelong object recognition challenges.

problem Lifelong learning in robotic vision for varied, dynamic environments.
method Design of a dataset with diverse conditions and rules for evaluation.
result Robotic vision systems improved over time with dynamic object appearances.

The paper investigates ethical issues in large image datasets, focusing on pornographic content.

problem Ethical issues in large-scale computer vision datasets, particularly concerning pornographic content.
method Cross-sectional model-based quantitative census covering various factors in the ImageNet-ILSVRC-2012 dataset.
result The dataset contains verifiably pornographic images, including non-consensual and voyeuristic content.

IrisNet tracks tongue contours in ultrasound videos using deep learning.

problem Automatic and real-time tracking of tongue contours in ultrasound videos.
method Convolutional neural network mimicking peripheral vision.
result Outstanding generalization on various ultrasound tongue datasets.

Typically a classifier trained on a given dataset (source domain) does not performs well if it is tested on data acquired in a different setting (target domain). This is the problem that domain adaptation (DA) tries to overcome and, while it is a well explored topic in computer vision, it is largely ignored in robotic …

2018-07-31abs ↗pdf ↗

Plex improves model reliability across vision and language tasks.

problem Improving model reliability in diverse decision-making tasks involving uncertainty and adaptation.
method Developed ViT-Plex and T5-Plex pretrained model extensions to evaluate and improve reliability across 40 datasets.
result Plex greatly improves state-of-the-art across reliability tasks, simplifying evaluation and performance.

We introduce two challenging datasets that reliably cause machine learning model performance to substantially degrade. The datasets are collected with a simple adversarial filtration technique to create datasets with limited spurious cues. Our datasets' real-world, unmodified examples transfer to various unseen models …

2019-07-16abs ↗pdf ↗

This paper improves ensemble learning for vision tasks by encouraging diversity in predictions.

problem Generating effective ensembles of neural networks for multi-modal data.
method Explicitly optimize a diversity inducing adversarial loss for learning stochastic latent variables.
result Significant improvements in classification accuracy and out-of-distribution detection compared to baselines.

Transfer learning is a cornerstone of computer vision, yet little work has been done to evaluate the relationship between architecture and transfer. An implicit hypothesis in modern computer vision research is that models that perform better on ImageNet necessarily perform better on other vision tasks. However, this hy…

2018-05-23abs ↗pdf ↗

Language grounded image understanding tasks have often been proposed as a method for evaluating progress in artificial intelligence. Ideally, these tasks should test a plethora of capabilities that integrate computer vision, reasoning, and natural language understanding. However, rather than behaving as visual Turing t…

2019-04-19abs ↗pdf ↗

FedVision uses federated learning to improve object detection without transmitting data.

problem Challenges in building object detection models on large training datasets due to privacy and cost issues.
method Federated learning (FL) platform for easy integration by non-experts.
result Significant efficiency improvement and cost reduction in smart city applications.

A new network controls task execution in a single vision system.

problem Executing multiple tasks accurately and efficiently in a single network.
method A top-down control network modifies main recognition network activations based on selected task, image content, and spatial location.
result Significantly better results on four datasets compared to state-of-the-art approaches.

System discovers new classes from unlabeled data, improving model performance.

problem Handling datapoints outside initial training distribution.
method Develops new classes through semi-supervised learning, using Dataset Reconstruction Accuracy and class learnability.
result Demonstrates improved model quality through automatic class discovery.

PACE explains ViTs by modeling patch-level concept distributions, surpassing existing methods.

problem Lack of trustworthy post-hoc explanations for Vision Transformers (ViTs)
method Variational Bayesian explanation framework (PACE)
result PACE surpasses state-of-the-art methods in meeting desiderata for ViT explanations.

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.

CutMix training technique improves spatial locality in Vision Transformers.

problem Improving spatial locality in Vision Transformers trained from scratch.
method Comparison of Baseline and Modern training protocols on CIFAR-10, CIFAR-100, and Tiny-ImageNet.
result CutMix training component significantly reduces Mean Attention Distance (MAD) in early layers of Vision Transformers.

The democratization of machine learning (ML) has led to ML-based machine vision systems for autonomous driving, traffic monitoring, and video surveillance. However, true democratization cannot be achieved without greatly simplifying the process of collecting groundtruth for training and testing these systems. This grou…

2018-11-08abs ↗pdf ↗

Proposes hinge-Wasserstein to improve uncertainty estimation in regression tasks.

problem Estimating multimodal aleatoric uncertainty in regression tasks from images.
method Regression-by-classification paradigm with hinge-Wasserstein loss.
result Hinge-Wasserstein loss improves uncertainty estimation on challenging tasks.

New tool uses computer vision to assess FOMC press conference complexity and its impact on equity returns.

problem Understanding the impact of FOMC press conferences on financial markets.
method Developed a measure of discussion complexity using video images and deep learning algorithms.
result Complex discussions during press conferences are associated with higher equity returns and lower volatility.

FMT model improves multimodal sequential learning across language, vision, and acoustic data.

problem Modeling spatio-temporal dynamics across multiple modalities.
method Factorized Multimodal Transformer (FMT) that models intramodal and intermodal dynamics in a factorized manner.
result FMT outperforms existing models on 3 datasets and 21 labels, setting new state of the art.

This paper introduces a novel approach to measuring privacy risks in deep computer vision models based on intermediate outputs.

problem The exposure of intermediate results in hidden layers of deep computer vision models poses significant privacy concerns.
method The approach leverages Degrees of Freedom (DoF) to evaluate the amount of information retained in each layer and combines this with the rank of the Jacobian matrix to assess sensitivity to input variations.
result The proposed framework provides deeper insights into privacy risks associated with intermediate representations without requiring adversarial attack simulations.

Proposes deep collective learning to learn inputs and weights together in neural networks.

problem The need to optimize inputs alongside weights in deep neural networks.
method Introduces deep collective learning to learn inputs and weights jointly, using lookup tables.
result Demonstrates advantages and promise of Lookup-VNets and deep collective learning.

Study evaluates conformal prediction methods for safety in vision models under shifts and long-tailed data.

problem Safety guarantees of conformal prediction methods under distribution shifts and long-tailed data.
method Empirical evaluation of post-hoc and training-based conformal prediction methods on large-scale datasets and models.
result Performance of conformal prediction methods degrades significantly under distribution shifts and long-tailed data.

A benchmark for NLP models trained on text datasets.

problem Limited access to high-performance clusters for NAS experiments.
method Created a search space for recurrent neural networks on text datasets and trained 14k architectures.
result Demonstrated the potential of precomputed NAS results for NLP.

This paper analyzes shallow ViTs, providing sample complexity and SGD behavior insights.

problem Theoretical understanding of shallow ViTs, especially their sample complexity and SGD behavior.
method Data model with label-relevant and label-irrelevant tokens, theoretical analysis of shallow ViT training.
result Characterization of sample complexity for zero generalization error in shallow ViTs.

Proposes MLCNN for better multivariate time series forecasting.

problem Challenges in forecasting multivariate time series, especially the limitation of predicting only one future moment.
method MLCNN, a multi-task deep learning framework inspired by Construal Level Theory, fuses future visions of near and distant future predictions.
result Significant improvements in forecasting accuracy (4.59% RMSE reduction, 6.87% MAE reduction) on real-world datasets.

Inspired by recent successes of deep learning in computer vision, we propose a novel framework for encoding time series as different types of images, namely, Gramian Angular Summation/Difference Fields (GASF/GADF) and Markov Transition Fields (MTF). This enables the use of techniques from computer vision for time serie…

2015-06-01abs ↗pdf ↗

Modern computer vision algorithms often rely on very large training datasets. However, it is conceivable that a carefully selected subsample of the dataset is sufficient for training. In this paper, we propose a gradient-based importance measure that we use to empirically analyze relative importance of training images …

2018-11-30abs ↗pdf ↗