NIPS 2018 Adversarial Vision Challenge aims to improve machine vision models.
problem Improving robustness of machine vision models and adversarial attacks.
method Organized a competition to measure progress in adversarial machine vision.
result Facilitated measurable progress in adversarial machine vision.
Satyam simplifies groundtruth collection for machine vision tasks.
problem Difficulty in collecting accurate groundtruth for machine vision systems.
method Crowdsourcing through Amazon Mechanical Turk, automation of task creation and quality control.
result Groundtruth collected by Satyam is comparable to that of trained experts and provides equivalent ML performance.
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.
Machine vision-guided 3D medical image compression improves segmentation accuracy.
problem High data traffic and computation costs in cloud-based medical image analysis.
method Developed a machine vision-oriented 3D image compression framework for medical segmentation.
result Significantly higher segmentation accuracy at the same compression rate or better compression rate under the same accuracy.
CViT learns complex physical systems using vision transformer techniques.
problem Learning maps between infinite-dimensional function spaces in scientific machine learning.
method Combines vision transformer encoder, grid-based coordinate embedding, and cross-attention mechanism.
result Achieves state-of-the-art performance on multiple benchmarks, often surpassing larger models.
Systematic review of machine vision in robotics, highlighting challenges and improvements.
problem Challenges in machine vision for robotics, especially occlusion and lighting variance.
method Systematic literature review of 172 papers from four databases, selecting 52 relevant papers.
result Robustness and computation time improvements, but occlusion and lighting variance remain major issues.
Paper proposes privacy-preserving learning for images, making them imperceptible to humans but recognizable by machines.
problem Conflict between developing AI systems and protecting sensitive training data.
method Encryption strategies (random shuffling and sub-patch mixing) followed by minimal adaptation to vision transformer.
result Achieves comparable accuracy to competitive methods while ensuring human-imperceptibility of encrypted images.
Deep learning brings major advances in AI, especially in computer vision.
problem Keeping track of regular advances in deep learning is challenging for new researchers.
method Briefly discusses recent advances in deep learning over the past few years.
result Revolutionary advances in computer vision and machine learning.
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.
Machine learning models are vulnerable to adversarial examples: small changes to images can cause computer vision models to make mistakes such as identifying a school bus as an ostrich. However, it is still an open question whether humans are prone to similar mistakes. Here, we address this question by leveraging recen…
Paper proposes EEIPU, a memoization-aware BO algorithm to reduce hyperparameter tuning costs.
problem High costs in GPU-days for training and fine-tuning language models.
method Memoization-aware Bayesian Optimization (EEIPU) algorithm in tandem with pipeline caching.
result EEIPU produces 103% more hyperparameter candidates and 108% more validation metric improvement.
Survey of complex-valued neural networks for improved performance.
problem Lack of complex-valued neural networks in machine learning frameworks.
method Literature review of CVNNs.
result Advantages of CVNNs over real-valued neural networks.
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.
B-cos transformers explain Vision Transformers' decisions.
problem Lack of holistic explanations for transformer outputs.
method Formulate each component as dynamic linear, allowing a single linear transform for summarization.
result Bcos-ViTs are highly interpretable and competitive on ImageNet.
Deep transfer learning improves malware classification speed and accuracy.
problem Static malware classification accuracy and speed.
method Transfer learning from computer vision to static malware detection.
result Our method outperforms classical machine learning methods in accuracy, false positive rate, true positive rate, and F1 score.
Scoping review of EO-ML methods for causal inference in poverty geography.
problem Lack of thorough documentation and best practices for EO-ML methods in causal analysis.
method Comprehensive scoping review cataloging five principal approaches.
result Detailed protocol for integrating EO data into causal analysis.
TACTO simulates high-resolution touch sensing for robotics.
problem Accurate simulation of touch sensing in robotics.
method Fast, flexible, open-source simulator for vision-based tactile sensors.
result Demonstrated TACTO's effectiveness in grasping stability prediction and marble manipulation control.
New datasets make AI models fail reliably, highlighting weaknesses.
problem AI models' vulnerabilities to adversarial examples.
method Created challenging datasets with adversarial filtering, tested on various models.
result Existing models perform poorly on new datasets, revealing shared weaknesses.
With the advent of large labelled datasets and high-capacity models, the performance of machine vision systems has been improving rapidly. However, the technology has still major limitations, starting from the fact that different vision problems are still solved by different models, trained from scratch or fine-tuned o…
LeagueAI generates synthetic data for better object detection in video games.
problem Laborious work of gathering large amounts of hand-labeled data for machine vision applications.
method Automatic synthetic dataset generation using game 3D models and background.
result Models trained on synthetic data outperformed those on hand-labeled data in precision and reliability.
Framework for efficient defect classification and inspection.
problem Adaptive defect classification and inspection from high volume data.
method Continual learning framework for dynamic classifier updates.
result Efficient storage and computational needs reduction.
Develops methods for training models with few annotations in computer vision tasks.
problem Training models with limited labeled data in computer vision.
method Theoretical, algorithmic, and experimental contributions for Meta-Learning and Semi-Supervised Learning.
result Improves Contrastive Learning and proposes a semi-supervised method for transformer-based object detectors.
Automatically optimizes simulation parameters for machine learning.
problem Costly or hard-to-acquire training data for machine learning models.
method Reinforcement learning to control simulator parameters for data synthesis.
result Approach optimizes simulation parameters to maximize model accuracy.
This study compares Matlab and OpenCV for machine learning algorithms.
problem Comparing execution speeds of Matlab and OpenCV for machine learning.
method 20 real datasets, 20 different machine learning algorithms.
result OpenCV is significantly faster than Matlab in execution.
A machine learning method predicts rock permeability from 3D images.
problem Efficiently predict permeability of heterogeneous rocks for planetary and robotic applications.
method Machine learning guided 3D properties recognition of rock morphology from 3D micro CT and MRI images.
result The morphology decoder method accurately predicts permeability from 3D images.
V-HMN integrates memory mechanisms for improved image recognition.
problem Limited interpretability and high data requirements of existing vision backbones.
method Brain-inspired hierarchical memory modules with iterative refinement.
result V-HMN achieves strong performance on image classification benchmarks.
New methods adapt conformal prediction to unknown subpopulation shifts.
problem Failure of conformal prediction under unknown subpopulation shifts.
method Proposes new methods that adapt conformal prediction to unknown subpopulation shifts without explicit subpopulation labels.
result Ensures valid coverage guarantees without explicit knowledge of subpopulation structure.
This paper surveys algorithmic advancements in Optimal Transport with applications in machine learning.
problem Quantifying differences between distributions in various fields.
method Examines classical and modern computational techniques, including Sinkhorn iterations and primal-dual strategies.
result Highlights the robustness and scalability of OT algorithms in high-dimensional problems.
Explains equivariant neural networks for machine learning.
problem Understanding equivariance in neural networks.
method Simple mathematical treatment of neural network concepts.
result Clarifies the mathematical basis of equivariant neural networks.
We integrate camera pose correlations into deep models using Gaussian processes.
problem Lack of inter-frame reasoning in deep neural networks.
method Derive a principled framework combining camera pose information with deep models using a novel view kernel.
result Soft-prior knowledge aids pose-related vision tasks like novel view synthesis.
Survey of methods for ML assurance across its lifecycle stages.
problem Ensuring safety of ML in safety-critical applications.
method Comprehensive survey of methods at each ML lifecycle stage.
result Identification of open challenges in ML assurance.
Deep learning improves material recognition in construction monitoring.
problem Varying illuminations and low accuracy rates in material classification.
method Deep learning methods, including convolutional neural networks, were used to classify and recognize materials in construction sites.
result Achieved 97.35% accuracy rate for material classification.
This dissertation tackles challenges in reliable machine learning measurement.
problem Challenges in reproducibility, scalability, and uncertainty quantification in machine learning.
method Develops criteria for meaningful metrics and methodologies for scalable, reliable measurement.
result Provides methods for evaluating generative-AI systems and quantifying memorization.
Novel approach to contextual bandits using self-supervised learning.
problem Exploiting rich data representations in computer vision without explicit labels.
method Combining contextual bandit objective with self-supervision objective.
result Substantial gains in cumulative reward on computer vision datasets.
Improved model robustness against corruptions using online adaptation.
problem Machine vision models' vulnerability to image corruptions like blurring or compression artefacts.
method Using corrupted images' statistics for unsupervised online adaptation to improve robustness.
result ResNet-50 achieves 62.2% mCE on ImageNet-C with adaptation, improving from 76.7% without.
This paper reviews and proposes a unified framework for contrastive learning.
problem The origins and development of contrastive learning across various fields.
method A comprehensive literature review and a general Contrastive Representation Learning framework.
result A unified framework simplifies and unifies contrastive learning methods.
This study automates blood cell classification using computer vision.
problem Automated detection and classification of white blood cells.
method Color-based segmentation, morphological processing, feature extraction, PCA, Unsupervised and Supervised learning algorithms, Deep Convolutional Neural Networks.
result Identification of robust algorithms for automated blood cell classification.
GWHD dataset offers 4,700 high-res images of wheat heads.
problem Challenges in wheat head detection from high-resolution imagery.
method Large, diverse dataset with detailed metadata.
result Benchmark for wheat head detection methods.
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.
Article presents QR and LQ decomposition algorithms for various matrix sizes and ranks.
problem Solving least squares problems in machine learning and computer vision.
method Developed novel matrix backpropagation algorithms for QR and LQ decompositions of different matrix sizes and ranks.
result Numerical stability and computational efficiency of the proposed methods.
Evaluates deep learning models in histopathology for robustness and classification strategies.
problem Lack of comprehensive evaluation of histopathology models beyond accuracy.
method Developed a new methodology to evaluate models on five histopathology datasets, including vision transformers and CNNs.
result Identified insights into cancer classification strategies and robustness against stain variations.
Extracts factors from Treasury yields using ML techniques.
problem Understanding factors underlying Treasury yields.
method Nonnegative Matrix Factorization (NMF) and clustering.
result Factors identified through NMF and clustering.
This paper surveys black-box attacks on computer vision models.
problem Real-life adversarial attacks on deep learning models.
method Comprehensive comparative study of attacks and defenses.
result Significant amount of research on reliability of models.
Develops counterfactual visual explanations to show how images could change to classify differently.
problem Creating understandable explanations for vision system predictions.
method Selects a distractor image and identifies spatial regions to modify for different classification.
result Users trained with counterfactual explanations perform better in fine-grained bird classification.
Experts assess fairness in machine learning, identifying promising research directions.
problem Understanding and ensuring fairness in machine learning algorithms.
method Convened a workshop of experts to assess the state of fairness research.
result Identified promising research directions in fairness in machine learning.
Automatic classification of trees using remotely sensed data has been a dream of many scientists and land use managers. Recently, Unmanned aerial vehicles (UAV) has been expected to be an easy-to-use, cost-effective tool for remote sensing of forests, and deep learning has attracted attention for its ability concerning…
New mechanism discovered for feature learning in CNNs.
problem Understanding how CNNs learn features from images.
method Proposed Convolutional Neural Feature Ansatz linking filter covariances to patch-based AGOPs.
result Deep ConvRFM algorithm learns features similar to deep CNNs, improving performance.
New methods for graph completion improve image annotation and neuroimaging.
problem Sequential acquisition of partial measurements on graphs.
method Optimization model in Fourier domain, adaptive submodularity.
result Promising results on images and neuroimaging applications.