Improved image classification accuracy on CIFAR-10 dataset.
problem Classifying images from the CIFAR-10 dataset with high accuracy.
method Combining features from manual and deep learning approaches, including VGG16, Inception ResNet v2, HOG, and pixel intensities.
result Achieved 94.6% testing accuracy by combining top 1000 principal components.
We propose deep convolutional Gaussian processes, a deep Gaussian process architecture with convolutional structure. The model is a principled Bayesian framework for detecting hierarchical combinations of local features for image classification. We demonstrate greatly improved image classification performance compared …
Score-based generative models achieve state-of-the-art classification accuracy on CIFAR-10.
problem Improving classification accuracy on natural image datasets.
method Score-based generative models applied to CIFAR-10.
result Score-based models achieve state-of-the-art classification accuracy on CIFAR-10.
Delta method vs Bootstrap for deep learning classification shows strong linear relationship and faster computation.
problem Validating the Delta method for deep learning classification.
method Comparison of Delta method and Bootstrap on LeNet-based neural networks using MNIST and CIFAR-10 datasets.
result The Delta method provides a five times faster computation with strong linear predictive uncertainty relationship.
The paper investigates how class mean vectors enhance neural network classification.
problem Improving neural network performance in classification tasks.
method Exploring the role of class mean vectors in neural networks, including direct computation of weights, performance monitoring, and self-training.
result Empirical evidence suggests that using class mean vectors can significantly improve neural network performance on classification tasks.
A new semi-supervised learning method using label gradients.
problem Improve accuracy in semi-supervised learning with limited labeled data.
method Impute labels for unlabeled data using a distance metric based on model gradients, then optimize these imputed labels.
result Demonstrates state-of-the-art accuracy in semi-supervised CIFAR-10 classification.
Super-AND improves unsupervised embedding learning with 89.2% accuracy on CIFAR-10.
problem Extracting good representations from data without labels.
method Super-AND uses unique losses to gather similar samples and maintain features.
result Super-AND achieves 89.2% accuracy on CIFAR-10 image classification.
This paper explores normalization in neural ODEs, achieving high accuracy in CIFAR-10.
problem Understanding the role of normalization in neural ODEs.
method Investigated different normalization techniques and their impact on neural ODEs performance.
result Achieved 93% accuracy in CIFAR-10 classification task.
New test sets show current image classifiers struggle with harder images.
problem Current image classifiers overfit to original test sets.
method Created new test sets for CIFAR-10 and ImageNet, evaluated various models.
result Accuracy drops of 3% - 15% on CIFAR-10 and 11% - 14% on ImageNet.
This work examines how non-identical data distributions affect Federated Learning performance.
problem The impact of non-identical data distributions on Federated Learning performance.
method Synthesized datasets with varying degrees of data distribution similarity, evaluated Federated Averaging algorithm performance, proposed server momentum mitigation.
result Performance of Federated Learning degrades as data distributions differ more, and a mitigation strategy improves accuracy.
Improved deep kernel machine achieves 94.5% test accuracy on CIFAR-10.
problem Achieving high accuracy on complex tasks like image classification.
method Stochastic kernel regularisation to add noise to learned Gram matrices.
result 94.5% test accuracy on CIFAR-10.
A new method for PU learning improves classification error on CIFAR-10.
problem Learning from positive and unlabeled data in practical applications.
method A simple yet effective data augmentation method based on consistency regularization.
result Achieves an averaged improvement of 3.40 points in classification error on CIFAR-10.
Paper estimates optimal ROC curve arc length and AUC, improving classification performance.
problem Estimating optimal ROC curve arc length and AUC in imbalanced binary classification.
method Expresses arc length and AUC as variational objectives, estimating using positive and negative samples.
result Proposed classification procedure maximizes an approximate lower bound of maximal AUC.
The paper shows strong correlation between in-distribution and out-of-distribution performance in various machine learning models.
problem Understanding reliability of machine learning systems in unseen environments.
method Empirical analysis of various models and distribution shifts on CIFAR-10, ImageNet, and other datasets.
result Out-of-distribution performance is strongly correlated with in-distribution performance across different models and distribution shifts.
Invertible neural networks with masked convolutions improve classification and generative models.
problem Building robust invertible neural networks for better model interpretability and generative tasks.
method Combining masked convolutions and iterative inversion methods to create invertible architectures.
result Invertible neural networks achieve competitive performance in classification and generative tasks.
Local unsupervised learning outperforms end-to-end training for image classification.
problem Local unsupervised learning is believed to be inferior to end-to-end training.
method Designing a local algorithm to learn convolutional filters at scale on large image datasets using local Hebbian learning.
result Convolutional networks with patch normalization significantly outperform standard networks on image classification tasks.
Study improves top-k set prediction with low cardinality.
problem Improving top-k set prediction accuracy with low cardinality.
method Introduces new target loss function and surrogate losses.
result Demonstrates effectiveness of cardinality-aware algorithms.
EXoN creates an explainable latent space for semi-supervised learning.
problem Creating an explainable latent space for semi-supervised learning.
method EXoN combines VAE with SCI (Soft-label Consistency Interpolation) to create an explainable latent space.
result EXoN reduces the cost of investigating representation patterns on the latent space.
Improved VGG networks enhance image classification accuracy.
problem Enhancing image classification accuracy using modified VGG architectures.
method Two improved VGG architectures were created by freezing the first two blocks and applying different dilation rates in the last three blocks.
result Significant out-performance on image classification tasks on CIFAR-10 and CIFAR-100 datasets.
Improved sample efficiency with normalized RBF kernels in neural networks.
problem Learning more with less data in deep learning models.
method Two-phase method to train neural networks with normalized RBF kernels as output layer.
result Normalized RBF kernel networks achieve higher sample efficiency, compactness, and separability.
New defense method inspired by encryption improves visual classification accuracy.
problem Conventional defenses reduce accuracy and are defeated by obfuscated gradients.
method Block-wise pixel shuffling with secret key for training and test images.
result Achieves high accuracy (91.55%) on clean images and (89.66%) on adversarial examples.
New artificial neuron doubles weight for improved deep learning accuracy.
problem Improving deep learning models' accuracy.
method Introducing a double-weight neuron, tested on MNIST and CIFAR-10 datasets.
result Significant improvement in classification accuracy for MNIST and CIFAR-10 datasets.
Study finds 10% redundant images in image classification datasets.
problem Redundancy in large image classification datasets.
method Analysis of CIFAR-10 and ImageNet datasets to identify redundant images.
result 10% of images are redundant and can be removed without significant loss of performance.
In deep neural network, the cross-entropy loss function is commonly used for classification. Minimizing cross-entropy is equivalent to maximizing likelihood under assumptions of uniform feature and class distributions. It belongs to generative training criteria which does not directly discriminate correct class from co…
Proposes a new pooling operator for CNNs to handle spatially varying information.
problem Need to treat spatial locations in non-uniform manner for better image classification.
method Introduces an extended pooling operator that can learn different weights for each pixel location.
result The proposed pooling operator improves generalization and robustness in image classification tasks.
Localized adversarial training improves image classifiers' robustness.
problem State-of-the-art image classifiers fail on carefully manipulated adversarial images.
method Developed a localized adversarial attack and used it to train a robust classifier.
result Localized adversarial training increases robustness against adversarial inputs.
Improved EBM training yields better samples and robust performance.
problem Training energy-based models (EBMs) on high-dimensional data.
method Scaled MCMC-based training techniques for continuous neural networks.
result Achieved state-of-the-art performance on various tasks.
New optimization algorithms for neural networks using operator splitting.
problem Training efficiency and convergence in neural networks.
method Sequential operator splitting technique applied to neural network training.
result Empirical rate of convergence towards local minimum of loss function validated.
NASES uses embedding space for efficient NAS in image classification tasks.
problem Difficulty in optimizing high-dimensional discrete architecture spaces.
method NASES employs architecture encoders and decoders to search in an embedding space using reinforcement learning.
result NASES discovers comparable final architectures to other NAS approaches in less time.
CNNs overinterpret inputs, leading to high accuracy without meaningful features.
problem High accuracy in image classifiers can mask subtle model failures.
method Batched Gradient SIS method for discovering sufficient input subsets.
result Overinterpretation allows models to make confident predictions with masked input features.
New method reduces labeler costs by aggregating predictions from local classifiers.
problem Reduce labeler costs in multiclass classification.
method Model K-class classification using smaller classifiers trained on subsets of tasks. result Near-optimal scheme for designing classifier configurations reduces labeler costs.
Study shows optimal self-distillation improves model performance on noisy data.
problem Improving model performance on noisy Gaussian mixture data.
method Hyperparameter-tuned multi-stage self-distillation with a linear classifier, using replica method.
result Primary driver of SD's performance improvement is denoising through hard pseudo-labels.
New algorithm improves quantized neural networks for image classification.
problem Improving approximation capabilities of quantized neural networks.
method Proposed a novel gradient-based training algorithm for quantized neural networks.
result State-of-the-art performance on image classification benchmarks.
This research tackles image classification with noise, proposing committees of CNNs.
problem Image classification with concurrent feature and label noise.
method Committees of Convolutional Neural Networks (CNNs) for MNIST, CIFAR-10, and CIFAR-100 datasets.
result Committees outperform single models in noisy conditions, especially on difficult datasets.
New scalable GP approximation using Fourier series decomposition.
problem Scalability and accuracy in Gaussian process approximations.
method Harmonic kernel decomposition (HKD) to decompose kernels orthogonally.
result Significantly outperforms standard variational methods in scalability and accuracy.
Proposes Bayesian differential privacy for machine learning.
problem Traditional differential privacy does not fit machine learning contexts.
method Bayesian differential privacy (BDP) accounting for data distribution.
result Models maintain high accuracy while providing stronger privacy guarantees.
We combine supervised learning with unsupervised learning in deep neural networks. The proposed model is trained to simultaneously minimize the sum of supervised and unsupervised cost functions by backpropagation, avoiding the need for layer-wise pre-training. Our work builds on the Ladder network proposed by Valpola (…
Capsule networks improve with dynamic routing using Wasserstein objective.
problem Capsule networks struggle to consistently outperform traditional neural networks.
method Dynamic routing scheme using approximate Wasserstein objective to select capsules.
result Capsule network achieves over 1.2% improvement on CIFAR-10 with fewer parameters.
Infinitely wide neural nets perform well on small datasets.
problem Performing well on small datasets with limited training samples.
method Using Neural Tangent Kernels (NTKs) for kernel regression.
result NTK SVM outperforms Random Forests and Convolutional NTK on CIFAR-10 with 10-640 training samples.
Defense against small image patches using occlusions.
problem Vulnerability of deep learning to small adversarial patches.
method Partially occlude image around each patch location.
result Certified security against patch attacks of a certain size.
We explore efficient neural architecture search methods and show that a simple yet powerful evolutionary algorithm can discover new architectures with excellent performance. Our approach combines a novel hierarchical genetic representation scheme that imitates the modularized design pattern commonly adopted by human ex…
A new method uses optimal transport for semi-supervised classification.
problem Semi-supervised learning with limited labeled data.
method Optimal transport formulation with Sinkhorn iteration for label assignment.
result Improved performance on CIFAR-10, CIFAR-100, and SVHN datasets compared to FixMatch.
Unified view of contrastive and supervised learning improves model performance.
problem Improving model performance in classification, robustness, and detection.
method Hybrid discriminative-generative training of energy-based models.
result Improved performance on classification, robustness, out-of-distribution detection, and calibration.
Adversarial training enhances model transferability without sacrificing accuracy.
problem The principle of minimal information in classification models is challenged by adversarial training.
method Investigation of the dual relationship between adversarial training and information theory.
result Adversarial training improves linear transferability and introduces a trade-off between transferability and source task accuracy.
VAE improves semi-supervised learning in small data.
problem Limited data in biological samples.
method Applied VAE to capture features in a lower-dimension.
result Improved performance in semi-supervised learning.
Automatic neural architecture design has shown its potential in discovering powerful neural network architectures. Existing methods, no matter based on reinforcement learning or evolutionary algorithms (EA), conduct architecture search in a discrete space, which is highly inefficient. In this paper, we propose a simple…
Convolutional DKMs improve kernel methods on MNIST, CIFAR-10, and CIFAR-100.
problem Improving kernel methods for image classification.
method Developed a novel inter-domain inducing point approximation and introduced various techniques to extend DKMs to convolutional networks.
result Achieved state-of-the-art performance on image classification benchmarks.
A new method detects and corrects adversarial attacks on classifiers.
problem Detecting and correcting adversarial attacks on machine learning models.
method Unsupervised autoencoder trained with KL divergence loss to match predictions.
result Almost completely neutralizes powerful attacks on MNIST and Fashion-MNIST.