Goldilocks activation functions improve neural network performance.
problem Improving neural network performance and understanding signal transformation.
method Introducing Goldilocks activation functions that locally deform input signals.
result Goldilocks networks outperform or match SELU and RELU on CIFAR-10 and CIFAR-100 datasets.
Empirical study on adversarial robustness in transfer learning from CIFAR 100 to CIFAR 10.
problem Evaluating adversarial robustness in transfer learning from CIFAR 100 to CIFAR 10.
method Study of adversarial robustness under transfer learning from a source trained on CIFAR 100 to a target network trained on CIFAR 10, using robust optimisation.
result Using PGD examples during training on the source task leads to more general robust features that are easier to transfer and achieve 5.2% more accuracy against white-box PGD attacks.
Res-SE-Net boosts Resnet performance by enhancing bridge-connections.
problem Reduced accuracy in Resnet due to lack of feature map contribution from bridge-connections.
method Proposed Res-SE-Net architecture with Squeeze-and-Excitation (SE) block to quantify and weight feature map importance.
result Res-SE-Net generalizes better than Resnet and SE-Resnet on CIFAR-10 and CIFAR-100 datasets.
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.
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.
Colored noise improves neural network robustness against adversarial attacks.
problem Vulnerability of neural networks to adversarial perturbations.
method Injection of colored noise into network weights and activations during adversarial training.
result Our approach outperforms previous methods in terms of adversarial accuracy 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.
EENA efficiently searches neural architectures with minimal resources.
problem Lack of direction and high computational cost in neural architecture search.
method EENA uses guided evolution with mutation and crossover operations.
result EENA designs highly effective neural architectures with minimal resources.
This paper explores adversarial training limits and improves model robustness against norm-bounded perturbations.
problem Understanding and improving adversarial robustness of deep neural networks.
method Systematic study of adversarial training with various factors, including model size, activation functions, and unlabeled data.
result Training robust models that go beyond state-of-the-art results by combining larger models, Swish/SiLU activations, and model weight averaging.
SPAT improves adversarial robustness by preserving semantics in adversarial training.
problem Adversarial examples often have different semantics than original data, introducing unintended biases.
method Semantics-preserving adversarial training (SPAT) that encourages pixel perturbation shared among all classes.
result SPAT improves adversarial robustness and achieves state-of-the-art results in CIFAR-10 and CIFAR-100.
New method enhances adversarial robustness of deep learning models.
problem Improving the robustness of deep learning models against adversarial attacks.
method Optimal transport regularized divergences applied to distributionally robust optimization.
result Improved adversarial robustness on CIFAR-10 and CIFAR-100 datasets.
New bound on neural network generalization error using geometric complexity.
problem Understanding the generalization capabilities of deep neural networks.
method Derive a new upper bound on generalization error using margin-normalized geometric complexity.
result Empirical validation of the bound for ResNet-18 on CIFAR-10 and CIFAR-100 datasets.
KD technique improves QDNN performance with reduced hyper-parameters.
problem Restoring performance loss in QDNNs due to quantization.
method Applied KD with reduced hyper-parameters, including a new coefficient reduction technique.
result Achieved 92.7% test accuracy on CIFAR-10 and 67.0% on CIFAR-100 with 2-bit weights.
SRS improves deep learning accuracy on small image datasets.
problem Training deep neural networks with limited images per class.
method Fixed sequence index sampling with batch replacement.
result Significantly improved classification accuracy on CIFAR-100.
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.
Method detects and relabels noisy image labels to improve DNN performance.
problem Label noise in training images harms DNN generalization.
method Identifies noisy labels based on predictive uncertainty changes over training.
result Iterative relabeling of noisy labels improves DNN performance.
Generative models improve adversarial robustness by adding synthetic data.
problem Improving robustness in machine learning models trained on limited data.
method Using synthetic data generated from a large dataset to augment the original training set.
result Generative models can significantly reduce the robust-accuracy gap compared to models trained with additional real data.
Patch augmentation boosts neural network accuracy and robustness.
problem Improving neural network accuracy and robustness to adversarial attacks.
method Data augmentation technique creating new images by superimposing patches from image pairs.
result Significant accuracy improvements on CIFAR-10 and CIFAR-100 datasets.
A new pruning method reduces neural network computation without retraining.
problem Efficiently reduce neural network computation while maintaining accuracy.
method Structured directional pruning via perturbation orthogonal projection.
result Achieves state-of-the-art pruned accuracy without retraining.
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.
ThriftyNet uses a single convolutional layer recursively to maximize parameter usage.
problem Maximizing the use of parameters in deep convolutional neural networks.
method A single convolutional layer is used recursively, with normalization, non-linearities, downsampling, and shortcuts to maintain model expressivity.
result ThriftyNet achieves competitive performance with significantly fewer parameters.
The paper calibrates uncertainty in dropout variational inference models.
problem Miscalibration of model uncertainty in dropout variational inference.
method Logit scaling methods are extended to recalibrate model uncertainty.
result Logit scaling reduces miscalibration, improving reliability of predictions.
TrustNet robustly learns noise patterns from trusted data to improve weakly-supervised classification.
problem Robustness to label noise in weakly-supervised learning.
method TrustNet learns noise patterns from trusted data, then trains a robust classifier using these patterns.
result TrustNet outperforms state-of-the-art methods in robustness to various noise patterns.
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.
A simple technique improves continual learning by 50% on image datasets.
problem Challenges in training neural networks on a stream of shifting data.
method Experience Replay (ER) with five tricks to mitigate its shortcomings.
result ER, enhanced with tricks, achieves significant accuracy gains.
This paper investigates how forgetting affects neural network representations and stabilizes deeper layers.
problem Catastrophic forgetting in machine learning models trained on sequential tasks.
method Representational analysis techniques and empirical studies on CIFAR-10 and CIFAR-100 datasets.
result Deeper layers are disproportionately the source of forgetting, and methods to mitigate forgetting stabilize these layers.
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.
Softmax is found ineffective for NL block, leading to improved performance.
problem Inefficiency of softmax in NL block for global context modeling.
method Empirical analysis and replacement of softmax with scaling factor.
result Improved performance on various datasets with reduced computational cost.
This work proposes a new adversarial training method based on L2L framework.
problem Training robust neural networks against adversarial attacks.
method Generic learning-to-learn (L2L) framework to learn an optimizer and a robust classifier.
result L2L outperforms existing adversarial training methods in classification accuracy and computational efficiency.
XferNAS reduces neural architecture search time by 33x.
problem Expensive neural architecture search for new tasks.
method Transfer knowledge from previous tasks to reduce search time.
result Reduction of search time from 200 to 6 GPU days.
This paper examines how to calibrate ensemble members for better prediction accuracy.
problem Improper calibration of deep neural networks leads to unreliable probability estimates.
method Theoretical analysis and empirical evaluation on CIFAR-100 dataset.
result Well-calibrated ensemble members do not guarantee a well-calibrated ensemble prediction, but a well-calibrated ensemble prediction cannot exceed the average performance of its members.
A new mutual information optimization method using self-supervised binary contrastive learning.
problem Improving self-supervised contrastive learning for better model performance.
method Proposes a novel loss function for contrastive learning that optimizes mutual information in positive and negative pairs.
result The proposed method outperforms state-of-the-art self-supervised contrastive frameworks on various benchmark datasets.
Residual networks (ResNets) have recently achieved state-of-the-art on challenging computer vision tasks. We introduce Resnet in Resnet (RiR): a deep dual-stream architecture that generalizes ResNets and standard CNNs and is easily implemented with no computational overhead. RiR consistently improves performance over R…
New method learns convolution-like structures from scratch.
problem Learning convolution-like structures from data.
method Minimum description length principle and β-LASSO algorithm. result Learned architectures achieve state-of-the-art accuracies.
Mixup inference improves adversarial robustness by mixing inputs with clean samples.
problem Adversarial examples can fool deep networks due to local non-linearity.
method Develops mixup inference, which mixes inputs with clean samples to shrink adversarial perturbations.
result Mixup inference enhances adversarial robustness for mixup-trained models.
We simplify neural network training by assigning minimal precision to all parameters, speeding up convergence.
problem Slow and resource-intensive neural network training on constrained systems.
method Analytical precision assignment for activations, weights, gradients, and accumulators.
result Empirically validated near-optimal precision assignment for four datasets, reducing complexity.
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.
Single network with segmented training prevents forgetting in dynamic systems.
problem Catastrophic forgetting in continual learning for dynamic systems.
method Single Net with Progressive Segmented Training (PST). Model parameters are divided into frozen and secondary groups.
result Achieves state-of-the-art accuracy in single-head evaluation on CIFAR-10 and CIFAR-100 datasets.
Simplified non-contrastive learning avoids representation collapse.
problem Training failure modes in self-supervised learning.
method Hyperdimensional computing and inductive bias.
result The approach avoids representation collapses.
A network architecture improves classification performance on various datasets.
problem Improving classification performance on diverse datasets.
method Divide fully connected layer into three levels, learn existing layers, cluster similar classes, reclassify using clustering masks.
result Achieved state-of-the-art performance with an error rate of 11.56% on Cifar-100.
Paper introduces new loss functions for multi-class abstention learning.
problem Learning with multi-class classification and the ability to abstain.
method Developed new families of surrogate losses for abstention.
result Proved strong consistency guarantees for new surrogate losses.
Minimalistic unsupervised learning with sparse manifold transform achieves SOTA performance.
problem Achieving state-of-the-art unsupervised learning performance without complex engineering.
method Sparse manifold transform, leveraging sparse coding, manifold learning, and slow feature analysis.
result 99.3% KNN top-1 accuracy on MNIST, 81.1% on CIFAR-10, and 53.2% on CIFAR-100.
Guided Evolution improves NAS efficiency and accuracy.
problem NAS methods converge to local minima and are complex.
method G-EA: guided evolutionary approach with initialization evaluation and continuous knowledge extraction.
result G-EA achieves state-of-the-art results in CIFAR-10, CIFAR-100, and ImageNet16-120.
New distance metric for neural architecture search reduces search space complexity.
problem Reducing the complexity of neural architecture search.
method Fisher task distance for measuring task similarity and online neural architecture search.
result Reduced search space complexity for task-specific architectures.
Dual Student separates the teacher from the student in SSL, improving performance.
problem Performance bottleneck caused by coupled teacher in consistency-based SSL methods.
method Introduces Dual Student, replacing the teacher with another student and defining a stabilization constraint.
result Significant improvement in classification performance on SSL benchmarks.
AdaNAS uses ensembles to improve neural architecture search.
problem Finding optimal neural network architectures is time-consuming and resource-intensive.
method AdaNAS employs ensemble learning to automatically compose neural networks.
result Ensemble networks improve accuracy compared to single neural networks with the same number of parameters.
MALT improves adversarial attacks by targeting classes more efficiently.
problem Naive targeting of adversarial attacks based on classifier confidence.
method MALT - Mesoscopic Almost Linearity Targeting, based on medium-scale almost linearity assumptions.
result MALT wins over AutoAttack on CIFAR-100 and ImageNet datasets, five times faster.
This paper calibrates uncertainty in dropout variational inference models.
problem Uncertainty in variational inference with dropout is poorly calibrated.
method Temperature scaling is extended to dropout variational inference.
result Temperature scaling reduces miscalibration of uncertainty.