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.

168,657 papers · 148 categories

Trend · papers per month

count % of corpus

6 results for “CutMix”

Provable Benefit of Cutout and CutMix for Feature Learningcs.LG

CutMix enhances feature learning in neural networks, improving test accuracy.

problem Understanding and improving feature learning in neural networks using patch-level augmentation.

method Three distinct methods: vanilla training, Cutout training, and CutMix training were studied.

result CutMix training yields the highest test accuracy and learns all features and noise vectors evenly.

feature learning patch-level augmentation Cutout CutMix neural networks

2024-10-31abs ↗pdf ↗

Inducing Spatial Locality in Vision Transformers through the Training Protocolcs.CV

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.

Vision Transformers Spatial Locality CutMix AutoAugment ColorJitter

2026-05-11abs ↗pdf ↗

FMix: Enhancing Mixed Sample Data Augmentationcs.LG

Mixed Sample Data Augmentation (MSDA) has received increasing attention in recent years, with many successful variants such as MixUp and CutMix. By studying the mutual information between the function learned by a VAE on the original data and on the augmented data we show that MixUp distorts learned functions in a way …

2020-02-27abs ↗pdf ↗

Towards Understanding Why Data Augmentation Improves Generalizationcs.CV

Unified theory explains how data augmentation improves deep learning models.

problem Understanding why data augmentation improves model generalization.

method Unified theoretical framework explaining two key effects: partial semantic feature removal and feature mixing.

result Data augmentation enhances generalization through partial semantic feature removal and feature mixing.

data augmentation deep learning generalization feature learning theoretical framework

2025-02-13abs ↗pdf ↗

Few-shot Adaptive Object Detection with Cross-Domain CutMixcs.CV

Adaptive object detection method synthesizes target domain images from source domain images.

problem Large domain gap between source and target domains in object detection.

method Cross-domain CutMix with adversarial learning.

result Higher accuracy in different domain settings compared to conventional methods.

object detection transfer learning domain adaptation cutmix adversarial learning

2022-08-31abs ↗pdf ↗

DeepIFSAC: Deep Imputation of Missing Values Using Feature and Sample Attention within Contrastive Frameworkcs.LG

DeepIFSAC uses attention mechanisms and contrastive learning to impute missing values in tabular data.

problem Missing values in tabular data, especially when high and not random.

method Row and column attention in a contrastive learning framework with CutMix data augmentation.

result Proposed method outperforms state-of-the-art methods for missing rates between 10% and 90% and various missing value types.

missing value imputation tabular data attention mechanisms contrastive learning CutMix

2025-01-19abs ↗pdf ↗