paper-with-me

Papers

Preventing Manifold Intrusion with Locality: Local Mixup

2022-01-12 · Raphael Baena, Lucas Drumetz, Vincent Gripon

Mixup is a data-dependent regularization technique that consists in linearly interpolating input samples and associated outputs. It has been shown to improve accuracy when used to train on standard machine learning datasets. However, authors have pointed out that Mixup can produce out-of-distribution virtual samples and even contradictions in the augmented training set, potentially resulting in adversarial effects. In this paper, we introduce Local Mixup in which distant input samples are weighted down when computing the loss. In constrained settings we demonstrate that Local Mixup can create a trade-off between bias and variance, with the extreme cases reducing to vanilla training and classical Mixup. Using standardized computer vision benchmarks , we also show that Local Mixup can improve test accuracy.

📄 PDF Abstract BibTeX arXiv:2201.04368

Code (1)

raphael-baena/Local-Mixup 공식 구현 pytorch

Tasks

Image Classification

Methods 이 논문이 사용한 방법론

Local Mixup 설명 없음
Mixup Mixup is a data augmentation technique that generates a weighted combination of random image pairs from the training data. Given two images and their ground truth labels:…

Similar Papers 제목 키워드 기반

MixUp as Locally Linear Out-Of-Manifold Regularization

2018-09-07 · Hongyu Guo, Yongyi Mao, Richong Zhang

MixUp is a recently proposed data-augmentation scheme, which linearly interpolates a random pair of training examples and correspondingly the one-hot representations of their labels. Training deep neural networks with su…

Data Augmentation

inversedMixup: Data Augmentation via Inverting Mixed Embeddings

2026-01-29 · Fanshuang Kong, Richong Zhang, Qiyu Sun, Zhijie Nie 외 arxiv

Mixup generates augmented samples by linearly interpolating inputs and labels with a controllable ratio. However, since it operates at the latent embedding level, the resulting samples are not human-interpretable. In con…

Data Augmentation

Intrusion-Free Graph Mixup

2021-09-29 · Hongyu Guo, Yongyi Mao

We present a simple and yet effective interpolation-based regularization technique to improve the generalization of Graph Neural Networks (GNNs). We leverage the recent advances in Mixup regularizer for vision and text…

Graph Classification

Mixup Inference: Better Exploiting Mixup to Defend Adversarial Attacks

2019-09-25 · ICLR 2020 1 · Tianyu Pang, Kun Xu, Jun Zhu

It has been widely recognized that adversarial examples can be easily crafted to fool deep networks, which mainly root from the locally non-linear behavior nearby input examples. Applying mixup in training provides an ef…

Adversarial Robustness

Modality-Adaptive Mixup and Invariant Decomposition for RGB-Infrared Person Re-Identification

2022-03-03 · Zhipeng Huang, Jiawei Liu, Liang Li, Kecheng Zheng 외

RGB-infrared person re-identification is an emerging cross-modality re-identification task, which is very challenging due to significant modality discrepancy between RGB and infrared images. In this work, we propose a no…

Deep Reinforcement LearningPerson Re-Identification