paper-with-me

Papers

DiffAug: A Diffuse-and-Denoise Augmentation for Training Robust Classifiers

2023-06-15 · Chandramouli Sastry, Sri Harsha Dumpala, Sageev Oore

We introduce DiffAug, a simple and efficient diffusion-based augmentation technique to train image classifiers for the crucial yet challenging goal of improved classifier robustness. Applying DiffAug to a given example consists of one forward-diffusion step followed by one reverse-diffusion step. Using both ResNet-50 and Vision Transformer architectures, we comprehensively evaluate classifiers trained with DiffAug and demonstrate the surprising effectiveness of single-step reverse diffusion in improving robustness to covariate shifts, certified adversarial accuracy and out of distribution detection. When we combine DiffAug with other augmentations such as AugMix and DeepAugment we demonstrate further improved robustness. Finally, building on this approach, we also improve classifier-guided diffusion wherein we observe improvements in: (i) classifier-generalization, (ii) gradient quality (i.e., improved perceptual alignment) and (iii) image generation performance. We thus introduce a computationally efficient technique for training with improved robustness that does not require any additional data, and effectively complements existing augmentation approaches.

📄 PDF Abstract BibTeX arXiv:2306.09192

Code (0)

등록된 구현이 없습니다.

Tasks

DenoisingImage GenerationOut-of-Distribution Detection

Methods 이 논문이 사용한 방법론

Attention 설명 없음
BPE Byte Pair Encoding, or BPE, is a subword segmentation algorithm that encodes rare and unknown words as sequences of subword units. The intuition is that various word…
Label Smoothing Label Smoothing is a regularization technique that introduces noise for the labels. This accounts for the fact that datasets may have mistakes in them, so maximizing the…
Adam 설명 없음
Position-Wise Feed-Forward Layer 설명 없음
Dropout Dropout is a regularization technique for neural networks that drops a unit (along with connections) at training time with a specified probability $p$ (a common value is…
Dense Connections Dense Connections, or Fully Connected Connections, are a type of layer in a deep neural network that use a linear operation where every input is connected to every output…
Absolute Position Encodings Absolute Position Encodings are a type of position embeddings for [Transformer-based models] where positional encodings are…

Similar Papers 제목 키워드 기반

DiffAug: Enhance Unsupervised Contrastive Learning with Domain-Knowledge-Free Diffusion-based Data Augmentation

2023-09-10 · Zelin Zang, Hao Luo, Kai Wang, Panpan Zhang 외

Unsupervised Contrastive learning has gained prominence in fields such as vision, and biology, leveraging predefined positive/negative samples for representation learning. Data augmentation, categorized into hand-designe…

Contrastive LearningData AugmentationImage ClassificationRepresentation Learning

Differentiable Augmentation for Data-Efficient GAN Training

2020-06-18 · NeurIPS 2020 12 · Shengyu Zhao, Zhijian Liu, Ji Lin, Jun-Yan Zhu 외

The performance of generative adversarial networks (GANs) heavily deteriorates given a limited amount of training data. This is mainly because the discriminator is memorizing the exact training set. To combat it, we prop…

Image Generation

MedDiffuseMix: Preserving Diagnostic Evidence with Saliency-Aware Diffusion Medical Image Data Augmentatio

2026-06-25 · Teerath Kumar, Raja Vavekanand, Muhammad Turab arxiv

Limited data availability, class imbalance, and domain variability remain major barriers to reliable medical image classification. Conventional augmentation can improve training diversity but may distort diagnostically i…

Medical Image ClassificationImage Augmentation

DiffuseDef: Improved Robustness to Adversarial Attacks via Iterative Denoising

2024-06-28 · Zhenhao Li, Huichi Zhou, Marek Rei, Lucia Specia

Pretrained language models have significantly advanced performance across various natural language processing tasks. However, adversarial attacks continue to pose a critical challenge to systems built using these models,…

Adversarial DefenseDenoising

PC-Diffuser: Path-Consistent Capsule CBF Safety Filtering for Diffusion-Based Trajectory Planner

2026-03-11 · Eugene Ku, Yiwei Lyu arxiv

Autonomous driving in complex traffic requires planners that generalize beyond hand-crafted rules, motivating data-driven approaches that learn behavior from expert demonstrations. Diffusion-based trajectory planners hav…

Autonomous Driving