paper-with-me

홈 › Papers

Dynamic Test-Time Augmentation via Differentiable Functions

2022-12-09 · Shohei Enomoto, Monikka Roslianna Busto, Takeharu Eda

Distribution shifts, which often occur in the real world, degrade the accuracy of deep learning systems, and thus improving robustness to distribution shifts is essential for practical applications. To improve robustness, we study an image enhancement method that generates recognition-friendly images without retraining the recognition model. We propose a novel image enhancement method, DynTTA, which is based on differentiable data augmentation techniques and generates a blended image from many augmented images to improve the recognition accuracy under distribution shifts. In addition to standard data augmentations, DynTTA also incorporates deep neural network-based image transformation, further improving the robustness. Because DynTTA is composed of differentiable functions, it can be directly trained with the classification loss of the recognition model. In experiments with widely used image recognition datasets using various classification models, DynTTA improves the robustness with almost no reduction in classification accuracy for clean images, thus outperforming the existing methods. Furthermore, the results show that robustness is significantly improved by estimating the training-time augmentations for distribution-shifted datasets using DynTTA and retraining the recognition model with the estimated augmentations. DynTTA is a promising approach for applications that require both clean accuracy and robustness. Our code is available at \url{https://github.com/s-enmt/DynTTA}.

📄 PDF Abstract BibTeX arXiv:2212.04681

Code (1)

s-enmt/DynTTA 공식 구현 pytorch

Tasks

ClassificationData AugmentationImage Enhancement

Methods 이 논문이 사용한 방법론

Refunds@Expedia|||How do I get a full refund from Expedia? “How do I get a full refund from Expedia? How do I get a full refund from Expedia? – Call ☎️ +1-(888) 829 (0881) or +1-805-330-4056 or +1-805-330-4056 for Quick Help &…
Multi-Head Attention 설명 없음
Attention 설명 없음
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…
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…
Average Pooling 설명 없음
Linear Layer A Linear Layer is a projection $\mathbf{XW + b}$.
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…

Similar Papers 제목 키워드 기반

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

End-to-End Augmentation Hyperparameter Tuning for Self-Supervised Anomaly Detection

2023-06-21 · Jaemin Yoo, Lingxiao Zhao, Leman Akoglu

Self-supervised learning (SSL) has emerged as a promising paradigm that presents self-generated supervisory signals to real-world problems, bypassing the extensive manual labeling burden. SSL is especially attractive for…

Anomaly DetectionData AugmentationSelf-Supervised Anomaly DetectionSelf-Supervised Learning+1

Neural Weighted A*: Learning Graph Costs and Heuristics with Differentiable Anytime A*

2021-05-04 · Alberto Archetti, Marco Cannici, Matteo Matteucci

Recently, the trend of incorporating differentiable algorithms into deep learning architectures arose in machine learning research, as the fusion of neural layers and algorithmic layers has been beneficial for handling c…

Invariance Learning in Deep Neural Networks with Differentiable Laplace Approximations

2022-02-22 · Alexander Immer, Tycho F. A. van der Ouderaa, Gunnar Rätsch, Vincent Fortuin 외

Data augmentation is commonly applied to improve performance of deep learning by enforcing the knowledge that certain transformations on the input preserve the output. Currently, the data augmentation parameters are chos…

Data AugmentationGaussian ProcessesModel Selection

Deep differentiable reinforcement learning and optimal trading

2021-12-06 · Thibault Jaisson

In many reinforcement learning applications, the underlying environment reward and transition functions are explicitly known differentiable functions. This enables us to use recent research which applies machine learning…

Portfolio Optimizationreinforcement-learningReinforcement LearningReinforcement Learning (RL)