paper-with-me

Papers

Downsampling leads to Image Memorization in Convolutional Autoencoders

2019-05-01 · ICLR 2019 5 · Adityanarayanan Radhakrishnan, Caroline Uhler, Mikhail Belkin

Memorization of data in deep neural networks has become a subject of significant research interest. In this paper, we link memorization of images in deep convolutional autoencoders to downsampling through strided convolution. To analyze this mechanism in a simpler setting, we train linear convolutional autoencoders and show that linear combinations of training data are stored as eigenvectors in the linear operator corresponding to the network when downsampling is used. On the other hand, networks without downsampling do not memorize training data. We provide further evidence that the same effect happens in nonlinear networks. Moreover, downsampling in nonlinear networks causes the model to not only memorize just linear combinations of images, but individual training images. Since convolutional autoencoder components are building blocks of deep convolutional networks, we envision that our findings will shed light on the important phenomenon of memorization in over-parameterized deep networks.

📄 PDF Abstract BibTeX

Code (0)

등록된 구현이 없습니다.

Tasks

Memorization

Methods 이 논문이 사용한 방법론

Solana Customer Service Number +1-833-534-1729 설명 없음

Similar Papers 제목 키워드 기반

Memorization in Overparameterized Autoencoders

2018-10-16 · ICML Workshop Deep_Phenomen 2019 6 · Adityanarayanan Radhakrishnan, Karren Yang, Mikhail Belkin, Caroline Uhler

The ability of deep neural networks to generalize well in the overparameterized regime has become a subject of significant research interest. We show that overparameterized autoencoders exhibit memorization, a form of in…

Inductive BiasMemorization

Dropout the High-rate Downsampling: A Novel Design Paradigm for UHD Image Restoration

2024-11-10 · Chen Wu, Ling Wang, Long Peng, Dianjie Lu 외

With the popularization of high-end mobile devices, Ultra-high-definition (UHD) images have become ubiquitous in our lives. The restoration of UHD images is a highly challenging problem due to the exaggerated pixel count…

DeblurringImage DeblurringImage DehazingImage Enhancement+2

How Much Training Data is Memorized in Overparameterized Autoencoders? An Inverse Problem Perspective on Memorization Evaluation

2023-10-04 · Koren Abitbul, Yehuda Dar

Overparameterized autoencoder models often memorize their training data. For image data, memorization is often examined by using the trained autoencoder to recover missing regions in its training images (that were used o…

MemorizationRetrieval

Refining activation downsampling with SoftPool

2021-01-02 · ICCV 2021 10 · Alexandros Stergiou, Ronald Poppe, Grigorios Kalliatakis

Convolutional Neural Networks (CNNs) use pooling to decrease the size of activation maps. This process is crucial to increase the receptive fields and to reduce computational requirements of subsequent convolutions. An i…

Action Recognition

Towards Efficient and Accurate CT Segmentation via Edge-Preserving Probabilistic Downsampling

2024-04-05 · Shahzad Ali, Yu Rim Lee, Soo Young Park, Won Young Tak 외

Downsampling images and labels, often necessitated by limited resources or to expedite network training, leads to the loss of small objects and thin boundaries. This undermines the segmentation network's capacity to inte…

Image SegmentationMedical Image SegmentationSegmentationSemantic Segmentation