Signal recovery from Pooling Representations
نویسندگان
چکیده
In this work we compute lower Lipschitz bounds of lp pooling operators for p = 1, 2,∞ as well as lp pooling operators preceded by halfrectification layers. These give sufficient conditions for the design of invertible neural network layers. Numerical experiments on MNIST and image patches confirm that pooling layers can be inverted with phase recovery algorithms. Moreover, the regularity of the inverse pooling, controlled by the lower Lipschitz constant, is empirically verified with a nearest neighbor regression.
منابع مشابه
A Convolutional Neural Network based on Adaptive Pooling for Classification of Noisy Images
Convolutional neural network is one of the effective methods for classifying images that performs learning using convolutional, pooling and fully-connected layers. All kinds of noise disrupt the operation of this network. Noise images reduce classification accuracy and increase convolutional neural network training time. Noise is an unwanted signal that destroys the original signal. Noise chang...
متن کاملSparse Modeling of High - Dimensional Data for Learning and Vision
Sparse representations account for most or all of the information of a signal by a linear combination of a few elementary signals called atoms, and have increasingly become recognized as providing high performance for applications as diverse as noise reduction, compression, inpainting, compressive sensing, pattern classification, and blind source separation. In this dissertation, we learn the s...
متن کاملImproving Temporal Coherence of Image Features by Clustering Technique Learned from Moving Images
Object recognition is difficult because the appearance of an object changes in many different ways. To recognize objects robustly, one needs representations that are constant despite those changes. Such invariant representations can be obtained by features with low sensitivity to various visual transformations. Spatial pooling is a widely used technique for extracting invariant features from im...
متن کاملPooling Robust Shift-Invariant Sparse Representations of Acoustic Signals
In recent years, designing the coding and pooling structures in layered networks has been shown to be a useful method for learning high-level feature representations for visual data. Yet, such learning structures have not been extensively studied for audio signals. In this paper, we investigate different pooling strategies based on the sparse coding scheme and propose a temporal pyramid pooling...
متن کاملA Study on Low-Cost Representations for Image Feature Extraction on Mobile Devices
Due the limited battery life and wireless network bandwidth limitations, compact and fast (but also accurate) representations of image features are important for multimedia applications running on mobile devices. The main purpose of this work is to analyze the behavior of techniques for image feature extraction on mobile devices by considering the triple trade-off problem regarding effectivenes...
متن کامل