Alle Publikationen
- <<
- <
- 1
2018
-
(2018): Large Scale GAN Training for High Fidelity Natural Image Synthesis. Online verfügbar unter http://arxiv.org/pdf/1809.11096v2
Abstract: Despite recent progress in generative image modeling, successfully generating high-resolution, diverse samples from complex datasets such as ImageNet remains an elusive goal. To this end, we train Generative Adversarial Networks at the largest scale yet attempted, and study the instabilities specific to such scale. We find that applying orthogonal regularization to the generator renders it amenable to a simple "truncation trick," allowing fine control over the trade-off between sample fidelity and variety by reducing the variance of the Generator's input. Our modifications lead to models which set the new state of the art in class-conditional image synthesis. When trained on ImageNet at 128x128 resolution, our models (BigGANs) achieve an Inception Score (IS) of 166.5 and Frechet Inception Distance (FID) of 7.4, improving over the previous best IS of 52.52 and FID of 18.6.
-
(2018): Adversarial Examples that Fool both Computer Vision and Time-Limited Humans. In: Advances in Neural Information Processing Systems. Online verfügbar unter http://arxiv.org/pdf/1802.08195v3
Abstract: Machine learning models are vulnerable to adversarial examples: small changes to images can cause computer vision models to make mistakes such as identifying a school bus as an ostrich. However, it is still an open question whether humans are prone to similar mistakes. Here, we address this question by leveraging recent techniques that transfer adversarial examples from computer vision models with known parameters and architecture to other models with unknown parameters and architecture, and by matching the initial processing of the human visual system. We find that adversarial examples that strongly transfer across computer vision models influence the classifications made by time-limited human observers.
2012
-
(2012) : Building high-level features using large scale unsupervised learning In: Langford, John; Pineau, Joelle (Hg.): Proceedings of the 29th International Conference on Machine Learning: Edinburgh, Scotland, UK: Anderson, USA: Omnipress, S. 507-514. Online verfügbar unter http://arxiv.org/pdf/1112.6209v5
Abstract: We consider the problem of building high-level, class-specific feature detectors from only unlabeled data. For example, is it possible to learn a face detector using only unlabeled images? To answer this, we train a 9-layered locally connected sparse autoencoder with pooling and local contrast normalization on a large dataset of images (the model has 1 billion connections, the dataset has 10 million 200x200 pixel images downloaded from the Internet). We train this network using model parallelism and asynchronous SGD on a cluster with 1,000 machines (16,000 cores) for three days. Contrary to what appears to be a widely-held intuition, our experimental results reveal that it is possible to train a face detector without having to label images as containing a face or not. Control experiments show that this feature detector is robust not only to translation but also to scaling and out-of-plane rotation. We also find that the same network is sensitive to other high-level concepts such as cat faces and human bodies. Starting with these learned features, we trained our network to obtain 15.8% accuracy in recognizing 20,000 object categories from ImageNet, a leap of 70% relative improvement over the previous state-of-the-art.
Keywords: Bilderkennung, Computer Science - Learning, Gestalt, Katze, schema, Schematheorie, Youtube -
: Characterizing Types of Convolution in Deep Convolutional Recurrent Neural Networks for Robust Speech Emotion Recognition. Online verfügbar unter http://arxiv.org/pdf/1706.02901v2
Abstract: Deep convolutional neural networks are being actively investigated in a wide range of speech and audio processing applications including speech recognition, audio event detection and computational paralinguistics, owing to their ability to reduce factors of variations, for learning from speech. However, studies have suggested to favor a certain type of convolutional operations when building a deep convolutional neural network for speech applications although there has been promising results using different types of convolutional operations. In this work, we study four types of convolutional operations on different input features for speech emotion recognition under noisy and clean conditions in order to derive a comprehensive understanding. Since affective behavioral information has been shown to reflect temporally varying of mental state and convolutional operation are applied locally in time, all deep neural networks share a deep recurrent sub-network architecture for further temporal modeling. We present detailed quantitative module-wise performance analysis to gain insights into information flows within the proposed architectures. In particular, we demonstrate the interplay of affective information and the other irrelevant information during the progression from one module to another. Finally we show that all of our deep neural networks provide state-of-the-art performance on the eNTERFACE'05 corpus.
Keywords: Alter, Computer Science - Computation and Language, Computer Science - Learning, Computer Science - Multimedia, Computer Science - Sound, Emotionserkennung, Favoriten, Genderabhängigkeit, Mensch-Technik-Relationen (MTR), Realtechnik, Situationsbedingter Kontext, Sprachgebrauch, Stimme / Prosodie, Technik
- <<
- <
- 1