Representation Learning in Continuous-Time Score-Based Generative Models
- URL: http://arxiv.org/abs/2105.14257v1
- Date: Sat, 29 May 2021 09:26:02 GMT
- Title: Representation Learning in Continuous-Time Score-Based Generative Models
- Authors: Korbinian Abstreiter, Stefan Bauer, Arash Mehrjou
- Abstract summary: Training such models relies on denoising score matching, which can be seen as multi-scale denoising autoencoders.
Here, we augment the denoising score-matching framework to enable representation learning without any supervised signal.
In contrast, score-based representation learning relies on a new formulation of the denoising score-matching objective.
- Score: 19.990583896271573
- License: http://creativecommons.org/licenses/by/4.0/
- Abstract: Score-based methods represented as stochastic differential equations on a
continuous time domain have recently proven successful as a non-adversarial
generative model. Training such models relies on denoising score matching,
which can be seen as multi-scale denoising autoencoders. Here, we augment the
denoising score-matching framework to enable representation learning without
any supervised signal. GANs and VAEs learn representations by directly
transforming latent codes to data samples. In contrast, score-based
representation learning relies on a new formulation of the denoising
score-matching objective and thus encodes information needed for denoising. We
show how this difference allows for manual control of the level of detail
encoded in the representation.
Related papers
- Pivotal Auto-Encoder via Self-Normalizing ReLU [20.76999663290342]
We formalize single hidden layer sparse auto-encoders as a transform learning problem.
We propose an optimization problem that leads to a predictive model invariant to the noise level at test time.
Our experimental results demonstrate that the trained models yield a significant improvement in stability against varying types of noise.
arXiv Detail & Related papers (2024-06-23T09:06:52Z) - Audio-Visual Speech Enhancement with Score-Based Generative Models [22.559617939136505]
This paper introduces an audio-visual speech enhancement system that leverages score-based generative models.
We exploit audio-visual embeddings obtained from a self-super-vised learning model that has been fine-tuned on lipreading.
Experimental evaluations show that the proposed audio-visual speech enhancement system yields improved speech quality.
arXiv Detail & Related papers (2023-06-02T10:43:42Z) - Scalable Learning of Latent Language Structure With Logical Offline
Cycle Consistency [71.42261918225773]
Conceptually, LOCCO can be viewed as a form of self-learning where the semantic being trained is used to generate annotations for unlabeled text.
As an added bonus, the annotations produced by LOCCO can be trivially repurposed to train a neural text generation model.
arXiv Detail & Related papers (2023-05-31T16:47:20Z) - Solving Inverse Problems with Score-Based Generative Priors learned from
Noisy Data [1.7969777786551424]
SURE-Score is an approach for learning score-based generative models using training samples corrupted by additive Gaussian noise.
We demonstrate the generality of SURE-Score by learning priors and applying posterior sampling to ill-posed inverse problems in two practical applications.
arXiv Detail & Related papers (2023-05-02T02:51:01Z) - From Denoising Diffusions to Denoising Markov Models [38.33676858989955]
Denoising diffusions are state-of-the-art generative models exhibiting remarkable empirical performance.
We propose a unifying framework generalising this approach to a wide class of spaces and leading to an original extension of score matching.
arXiv Detail & Related papers (2022-11-07T14:34:27Z) - Learning with Neighbor Consistency for Noisy Labels [69.83857578836769]
We present a method for learning from noisy labels that leverages similarities between training examples in feature space.
We evaluate our method on datasets evaluating both synthetic (CIFAR-10, CIFAR-100) and realistic (mini-WebVision, Clothing1M, mini-ImageNet-Red) noise.
arXiv Detail & Related papers (2022-02-04T15:46:27Z) - Composable Augmentation Encoding for Video Representation Learning [94.2358972764708]
We focus on contrastive methods for self-supervised video representation learning.
A common paradigm in contrastive learning is to construct positive pairs by sampling different data views for the same instance, with different data instances as negatives.
We propose an 'augmentation aware' contrastive learning framework, where we explicitly provide a sequence of augmentation parameterisations.
We show that our method encodes valuable information about specified spatial or temporal augmentation, and in doing so also achieve state-of-the-art performance on a number of video benchmarks.
arXiv Detail & Related papers (2021-04-01T16:48:53Z) - Unsupervised Sound Localization via Iterative Contrastive Learning [106.56167882750792]
We propose an iterative contrastive learning framework that requires no data annotations.
We then use the pseudo-labels to learn the correlation between the visual and audio signals sampled from the same video.
Our iterative strategy gradually encourages the localization of the sounding objects and reduces the correlation between the non-sounding regions and the reference audio.
arXiv Detail & Related papers (2021-04-01T07:48:29Z) - CDLNet: Robust and Interpretable Denoising Through Deep Convolutional
Dictionary Learning [6.6234935958112295]
Unrolled optimization networks propose an interpretable alternative to constructing deep neural networks.
We show that the proposed model outperforms the state-of-the-art denoising models when scaled to similar parameter count.
arXiv Detail & Related papers (2021-03-05T01:15:59Z) - Autoencoding Variational Autoencoder [56.05008520271406]
We study the implications of this behaviour on the learned representations and also the consequences of fixing it by introducing a notion of self consistency.
We show that encoders trained with our self-consistency approach lead to representations that are robust (insensitive) to perturbations in the input introduced by adversarial attacks.
arXiv Detail & Related papers (2020-12-07T14:16:14Z) - Learning Noise-Aware Encoder-Decoder from Noisy Labels by Alternating
Back-Propagation for Saliency Detection [54.98042023365694]
We propose a noise-aware encoder-decoder framework to disentangle a clean saliency predictor from noisy training examples.
The proposed model consists of two sub-models parameterized by neural networks.
arXiv Detail & Related papers (2020-07-23T18:47:36Z)
This list is automatically generated from the titles and abstracts of the papers in this site.
This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.