We propose a composable framework for latent space image augmentation that allows for easy combination of multiple augmentations. Image augmentation has been shown to be an effective technique for improving the performance of a wide variety of image classification and generation tasks. Our framework is based on the Variational Autoencoder architecture and uses a novel approach for augmentation via linear transformation within the latent space itself. We explore losses and augmentation latent geometry to enforce the transformations to be composable and involuntary, thus allowing the transformations to be readily combined or inverted. Finally, we show these properties are better performing with certain pairs of augmentations, but we can transfer the latent space to other sets of augmentations to modify performance, effectively constraining the VAE's bottleneck to preserve the variance of specific augmentations and features of the image which we care about. We demonstrate the effectiveness of our approach with initial results on the MNIST dataset against both a standard VAE and a Conditional VAE. This latent augmentation method allows for much greater control and geometric interpretability of the latent space, making it a valuable tool for researchers and practitioners in the field.
CoCoEmo: Composable and Controllable Human-Like Emotional TTS via Activation Steering
The University of Melbourne, Australia（墨尔本大学）；Wuhan University, China（武汉大学）；The Hong Kong University of Science（香港科学与技术大学）；The University of Auckland, New Zealand（奥克兰大学）；Monash University, Australia（莫纳什大学）
University of Toronto（多伦多大学）；Vector Institute（向量学院）；Google Research（谷歌研究院）
We introduce Exemplar VAEs, a family of generative models that bridge the gap between parametric and non-parametric, exemplar based generative models. Exemplar VAE is a variant of VAE with a non-parametric prior in the latent space based on a Parzen window estimator. To sample from it, one first draws a random exemplar from a training set, then stochastically transforms that exemplar into a latent code and a new observation. We propose retrieval augmented training (RAT) as a way to speed up Exemplar VAE training by using approximate nearest neighbor search in the latent space to define a lower…
National University of Singapore（新加坡国立大学）；Singapore Management University（新加坡管理大学）
VAE, or variational auto-encoder, compresses data into latent attributes, and generates new data of different varieties. VAE based on KL divergence has been considered as an effective technique for data augmentation. In this paper, we propose the use of Wasserstein distance as a measure of distributional similarity for the latent attributes, and show its superior theoretical lower bound (ELBO) compared with that of KL divergence under mild conditions. Using multiple experiments, we demonstrate that the new loss function exhibits better convergence property and generates artificial images that …
DeepJEB++: Foundation Model-Driven Large-Scale 3D Engineering Dataset via 2D Latent Space Augmentation
Cho Chun Shik Graduate School of Mobility, Korea Advanced Institute of Science and Technology（韩国科学技术院赵春植移动研究生院）；Department of Mechanical Engineering, Hanyang University（汉阳大学机械工程系）；Narnia Labs（纳尼亚实验室）
Image classification datasets are often imbalanced, characteristic that negatively affects the accuracy of deep-learning classifiers. In this work we propose balancing GAN (BAGAN) as an augmentation tool to restore balance in imbalanced datasets. This is challenging because the few minority-class images may not be enough to train a GAN. We overcome this issue by including during the adversarial training all available images of majority and minority classes. The generative model learns useful features from majority classes and uses these to generate images for minority classes. We apply class c…
Interaction Asymmetry: A General Principle for Learning Composable Abstractions
Tübingen AI Center（蒂宾根人工智能中心）；ETH Zürich（苏黎世联邦理工学院）；Samsung - SAIT AI Lab, Montreal（三星- SAIT AI 实验室蒙特利尔分部）；Google DeepMind（谷歌DeepMind）；Max Planck Institute for Intelligent Systems（马克斯·普朗克智能系统研究所）；ELLIS Institute, Tübingen（ELLIS 研究所蒂宾根分部）
Diffusion-Based Data Augmentation for Medical Image Segmentation
School of Computer Science and Engineering, Beihang University（北京航空航天大学计算机科学与工程学院）；Dept. of Engineering for Innovation Medicine, University of Verona（威尼斯大学创新医学工程系）
Columbia University（哥伦比亚大学）；Nanyang Technological University（南洋理工大学）
Deep neural networks suffer from over-fitting and catastrophic forgetting when trained with small data. One natural remedy for this problem is data augmentation, which has been recently shown to be effective. However, previous works either assume that intra-class variances can always be generalized to new classes, or employ naive generation methods to hallucinate finite examples without modeling their latent distributions. In this work, we propose Covariance-Preserving Adversarial Augmentation Networks to overcome existing limits of low-shot learning. Specifically, a novel Generative Adversari…
Data augmentation is a widely adopted technique for avoiding overfitting when training deep neural networks. However, this approach requires domain-specific knowledge and is often limited to a fixed set of hard-coded transformations. Recently, several works proposed to use generative models for generating semantically meaningful perturbations to train a classifier. However, because accurate encoding and decoding are critical, these methods, which use architectures that approximate the latent-variable inference, remained limited to pilot studies on small datasets. Exploiting the exactly reversi…
Data61, CSIRO（联邦科学与工业研究组织数据61研究所）；University of New South Wales（新南威尔士大学）；University of Technology Sydney（悉尼科技大学）
In this paper, we consider the sigmoid Gaussian Hawkes process model: the baseline intensity and triggering kernel of Hawkes process are both modeled as the sigmoid transformation of random trajectories drawn from Gaussian processes (GP). By introducing auxiliary latent random variables (branching structure, Pólya-Gamma random variables and latent marked Poisson processes), the likelihood is converted to two decoupled components with a Gaussian form which allows for an efficient conjugate analytical inference. Using the augmented likelihood, we derive an expectation-maximization (EM) algorithm…
Domain mismatch between training and testing can lead to significant degradation in performance in many machine learning scenarios. Unfortunately, this is not a rare situation for automatic speech recognition deployments in real-world applications. Research on robust speech recognition can be regarded as trying to overcome this domain mismatch issue. In this paper, we address the unsupervised domain adaptation problem for robust speech recognition, where both source and target domain speech are presented, but word transcripts are only available for the source domain speech. We present novel au…
We propose a new scalable multi-class Gaussian process classification approach building on a novel modified softmax likelihood function. The new likelihood has two benefits: it leads to well-calibrated uncertainty estimates and allows for an efficient latent variable augmentation. The augmented model has the advantage that it is conditionally conjugate leading to a fast variational inference method via block coordinate ascent updates. Previous approaches suffered from a trade-off between uncertainty calibration and speed. Our experiments show that our method leads to well-calibrated uncertaint…
University of Tübingen（图宾根大学）；Max Planck Institute for Intelligent Systems（马克斯·普朗克智能系统研究所）
Generative modeling of 3D brain MRIs presents difficulties in achieving high visual fidelity while ensuring sufficient coverage of the data distribution. In this work, we propose to address this challenge with composable, multiscale morphological transformations in a variational autoencoder (VAE) framework. These transformations are applied to a chosen reference brain image to generate MRI volumes, equipping the model with strong anatomical inductive biases. We structure the VAE latent space in a way such that the model covers the data distribution sufficiently well. We show substantial perfor…
Kyushu Institute of Technology（九州工业大学）；RIKEN center for Advanced Intelligence Project（理化学研究所先进智能项目中心）
Imitation learning is an intuitive approach for teaching motion to robotic systems. Although previous studies have proposed various methods to model demonstrated movement primitives, one of the limitations of existing methods is that the shape of the trajectories are encoded in high dimensional space. The high dimensionality of the trajectory representation can be a bottleneck in the subsequent process such as planning a sequence of primitive motions. We address this problem by learning the latent space of the robot trajectory. If the latent variable of the trajectories can be learned, it can …
Imperial College London（帝国理工学院）；Technical University of Munich（慕尼黑工业大学）；Klinikum rechts der Isar（伊萨尔河右岸医院）；University of Edinburgh（爱丁堡大学）
Deep learning-based segmentation methods are vulnerable to unforeseen data distribution shifts during deployment, e.g. change of image appearances or contrasts caused by different scanners, unexpected imaging artifacts etc. In this paper, we present a cooperative framework for training image segmentation models and a latent space augmentation method for generating hard examples. Both contributions improve model generalization and robustness with limited data. The cooperative training framework consists of a fast-thinking network (FTN) and a slow-thinking network (STN). The FTN learns decoupled…
L-GTA: Latent Generative Modeling for Time Series Augmentation
Faculdade de Engenharia da Universidade do Porto（葡萄牙波尔图大学工程学院）；Fraunhofer Portugal AICOS（德国弗劳恩霍夫葡萄牙AICOS研究所）；University of Coimbra（科英布拉大学）；Dalhousie University（达尔豪斯大学）
Max Planck Institute for Intelligent Systems Tübingen（马克斯·普朗克智能系统研究所（蒂宾根））；University of Cambridge（剑桥大学）；Tübingen AI Center, University of Tübingen（蒂宾根大学蒂宾根人工智能中心）；IMPRS for Intelligent Systems（智能系统国际马克斯·普朗克研究学院）；Amazon（亚马逊）
Self-supervised representation learning has shown remarkable success in a number of domains. A common practice is to perform data augmentation via hand-crafted transformations intended to leave the semantics of the data invariant. We seek to understand the empirical success of this approach from a theoretical perspective. We formulate the augmentation process as a latent variable model by postulating a partition of the latent representation into a content component, which is assumed invariant to augmentation, and a style component, which is allowed to change. Unlike prior work on disentangleme…
We develop a novel data-driven nonlinear mixup mechanism for graph data augmentation and present different mixup functions for sample pairs and their labels. Mixup is a data augmentation method to create new training data by linearly interpolating between pairs of data samples and their labels. Mixup of graph data is challenging since the interpolation between graphs of potentially different sizes is an ill-posed operation. Hence, a promising approach for graph mixup is to first project the graphs onto a common latent feature space and then explore linear and nonlinear mixup strategies in this…
We present a discriminative nonparametric latent feature relational model (LFRM) for link prediction to automatically infer the dimensionality of latent features. Under the generic RegBayes (regularized Bayesian inference) framework, we handily incorporate the prediction loss with probabilistic inference of a Bayesian model; set distinct regularization parameters for different types of links to handle the imbalance issue in real networks; and unify the analysis of both the smooth logistic log-loss and the piecewise linear hinge loss. For the nonconjugate posterior inference, we present a simpl…
Imperial College London（帝国理工学院）；Middlesex University London（伦敦密德萨斯大学）
The rapid progress in machine learning methods has been empowered by i) huge datasets that have been collected and annotated, ii) improved engineering (e.g. data pre-processing/normalization). The existing datasets typically include several million samples, which constitutes their extension a colossal task. In addition, the state-of-the-art data-driven methods demand a vast amount of data, hence a standard engineering trick employed is artificial data augmentation for instance by adding into the data cropped and (affinely) transformed images. However, this approach does not correspond to any c…
Dropout and other feature noising schemes have shown promising results in controlling over-fitting by artificially corrupting the training data. Though extensive theoretical and empirical studies have been performed for generalized linear models, little work has been done for support vector machines (SVMs), one of the most successful approaches for supervised learning. This paper presents dropout training for both linear SVMs and the nonlinear extension with latent representation learning. For linear SVMs, to deal with the intractable expectation of the non-smooth hinge loss under corrupting d…
Adapting Technical-Service LLM Agents with Latent Logic Augmentation, Robust Noise Reduction, and Hybrid Reward Modeling
School of Mathematics and Sciences, Fudan University, Shanghai, China（复旦大学数学科学学院，上海，中国）；Shanghai Center for Mathematical Sciences, Fudan University, Shanghai, China（复旦大学上海数学中心，上海，中国）；Alibaba Group, Hangzhou, China（阿里巴巴集团，杭州，中国）；Institute of Science and Technology for Brain-Inspired Intelligence, Fudan University, Shanghai, China（脑启发式智能科学技术研究院，复旦大学，上海，中国）；Center for Applied Mathematics & Shanghai Key Laboratory of Contemporary Applied Mathematics, Fudan University, Shanghai, China（应用数学中心及上海当代应用数学重点实验室，复旦大学，上海，中国）
The University of Sydney（悉尼大学）；ByteDance AI Lab（字节跳动人工智能实验室）；University of California San Diego（加利福尼亚大学圣迭戈分校）
Existing graph contrastive learning methods rely on augmentation techniques based on random perturbations (e.g., randomly adding or dropping edges and nodes). Nevertheless, altering certain edges or nodes can unexpectedly change the graph characteristics, and choosing the optimal perturbing ratio for each dataset requires onerous manual tuning. In this paper, we introduce Implicit Graph Contrastive Learning (iGCL), which utilizes augmentations in the latent space learned from a Variational Graph Auto-Encoder by reconstructing graph topological structure. Importantly, instead of explicitly samp…
Training models with discrete latent variables is challenging due to the difficulty of estimating the gradients accurately. Much of the recent progress has been achieved by taking advantage of continuous relaxations of the system, which are not always available or even possible. The Augment-REINFORCE-Merge (ARM) estimator provides an alternative that, instead of relaxation, uses continuous augmentation. Applying antithetic sampling over the augmenting variables yields a relatively low-variance and unbiased estimator applicable to any model with binary latent variables. However, while antitheti…
