Multi-modal learning relates information across observation modalities of the same physical phenomenon to leverage complementary information. Most multi-modal machine learning methods require that all the modalities used for training are also available for testing. This is a limitation when the signals from some modalities are unavailable or are severely degraded by noise. To address this limitation, we aim to improve the testing performance of uni-modal systems using multiple modalities during training only. The proposed multi-modal training framework uses cross-modal translation and correlation-based latent space alignment to improve the representations of the weaker modalities. The translation from the weaker to the stronger modality generates a multi-modal intermediate encoding that is representative of both modalities. This encoding is then correlated with the stronger modality representations in a shared latent space. We validate the proposed approach on the AVEC 2016 dataset for continuous emotion recognition and show the effectiveness of the approach that achieves state-of-the-art (uni-modal) performance for weaker modalities.
We propose Mask CycleGAN, a novel architecture for unpaired image domain translation built based on CycleGAN, with an aim to address two issues: 1) unimodality in image translation and 2) lack of interpretability of latent variables. Our innovation in the technical approach is comprised of three key components: masking scheme, generator and objective. Experimental results demonstrate that this architecture is capable of bringing variations to generated images in a controllable manner and is reasonably robust to different masks.
The Blavatnik School of Computer Science（布拉瓦特尼克计算机科学学院）；Tel Aviv University（特拉维夫大学）
Latent alignment objectives such as CTC and AXE significantly improve non-autoregressive machine translation models. Can they improve autoregressive models as well? We explore the possibility of training autoregressive machine translation models with latent alignment objectives, and observe that, in practice, this approach results in degenerate models. We provide a theoretical explanation for these empirical results, and prove that latent alignment objectives are incompatible with teacher forcing.
School of Electronics and Information Technology, Sun Yat-sen University（中山大学电子与信息工程学院）
Learning joint embedding space for various modalities is of vital importance for multimodal fusion. Mainstream modality fusion approaches fail to achieve this goal, leaving a modality gap which heavily affects cross-modal fusion. In this paper, we propose a novel adversarial encoder-decoder-classifier framework to learn a modality-invariant embedding space. Since the distributions of various modalities vary in nature, to reduce the modality gap, we translate the distributions of source modalities into that of target modality via their respective encoders using adversarial training. Furthermore…
From Orthogonality to Dependency: Learning Disentangled Representation for Multi-Modal Time-Series Sensing Signals
School of Computer Science, Guangdong University of Technology（广东工业大学计算机学院）；Mohamed bin Zayed University of Artificial Intelligence（穆罕默德·本·扎耶德人工智能大学）；Shantou University（汕头大学）；Carnegie Mellon University（卡内基梅隆大学）
Tel Aviv University（特拉维夫大学）；Hebrew University Jerusalem（耶路撒冷希伯来大学）
Recent GAN-based architectures have been able to deliver impressive performance on the general task of image-to-image translation. In particular, it was shown that a wide variety of image translation operators may be learned from two image sets, containing images from two different domains, without establishing an explicit pairing between the images. This was made possible by introducing clever regularizers to overcome the under-constrained nature of the unpaired translation problem. In this work, we introduce a novel architecture for unpaired image translation, and explore several new regular…
Multimodal sentiment analysis is a core research area that studies speaker sentiment expressed from the language, visual, and acoustic modalities. The central challenge in multimodal learning involves inferring joint representations that can process and relate information from these modalities. However, existing work learns joint representations by requiring all modalities as input and as a result, the learned representations may be sensitive to noisy or missing modalities at test time. With the recent success of sequence to sequence (Seq2Seq) models in machine translation, there is an opportu…
This paper presents two strong methods, CTC and Imputer, for non-autoregressive machine translation that model latent alignments with dynamic programming. We revisit CTC for machine translation and demonstrate that a simple CTC model can achieve state-of-the-art for single-step non-autoregressive machine translation, contrary to what prior work indicates. In addition, we adapt the Imputer model for non-autoregressive machine translation and demonstrate that Imputer with just 4 generation steps can match the performance of an autoregressive Transformer baseline. Our latent alignment models are …
Image-to-image translation aims to preserve source contents while translating to discriminative target styles between two visual domains. Most works apply adversarial learning in the ambient image space, which could be computationally expensive and challenging to train. In this paper, we propose to deploy an energy-based model (EBM) in the latent space of a pretrained autoencoder for this task. The pretrained autoencoder serves as both a latent code extractor and an image reconstruction worker. Our model, LETIT, is based on the assumption that two domains share the same latent space, where lat…
INSA Rouen Normandie（诺曼底鲁昂国立应用科学学院）；Univ Rouen Normandie（诺曼底鲁昂大学）；LITIS UR 4108（LITIS 4108联合研究单位）
In this paper, we investigate the problem of multi-domain translation: given an element $a$ of domain $A$, we would like to generate a corresponding $b$ sample in another domain $B$, and vice versa. Acquiring supervision in multiple domains can be a tedious task, also we propose to learn this translation from one domain to another when supervision is available as a pair $(a,b)\sim A\times B$ and leveraging possible unpaired data when only $a\sim A$ or only $b\sim B$ is available. We introduce a new unified framework called Latent Space Mapping (\model) that exploits the manifold assumption in …
University of Trento（特伦托大学）；Tencent AI Lab（腾讯人工智能实验室）；Fondazione Bruno Kessler（布鲁诺·凯塞勒基金会）
Image-to-Image (I2I) multi-domain translation models are usually evaluated also using the quality of their semantic interpolation results. However, state-of-the-art models frequently show abrupt changes in the image appearance during interpolation, and usually perform poorly in interpolations across domains. In this paper, we propose a new training protocol based on three specific losses which help a translation network to learn a smooth and disentangled latent style space in which: 1) Both intra- and inter-domain interpolations correspond to gradual changes in the generated images and 2) The …
The University of Tokyo（东京大学）；New York University（纽约大学）；Facebook AI Research（脸书人工智能研究院）
Although neural machine translation models reached high translation quality, the autoregressive nature makes inference difficult to parallelize and leads to high translation latency. Inspired by recent refinement-based approaches, we propose LaNMT, a latent-variable non-autoregressive model with continuous latent variables and deterministic inference procedure. In contrast to existing approaches, we use a deterministic inference algorithm to find the target sequence that maximizes the lowerbound to the log-probability. During inference, the length of translation automatically adapts itself. Ou…
University of Illinois at Urbana-Champaign（伊利诺伊大学厄巴纳-香槟分校）；University at Buffalo（布法罗大学）；Amazon（亚马逊）
Contrastive loss has been increasingly used in learning representations from multiple modalities. In the limit, the nature of the contrastive loss encourages modalities to exactly match each other in the latent space. Yet it remains an open question how the modality alignment affects the downstream task performance. In this paper, based on an information-theoretic argument, we first prove that exact modality alignment is sub-optimal in general for downstream prediction tasks. Hence we advocate that the key of better performance lies in meaningful latent modality structures instead of perfect m…
Multi-modal generative models represent an important family of deep models, whose goal is to facilitate representation learning on data with multiple views or modalities. However, current deep multi-modal models focus on the inference of shared representations, while neglecting the important private aspects of data within individual modalities. In this paper, we introduce a disentangled multi-modal variational autoencoder (DMVAE) that utilizes disentangled VAE strategy to separate the private and shared latent spaces of multiple modalities. We specifically consider the instance where the laten…
One task that is often discussed in a computer vision is the mapping of an image from one domain to a corresponding image in another domain known as image-to-image translation. Currently there are several approaches solving this task. In this paper, we present an enhancement of the UNIT framework that aids in removing its main drawbacks. More specifically, we introduce an additional adversarial discriminator on the latent representation used instead of VAE, which enforces the latent space distributions of both domains to be similar. On MNIST and USPS domain adaptation tasks, this approach grea…
Seoul National University（首尔大学）；Samsung SDS（三星SDS）；Samsung Research（三星研究院）
In this paper, we propose a novel structure for a cross-modal data association, which is inspired by the recent research on the associative learning structure of the brain. We formulate the cross-modal association in Bayesian inference framework realized by a deep neural network with multiple variational auto-encoders and variational associators. The variational associators transfer the latent spaces between auto-encoders that represent different modalities. The proposed structure successfully associates even heterogeneous modal data and easily incorporates the additional modality to the entir…
Diffusion based Zero-shot Medical Image-to-Image Translation for Cross Modality Segmentation
Athinoula A. Martinos Center for Biomedical Imaging（阿西诺拉·A.马蒂诺斯生物医学成像中心）；Massachusetts General Hospital（麻省总医院）；Harvard University（哈佛大学）；Inria centre at Université Côte d’Azur（蔚蓝海岸大学国家信息与自动化研究所中心）；Temple University（天普大学）；Georg-August-University of Göttingen（哥廷根大学）
Centre Inria d’Université Côte d’Azur（蔚蓝海岸大学法国国家信息与自动化研究所中心）
Cross-modality data translation has attracted great interest in image computing. Deep generative models (\textit{e.g.}, GANs) show performance improvement in tackling those problems. Nevertheless, as a fundamental challenge in image translation, the problem of Zero-shot-Learning Cross-Modality Data Translation with fidelity remains unanswered. This paper proposes a new unsupervised zero-shot-learning method named Mutual Information guided Diffusion cross-modality data translation Model (MIDiffusion), which learns to translate the unseen source data to the target domain. The MIDiffusion leverag…
We propose VecGAN, an image-to-image translation framework for facial attribute editing with interpretable latent directions. Facial attribute editing task faces the challenges of precise attribute editing with controllable strength and preservation of the other attributes of an image. For this goal, we design the attribute editing by latent space factorization and for each attribute, we learn a linear direction that is orthogonal to the others. The other component is the controllable strength of the change, a scalar value. In our framework, this scalar can be either sampled or encoded from a …
Seoul National University（首尔国立大学）；University of California, Davis（加州大学戴维斯分校）
Novelty detection using deep generative models such as autoencoder, generative adversarial networks mostly takes image reconstruction error as novelty score function. However, image data, high dimensional as it is, contains a lot of different features other than class information which makes models hard to detect novelty data. The problem gets harder in multi-modal normality case. To address this challenge, we propose a new way of measuring novelty score in multi-modal normality cases using orthogonalized latent space. Specifically, we employ orthogonal low-rank embedding in the latent space t…
Massachusetts Institute of Technology（麻省理工学院）；New York Structural Biology Center（纽约结构生物学中心）
Given an image dataset, we are often interested in finding data generative factors that encode semantic content independently from pose variables such as rotation and translation. However, current disentanglement approaches do not impose any specific structure on the learned latent representations. We propose a method for explicitly disentangling image rotation and translation from other unstructured latent factors in a variational autoencoder (VAE) framework. By formulating the generative model as a function of the spatial coordinate, we make the reconstruction error differentiable with respe…
Samsung AI Center Cambridge（三星剑桥人工智能中心）；Rutgers University（罗格斯大学）
We deal with the problem of learning the underlying disentangled latent factors that are shared between the paired bi-modal data in cross-modal retrieval. Our assumption is that the data in both modalities are complex, structured, and high dimensional (e.g., image and text), for which the conventional deep auto-encoding latent variable models such as the Variational Autoencoder (VAE) often suffer from difficulty of accurate decoder training or realistic synthesis. A suboptimally trained decoder can potentially harm the model's capability of identifying the true factors. In this paper we propos…
Generative adversarial networks have led to significant advances in cross-modal/domain translation. However, typically these networks are designed for a specific task (e.g., dialogue generation or image synthesis, but not both). We present a unified model, M3D-GAN, that can translate across a wide range of modalities (e.g., text, image, and speech) and domains (e.g., attributes in images or emotions in speech). Our model consists of modality subnets that convert data from different modalities into unified representations, and a unified computing body where data from different modalities share …
Many important problems in the real world don't have unique solutions. It is thus important for machine learning models to be capable of proposing different plausible solutions with meaningful probability measures. In this work we introduce such a deep learning framework that learns the one-to-many mappings between the inputs and outputs, together with faithful uncertainty measures. We call our framework {\it modal uncertainty estimation} since we model the one-to-many mappings to be generated through a set of discrete latent variables, each representing a latent mode hypothesis that explains …
LatentVerse: A Framework for Understanding Shared and Modality-Specific Information in Multimodal Latent Representations
Broad Institute of MIT and Harvard（麻省理工学院和哈佛大学布罗德研究所）；Massachusetts Institute of Technology（麻省理工学院）；The Schmidt Center, Broad Institute of MIT and Harvard（麻省理工学院和哈佛大学布罗德研究所施密特中心）
University of Trento（特伦托大学）；Fondazione Bruno Kessler（布鲁诺·凯斯勒基金会）；University of Modena and Reggio Emilia（摩德纳-雷焦艾米利亚大学）；Shanghai Jiao Tong University（上海交通大学）；Tencent AI Lab（腾讯人工智能实验室）
Multi-domain image-to-image (I2I) translations can transform a source image according to the style of a target domain. One important, desired characteristic of these transformations, is their graduality, which corresponds to a smooth change between the source and the target image when their respective latent-space representations are linearly interpolated. However, state-of-the-art methods usually perform poorly when evaluated using inter-domain interpolations, often producing abrupt changes in the appearance or non-realistic intermediate images. In this paper, we argue that one of the main re…
Normandie Univ, INSA Rouen, UNIROUEN, UNIHAVRE, LITIS（诺曼底大学，鲁昂国立应用科学学院，鲁昂大学，勒阿弗尔大学，LITIS）；Department of Nuclear Medicine, Henri Becquerel Cancer Center（亨利·贝克勒尔癌症中心核医学科）
Multimodal MR images can provide complementary information for accurate brain tumor segmentation. However, it's common to have missing imaging modalities in clinical practice. Since there exists a strong correlation between multi modalities, a novel correlation representation block is proposed to specially discover the latent multi-source correlation. Thanks to the obtained correlation representation, the segmentation becomes more robust in the case of missing modalities. The model parameter estimation module first maps the individual representation produced by each encoder to obtain independe…
End-to-end optimization has achieved state-of-the-art performance on many specific problems, but there is no straight-forward way to combine pretrained models for new problems. Here, we explore improving modularity by learning a post-hoc interface between two existing models to solve a new task. Specifically, we take inspiration from neural machine translation, and cast the challenging problem of cross-modal domain transfer as unsupervised translation between the latent spaces of pretrained deep generative models. By abstracting away the data representation, we demonstrate that it is possible …
University of Chinese Academy of Sciences（中国科学院大学）；Institute of Computing Technology, Chinese Academy of Sciences（中国科学院计算技术研究所）；Noah’s Ark Lab（诺亚方舟实验室）；The University of Texas at San Antonio（德克萨斯大学圣安东尼奥分校）
Multimodal learning aims to discover the relationship between multiple modalities. It has become an important research topic due to extensive multimodal applications such as cross-modal retrieval. This paper attempts to address the modality heterogeneity problem based on Gaussian process latent variable models (GPLVMs) to represent multimodal data in a common space. Previous multimodal GPLVM extensions generally adopt individual learning schemes on latent representations and kernel hyperparameters, which ignore their intrinsic relationship. To exploit strong complementarity among different mod…
Simultaneous EEG-fMRI is a multi-modal neuroimaging technique that provides complementary spatial and temporal resolution. Challenging has been developing principled and interpretable approaches for fusing the modalities, specifically approaches enabling inference of latent source spaces representative of neural activity. In this paper, we address this inference problem within the framework of transcoding -- mapping from a specific encoding (modality) to a decoding (the latent source space) and then encoding the latent source space to the other modality. Specifically, we develop a symmetric me…
While deep learning methods have shown great success in medical image analysis, they require a number of medical images to train. Due to data privacy concerns and unavailability of medical annotators, it is oftentimes very difficult to obtain a lot of labeled medical images for model training. In this paper, we study cross-modality data augmentation to mitigate the data deficiency issue in the medical imaging domain. We propose a discriminative unpaired image-to-image translation model which translates images in source modality into images in target modality where the translation task is condu…
ASLSL: Adaptive shared latent structure learning with incomplete multi-modal physiological data for multi-dimensional emotional feature selection
School of Information Science and Technology, Beijing University of Technology, Beijing 100124, China（信息科学与技术学院，北京理工大学，北京）；School of Artificial Intelligence, Anhui University, Beijing 100124, China（人工智能学院，安徽大学，北京）
Deep learning techniques, especially Generative Adversarial Networks (GANs) have significantly improved image inpainting and image-to-image translation tasks over the past few years. To the best of our knowledge, the problem of combining the image inpainting task with the multi-modality image-to-image translation remains intact. In this paper, we propose a model to address this problem. The model will be evaluated on combined night-to-day image translation and inpainting, along with promising qualitative and quantitative results.
