This research shows how to learn shared representations from unpaired data.
problem Learning shared representations from unpaired data.
method Spectral embeddings of random walk matrices from each unimodal representation.
result Shared representations can be learned almost exclusively from unpaired data.
The paper proves probabilistic alignment between unseen modalities using contrastive learning.
problem Aligning unseen modalities in unsupervised learning.
method Bayesian approach and direct comparison of contrastive representations.
result Direct comparison of contrastive representations recovers the same likelihood ratio as probabilistic graphical models.
New method identifies shared components from unpaired multimodal mixtures.
problem Identify shared components from unpaired multimodal mixtures.
method Distribution divergence minimization-based loss with sufficient conditions for identifiability.
result Sufficient conditions for shared component identifiability from unaligned multimodal mixtures.
Paper investigates multimodal contrastive learning and incorporates unpaired data.
problem Improving feature learning ability of multimodal models under noisy data.
method Initiates investigation of nonlinear loss functions for multimodal contrastive learning, analyzes performance, proposes new loss incorporating unpaired data.
result MMCL can outperform unimodal contrastive learning and robustly handle noisy data.
Paper presents a method to align unpaired samples across different modalities.
problem Challenges in collecting paired samples for multimodal representation learning.
method Uses propensity score alignment based on Rubin's framework to estimate a common space for unpaired samples.
result Optimal transport matching significantly improves alignment in real-world data.
Magnetic Resonance Imaging (MRI) of the brain can come in the form of different modalities such as T1-weighted and Fluid Attenuated Inversion Recovery (FLAIR) which has been used to investigate a wide range of neurological disorders. Current state-of-the-art models for brain tissue segmentation and disease classificati…
Increasingly many real world tasks involve data in multiple modalities or views. This has motivated the development of many effective algorithms for learning a common latent space to relate multiple domains. However, most existing cross-view learning algorithms assume access to paired data for training. Their applicabi…
Model learns association between text and speech without paired data.
problem Learning association between text and speech with limited paired data.
method Noisy channel generative model with variational inference and KL encoder loss.
result Tiny paired data (5 minutes) sufficient to learn association.
TAP transfers knowledge from unlabeled data to improve cross-modal learning.
problem Improving supervised learning performance using unlabeled data from a different modality.
method Probabilistic approach for missing information estimation, kernel regression, cross-attention module, TAP neural network.
result TAP significantly improves generalization across different domains and neural network architectures.
This paper tackles unpaired data in multi-view learning, proposing a new framework and models.
problem Handling unpaired data in multi-view learning, which is more common than paired data.
method Generalized uncorrelated multi-view subspace learning framework with successive alternating approximation (SAA) method.
result Proposed models perform competitively or better than baselines in multi-view feature extraction and multi-modality classification.
Creating large scale high-quality annotations is a known challenge in medical imaging. In this work, based on the CycleGAN algorithm, we propose leveraging annotations from one modality to be useful in other modalities. More specifically, the proposed algorithm creates highly realistic synthetic CT images (SynCT) from …
DDSTN improves breast cancer diagnosis by leveraging imbalanced ultrasound modalities.
problem Imbalanced ultrasound modalities in diagnosing breast cancer.
method Integrates LUPI and MMD into a deep transfer learning framework.
result Outperforms state-of-the-art algorithms in BUS-based CAD.
UNSB uses neural Schrödinger Bridge to solve unpaired image-to-image translation.
problem Difficulties in unpaired image-to-image translation with diffusion models.
method Expresses SB problem as adversarial learning problems, incorporating advanced discriminators and regularization.
result Successfully solves various unpaired image-to-image translation tasks.
Develops a contrastive framework for data-efficient multimodal learning.
problem Expensive training of multimodal generative models requiring related multimodal data.
method Contrastive framework for multimodal learning, distinguishing related from unrelated data.
result Data-efficient multimodal learning on challenging datasets for various VAE models.
We address the problems of multi-domain and single-domain regression based on distinct and unpaired labeled training sets for each of the domains and a large unlabeled training set from all domains. We formulate these problems as a Bayesian estimation with partial knowledge of statistical relations. We propose a worst-…
The paper tightens bounds for estimating Schrödinger potentials in unpaired data translation.
problem Estimating Schrödinger potentials in unpaired data translation.
method Using stochastic optimal control and Ornstein-Uhlenbeck process, the paper derives tight bounds on the generalization ability of an empirical risk minimizer.
result The approach achieves almost optimal convergence rates for Gaussian mixtures.
Unpaired multi-domain causal representation learning is possible with sufficient conditions.
problem Learning shared causal representation from unpaired data across domains.
method Identify sufficient conditions for joint distribution and shared causal graph recovery.
result Practical method to recover shared latent causal graph from marginal distributions.
The paper analyzes CycleGAN's error components for unpaired data generation.
problem Analyzing approximation and estimation errors in CycleGAN for unpaired data.
method Decomposes risk into approximation and estimation errors, analyzing each separately and considering their trade-offs.
result Theoretical insights into CycleGAN's performance through error analysis.
Unpaired deep learning reconstructs MRI images from accelerated data.
problem Difficulty in acquiring matched fully sampled k-space data for supervised deep learning.
method Optimal transport driven cycleGAN architecture.
result Reconstructs high resolution MR images from accelerated k-space data.
LSDM uses unpaired data to match latent space distributions for generative modeling.
problem Generating high-quality images with limited paired data.
method Two-stage approach: latent space learning from paired and unpaired data, followed by joint distribution matching.
result LSDM enhances geometric fidelity in generated outputs and provides theoretical insights into LDMs.
New algorithm computes Schrödinger Bridge for unpaired data translation.
problem Computing optimal transport maps for unpaired data translation.
method Schrödinger Bridge Flow, a discretization of a flow of path measures.
result Eliminates the need to train multiple DDM-like models.
A new method for image translation without paired data.
problem Image-to-image translation between two domains with content preservation.
method Energy-based model in latent space of pretrained autoencoder.
result Improved translation quality and content preservation.
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 expl…
Synthetic image translation has significant potentials in autonomous transportation systems. That is due to the expense of data collection and annotation as well as the unmanageable diversity of real-words situations. The main issue with unpaired image-to-image translation is the ill-posed nature of the problem. In thi…
Study on estimating causal effects with limited data and multiple environments.
problem Estimating causal effects under hidden confounding with unpaired data and sparse effects.
method Instrumental variable (IV) regression with cross-fold sample splitting and ℓ1-regularized estimation. result Proposed GMM-type estimator is consistent as the number of environments grows.
DPOT uses deep learning to compute optimal transport efficiently.
problem Computing optimal transport between continuous distributions from unpaired samples.
method DeepParticle methods for min-min optimization without network structure restrictions.
result Established weak convergence and error bounds between learned and optimal maps.
We tackle unsupervised anomaly detection (UAD), a problem of detecting data that significantly differ from normal data. UAD is typically solved by using density estimation. Recently, deep neural network (DNN)-based density estimators, such as Normalizing Flows, have been attracting attention. However, one of their draw…
FDBM models use fractional Brownian motion to model complex stochastic processes.
problem Capturing memory effects and long-range dependencies in stochastic processes.
method Developed a generative diffusion bridge framework using a Markovian approximation of fractional Brownian motion.
result FDBM outperforms standard models in predicting future states and unpaired data translation.
There has been remarkable recent work in unpaired image-to-image translation. However, they're restricted to translation on single pairs of distributions, with some exceptions. In this study, we extend one of these works to a scalable multidistribution translation mechanism. Our translation models not only converts fro…
The paper proposes a method to estimate joint probability from unpaired data using entropic transport kernels.
problem Estimating joint probability from unpaired data with unknown internal ordering.
method Maximum-likelihood inference, entropic optimal transport kernels, EMML algorithm.
result The method can recover true density from empirical approximations as the number of blocks increases.
A new method improves robustness in image translation by modeling uncertainty.
problem Performance degradation in image translation models due to lack of robustness to outliers and uncertainty.
method UGAC method based on Uncertainty-aware Generalized Adaptive Cycle Consistency, modeling per-pixel residual with generalized Gaussian distribution.
result Our method exhibits stronger robustness towards unseen perturbations in test data.
Adaptive anchor methods improve multi-modal learning by balancing intra-modal and inter-modal information.
problem Fixed anchor methods limit multi-modal learning by over-reliance on a single modality and inadequate cross-modal correlation.
method Adaptive anchor methods using centroid-based anchors from all modalities.
result Adaptive anchor methods like CentroBind consistently outperform fixed anchor methods across various datasets.
Current multi-reference style transfer models for Text-to-Speech (TTS) perform sub-optimally on disjoints datasets, where one dataset contains only a single style class for one of the style dimensions. These models generally fail to produce style transfer for the dimension that is underrepresented in the dataset. In th…
Spatial studies of transcriptome provide biologists with gene expression maps of heterogeneous and complex tissues. However, most experimental protocols for spatial transcriptomics suffer from the need to select beforehand a small fraction of genes to be quantified over the entire transcriptome. Standard single-cell RN…
KD-Net transfers knowledge from multi-modal to mono-modal segmentation networks.
problem Limited acquisition of multiple imaging modalities in clinical settings.
method Generalized distillation framework adapted for mono-modal networks.
result The student network outperforms baseline mono-modal networks in brain tumor segmentation.
MHVAE learns cross-modality inference inspired by human cognition.
problem Cross-modality inference in multimodal data.
method Hierarchical multimodal generative model with modality-specific and joint-modality distributions.
result MHVAE performs on par with state-of-the-art models on multimodal datasets.
The paper analyzes and proposes an algorithm for multi-modal nonlinear embeddings with theoretical performance bounds.
problem Generalizability of multi-modal nonlinear embeddings to unseen data.
method Theoretical analysis and a multi-modal nonlinear representation learning algorithm motivated by performance bounds.
result The proposed algorithm yields promising performance in multi-modal image classification and cross-modal image-text retrieval applications.
COBRA reduces modality gap in cross-modal tasks.
problem Joint embedding spaces fail to sufficiently reduce modality gap in multi-modal tasks.
method COBRA trains image and text modalities in a joint fashion using Contrastive Predictive Coding and Noise Contrastive Estimation.
result COBRA significantly reduces the modality gap and generates robust joint-embedding space.
Proposes a novel network for CTR prediction by learning modality-specific and modality-invariant representations.
problem Learning good representation of items from multimodal features in E-commerce is challenging due to redundant information across modalities.
method Introduces a Multimodal Adversarial Representation Network (MARN) that calculates modality-specific weights and learns modality-invariant representations.
result Consistently achieves remarkable improvements over state-of-the-art methods in CTR prediction.
Combining complementary information from multiple modalities is intuitively appealing for improving the performance of learning-based approaches. However, it is challenging to fully leverage different modalities due to practical challenges such as varying levels of noise and conflicts between modalities. Existing metho…
We investigate deep generative models that can exchange multiple modalities bi-directionally, e.g., generating images from corresponding texts and vice versa. Recently, some studies handle multiple modalities on deep generative models, such as variational autoencoders (VAEs). However, these models typically assume that…
Improves video search by balancing text and visual modalities.
problem Modality imbalance in video search models, focusing mainly on text matching.
method Proposes MBVR with MS samples and DM to balance modalities.
result Empirically shows significant improvement in modality balance and search effectiveness.
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 l…
MoCA uses a novel autoencoder to analyze multi-modal health data.
problem Challenges in analyzing continuous multi-modal health data from wearable devices.
method Proposes MoCA, a self-supervised learning framework combining transformer and masked autoencoder methods.
result Demonstrates strong performance boosts across reconstruction and classification tasks.
We explore training an automatic modality tagger. Modality is the attitude that a speaker might have toward an event or state. One of the main hurdles for training a linguistic tagger is gathering training data. This is particularly problematic for training a tagger for modality because modality triggers are sparse for…
Obtaining common representations from different modalities is important in that they are interchangeable with each other in a classification problem. For example, we can train a classifier on image features in the common representations and apply it to the testing of the text features in the representations. Existing m…
Framework for handling long-tailed multi-modal data.
problem Class imbalance and long-tailed distributions in multi-modal data.
method Multi-expert architecture with modality-specific networks and dynamic fusion weights.
result Framework outperforms existing methods in long-tailed, class-imbalanced scenarios.
Learning generative models that span multiple data modalities, such as vision and language, is often motivated by the desire to learn more useful, generalisable representations that faithfully capture common underlying factors between the modalities. In this work, we characterise successful learning of such models as t…