Learning Multimodal VAEs through Mutual Supervision

• URL: http://arxiv.org/abs/2106.12570v1
• Date: Wed, 23 Jun 2021 17:54:35 GMT
• Title: Learning Multimodal VAEs through Mutual Supervision
• Authors: Tom Joy, Yuge Shi, Philip H.S. Torr, Tom Rainforth, Sebastian M. Schmon, N. Siddharth
• Abstract summary: MEME combines information between modalities implicitly through mutual supervision. We demonstrate that MEME outperforms baselines on standard metrics across both partial and complete observation schemes.
• Score: 72.77685889312889
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: Multimodal VAEs seek to model the joint distribution over heterogeneous data (e.g.\ vision, language), whilst also capturing a shared representation across such modalities. Prior work has typically combined information from the modalities by reconciling idiosyncratic representations directly in the recognition model through explicit products, mixtures, or other such factorisations. Here we introduce a novel alternative, the MEME, that avoids such explicit combinations by repurposing semi-supervised VAEs to combine information between modalities implicitly through mutual supervision. This formulation naturally allows learning from partially-observed data where some modalities can be entirely missing -- something that most existing approaches either cannot handle, or do so to a limited extent. We demonstrate that MEME outperforms baselines on standard metrics across both partial and complete observation schemes on the MNIST-SVHN (image-image) and CUB (image-text) datasets. We also contrast the quality of the representations learnt by mutual supervision against standard approaches and observe interesting trends in its ability to capture relatedness between data.

Related papers

• Enhancing Unimodal Latent Representations in Multimodal VAEs through Iterative Amortized Inference [20.761803725098005]
  Multimodal variational autoencoders (VAEs) aim to capture shared latent representations by integrating information from different data modalities. A significant challenge is accurately inferring representations from any subset of modalities without training an impractical number of inference networks for all possible modality combinations. We introduce multimodal iterative amortized inference, an iterative refinement mechanism within the multimodal VAE framework.
  arXiv  Detail & Related papers  (2024-10-15T08:49:38Z)
• Mutual Information-based Representations Disentanglement for Unaligned Multimodal Language Sequences [25.73415065546444]
  Key challenge in unaligned multimodal language sequences is to integrate information from various modalities to obtain a refined multimodal joint representation. We propose a Mutual Information-based Representations Disentanglement (MIRD) method for unaligned multimodal language sequences.
  arXiv  Detail & Related papers  (2024-09-19T02:12:26Z)
• Joint Multimodal Transformer for Emotion Recognition in the Wild [49.735299182004404]
  Multimodal emotion recognition (MMER) systems typically outperform unimodal systems. This paper proposes an MMER method that relies on a joint multimodal transformer (JMT) for fusion with key-based cross-attention.
  arXiv  Detail & Related papers  (2024-03-15T17:23:38Z)
• Leveraging Diffusion Disentangled Representations to Mitigate Shortcuts in Underspecified Visual Tasks [92.32670915472099]
  We propose an ensemble diversification framework exploiting the generation of synthetic counterfactuals using Diffusion Probabilistic Models (DPMs) We show that diffusion-guided diversification can lead models to avert attention from shortcut cues, achieving ensemble diversity performance comparable to previous methods requiring additional data collection.
  arXiv  Detail & Related papers  (2023-10-03T17:37:52Z)
• Learning Data Representations with Joint Diffusion Models [20.25147743706431]
  Joint machine learning models that allow synthesizing and classifying data often offer uneven performance between those tasks or are unstable to train. We extend the vanilla diffusion model with a classifier that allows for stable joint end-to-end training with shared parameterization between those objectives. The resulting joint diffusion model outperforms recent state-of-the-art hybrid methods in terms of both classification and generation quality on all evaluated benchmarks.
  arXiv  Detail & Related papers  (2023-01-31T13:29:19Z)
• Multi-Modal Mutual Information Maximization: A Novel Approach for Unsupervised Deep Cross-Modal Hashing [73.29587731448345]
  We propose a novel method, dubbed Cross-Modal Info-Max Hashing (CMIMH) We learn informative representations that can preserve both intra- and inter-modal similarities. The proposed method consistently outperforms other state-of-the-art cross-modal retrieval methods.
  arXiv  Detail & Related papers  (2021-12-13T08:58:03Z)
• Discriminative Multimodal Learning via Conditional Priors in Generative Models [21.166519800652047]
  This research studies the realistic scenario in which all modalities and class labels are available for model training. We show, in this scenario, that the variational lower bound limits mutual information between joint representations and missing modalities.
  arXiv  Detail & Related papers  (2021-10-09T17:22:24Z)
• A Variational Information Bottleneck Approach to Multi-Omics Data Integration [98.6475134630792]
  We propose a deep variational information bottleneck (IB) approach for incomplete multi-view observations. Our method applies the IB framework on marginal and joint representations of the observed views to focus on intra-view and inter-view interactions that are relevant for the target. Experiments on real-world datasets show that our method consistently achieves gain from data integration and outperforms state-of-the-art benchmarks.
  arXiv  Detail & Related papers  (2021-02-05T06:05:39Z)
• Relating by Contrasting: A Data-efficient Framework for Multimodal Generative Models [86.9292779620645]
  We develop a contrastive framework for generative model learning, allowing us to train the model not just by the commonality between modalities, but by the distinction between "related" and "unrelated" multimodal data. Under our proposed framework, the generative model can accurately identify related samples from unrelated ones, making it possible to make use of the plentiful unlabeled, unpaired multimodal data.
  arXiv  Detail & Related papers  (2020-07-02T15:08:11Z)

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.