Semi-supervised Multimodal Representation Learning through a Global Workspace

• URL: http://arxiv.org/abs/2306.15711v2
• Date: Mon, 27 May 2024 09:43:02 GMT
• Title: Semi-supervised Multimodal Representation Learning through a Global Workspace
• Authors: Benjamin Devillers, Léopold Maytié, Rufin VanRullen,
• Abstract summary: "Global Workspace" is a shared representation for two input modalities. This architecture is amenable to self-supervised training via cycle-consistency. We show that such an architecture can be trained to align and translate between two modalities with very little need for matched data.
• Score: 2.8948274245812335
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: Recent deep learning models can efficiently combine inputs from different modalities (e.g., images and text) and learn to align their latent representations, or to translate signals from one domain to another (as in image captioning, or text-to-image generation). However, current approaches mainly rely on brute-force supervised training over large multimodal datasets. In contrast, humans (and other animals) can learn useful multimodal representations from only sparse experience with matched cross-modal data. Here we evaluate the capabilities of a neural network architecture inspired by the cognitive notion of a "Global Workspace": a shared representation for two (or more) input modalities. Each modality is processed by a specialized system (pretrained on unimodal data, and subsequently frozen). The corresponding latent representations are then encoded to and decoded from a single shared workspace. Importantly, this architecture is amenable to self-supervised training via cycle-consistency: encoding-decoding sequences should approximate the identity function. For various pairings of vision-language modalities and across two datasets of varying complexity, we show that such an architecture can be trained to align and translate between two modalities with very little need for matched data (from 4 to 7 times less than a fully supervised approach). The global workspace representation can be used advantageously for downstream classification tasks and for robust transfer learning. Ablation studies reveal that both the shared workspace and the self-supervised cycle-consistency training are critical to the system's performance.

Related papers

• Multi-modal Semantic Understanding with Contrastive Cross-modal Feature Alignment [11.897888221717245]
  This paper proposes a novel CLIP-guided contrastive-learning-based architecture to perform multi-modal feature alignment. Our model is simple to implement without using task-specific external knowledge, and thus can easily migrate to other multi-modal tasks.
  arXiv  Detail & Related papers  (2024-03-11T01:07:36Z)
• Unity by Diversity: Improved Representation Learning in Multimodal VAEs [24.691068754720106]
  We show that a better latent representation can be obtained by replacing hard constraints with a soft constraint. We show improved learned latent representations and imputation of missing data modalities compared to existing methods.
  arXiv  Detail & Related papers  (2024-03-08T13:29:46Z)
• Zero-shot cross-modal transfer of Reinforcement Learning policies through a Global Workspace [48.24821328103934]
  We train a 'Global Workspace' to exploit information collected about the environment via two input modalities. In two distinct environments and tasks, our results reveal the model's ability to perform zero-shot cross-modal transfer between input modalities.
  arXiv  Detail & Related papers  (2024-03-07T15:35:29Z)
• Factorized Contrastive Learning: Going Beyond Multi-view Redundancy [116.25342513407173]
  This paper proposes FactorCL, a new multimodal representation learning method to go beyond multi-view redundancy. On large-scale real-world datasets, FactorCL captures both shared and unique information and achieves state-of-the-art results.
  arXiv  Detail & Related papers  (2023-06-08T15:17:04Z)
• Multimodal Masked Autoencoders Learn Transferable Representations [127.35955819874063]
  We propose a simple and scalable network architecture, the Multimodal Masked Autoencoder (M3AE) M3AE learns a unified encoder for both vision and language data via masked token prediction. We provide an empirical study of M3AE trained on a large-scale image-text dataset, and find that M3AE is able to learn generalizable representations that transfer well to downstream tasks.
  arXiv  Detail & Related papers  (2022-05-27T19:09:42Z)
• i-Code: An Integrative and Composable Multimodal Learning Framework [99.56065789066027]
  i-Code is a self-supervised pretraining framework where users may flexibly combine the modalities of vision, speech, and language into unified and general-purpose vector representations. The entire system is pretrained end-to-end with new objectives including masked modality unit modeling and cross-modality contrastive learning. Experimental results demonstrate how i-Code can outperform state-of-the-art techniques on five video understanding tasks and the GLUE NLP benchmark, improving by as much as 11%.
  arXiv  Detail & Related papers  (2022-05-03T23:38:50Z)
• Routing with Self-Attention for Multimodal Capsule Networks [108.85007719132618]
  We present a new multimodal capsule network that allows us to leverage the strength of capsules in the context of a multimodal learning framework. To adapt the capsules to large-scale input data, we propose a novel routing by self-attention mechanism that selects relevant capsules. This allows not only for robust training with noisy video data, but also to scale up the size of the capsule network compared to traditional routing methods.
  arXiv  Detail & Related papers  (2021-12-01T19:01:26Z)
• Unsupervised Multimodal Language Representations using Convolutional Autoencoders [5.464072883537924]
  We propose extracting unsupervised Multimodal Language representations that are universal and can be applied to different tasks. We map the word-level aligned multimodal sequences to 2-D matrices and then use Convolutional Autoencoders to learn embeddings by combining multiple datasets. It is also shown that our method is extremely lightweight and can be easily generalized to other tasks and unseen data with small performance drop and almost the same number of parameters.
  arXiv  Detail & Related papers  (2021-10-06T18:28:07Z)
• Multimodal Clustering Networks for Self-supervised Learning from Unlabeled Videos [69.61522804742427]
  This paper proposes a self-supervised training framework that learns a common multimodal embedding space. We extend the concept of instance-level contrastive learning with a multimodal clustering step to capture semantic similarities across modalities. The resulting embedding space enables retrieval of samples across all modalities, even from unseen datasets and different domains.
  arXiv  Detail & Related papers  (2021-04-26T15:55:01Z)

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.