OmniVec2 -- A Novel Transformer based Network for Large Scale Multimodal and Multitask Learning

• URL: http://arxiv.org/abs/2507.13364v1
• Date: Sun, 06 Jul 2025 18:51:22 GMT
• Title: OmniVec2 -- A Novel Transformer based Network for Large Scale Multimodal and Multitask Learning
• Authors: Siddharth Srivastava, Gaurav Sharma,
• Abstract summary: We present a novel multimodal multitask network and associated training algorithm.<n>The method is capable of ingesting data from approximately 12 different modalities.<n>It addresses multimodal and multitask scenarios by incorporating modality-specific task heads for different tasks in respective modalities.
• Score: 23.720996132491734
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: We present a novel multimodal multitask network and associated training algorithm. The method is capable of ingesting data from approximately 12 different modalities namely image, video, audio, text, depth, point cloud, time series, tabular, graph, X-ray, infrared, IMU, and hyperspectral. The proposed approach utilizes modality specialized tokenizers, a shared transformer architecture, and cross-attention mechanisms to project the data from different modalities into a unified embedding space. It addresses multimodal and multitask scenarios by incorporating modality-specific task heads for different tasks in respective modalities. We propose a novel pretraining strategy with iterative modality switching to initialize the network, and a training algorithm which trades off fully joint training over all modalities, with training on pairs of modalities at a time. We provide comprehensive evaluation across 25 datasets from 12 modalities and show state of the art performances, demonstrating the effectiveness of the proposed architecture, pretraining strategy and adapted multitask training.

Related papers

• MultiMAE Meets Earth Observation: Pre-training Multi-modal Multi-task Masked Autoencoders for Earth Observation Tasks [11.359741665798195]
  This paper explores a more flexible multi-modal, multi-task pre-training strategy for Earth Observation (EO) data.<n>Specifically, we adopt a Multi-modal Multi-task Masked Autoencoder (MultiMAE) that we pre-train by reconstructing diverse input modalities.<n>Our approach exhibits significant flexibility, handling diverse input configurations without requiring modality-specific pre-trained models.
  arXiv  Detail & Related papers  (2025-05-20T22:24:36Z)
• Pilot: Building the Federated Multimodal Instruction Tuning Framework [79.56362403673354]
  Our framework integrates two stages of "adapter on adapter" into the connector of the vision encoder and the LLM.<n>In stage 1, we extract task-specific features and client-specific features from visual information.<n>In stage 2, we build the cross-task Mixture-of-Adapters(CT-MoA) module to perform cross-task interaction.
  arXiv  Detail & Related papers  (2025-01-23T07:49:24Z)
• OmniVec: Learning robust representations with cross modal sharing [28.023214572340336]
  We present an approach to learn multiple tasks, in multiple modalities, with a unified architecture. The proposed network is composed of task specific encoders, a common trunk in the middle, followed by task specific prediction heads. We train the network on all major modalities, e.g. visual, audio, text and 3D, and report results on $22$ diverse and challenging public benchmarks.
  arXiv  Detail & Related papers  (2023-11-07T14:00:09Z)
• Unified Multi-modal Unsupervised Representation Learning for Skeleton-based Action Understanding [62.70450216120704]
  Unsupervised pre-training has shown great success in skeleton-based action understanding. We propose a Unified Multimodal Unsupervised Representation Learning framework, called UmURL. UmURL exploits an efficient early-fusion strategy to jointly encode the multi-modal features in a single-stream manner.
  arXiv  Detail & Related papers  (2023-11-06T13:56:57Z)
• Multimodality Representation Learning: A Survey on Evolution, Pretraining and Its Applications [47.501121601856795]
  Multimodality Representation Learning is a technique of learning to embed information from different modalities and their correlations. Cross-modal interaction and complementary information from different modalities are crucial for advanced models to perform any multimodal task. This survey presents the literature on the evolution and enhancement of deep learning multimodal architectures.
  arXiv  Detail & Related papers  (2023-02-01T11:48:34Z)
• 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)
• High-Modality Multimodal Transformer: Quantifying Modality & Interaction Heterogeneity for High-Modality Representation Learning [112.51498431119616]
  This paper studies efficient representation learning for high-modality scenarios involving a large set of diverse modalities. A single model, HighMMT, scales up to 10 modalities (text, image, audio, video, sensors, proprioception, speech, time-series, sets, and tables) and 15 tasks from 5 research areas.
  arXiv  Detail & Related papers  (2022-03-02T18:56:20Z)
• Channel Exchanging Networks for Multimodal and Multitask Dense Image Prediction [125.18248926508045]
  We propose Channel-Exchanging-Network (CEN) which is self-adaptive, parameter-free, and more importantly, applicable for both multimodal fusion and multitask learning. CEN dynamically exchanges channels betweenworks of different modalities. For the application of dense image prediction, the validity of CEN is tested by four different scenarios.
  arXiv  Detail & Related papers  (2021-12-04T05:47:54Z)
• 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)
• 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)
• Dynamic Task Weighting Methods for Multi-task Networks in Autonomous Driving Systems [10.625400639764734]
  Deep multi-task networks are of particular interest for autonomous driving systems. We propose a novel method combining evolutionary meta-learning and task-based selective backpropagation. Our method outperforms state-of-the-art methods by a significant margin on a two-task application.
  arXiv  Detail & Related papers  (2020-01-07T18:54:21Z)

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.