Turbo your multi-modal classification with contrastive learning

• URL: http://arxiv.org/abs/2409.09282v1
• Date: Sat, 14 Sep 2024 03:15:34 GMT
• Title: Turbo your multi-modal classification with contrastive learning
• Authors: Zhiyu Zhang, Da Liu, Shengqiang Liu, Anna Wang, Jie Gao, Yali Li,
• Abstract summary: In this paper, we propose a novel contrastive learning strategy, called $Turbo$, to promote multi-modal understanding. Specifically, multi-modal data pairs are sent through the forward pass twice with different hidden dropout masks to get two different representations for each modality. With these representations, we obtain multiple in-modal and cross-modal contrastive objectives for training.
• Score: 17.983460380784337
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: Contrastive learning has become one of the most impressive approaches for multi-modal representation learning. However, previous multi-modal works mainly focused on cross-modal understanding, ignoring in-modal contrastive learning, which limits the representation of each modality. In this paper, we propose a novel contrastive learning strategy, called $Turbo$, to promote multi-modal understanding by joint in-modal and cross-modal contrastive learning. Specifically, multi-modal data pairs are sent through the forward pass twice with different hidden dropout masks to get two different representations for each modality. With these representations, we obtain multiple in-modal and cross-modal contrastive objectives for training. Finally, we combine the self-supervised Turbo with the supervised multi-modal classification and demonstrate its effectiveness on two audio-text classification tasks, where the state-of-the-art performance is achieved on a speech emotion recognition benchmark dataset.

Related papers

• On the Comparison between Multi-modal and Single-modal Contrastive Learning [50.74988548106031]
  We introduce a theoretical foundation for understanding the differences between multi-modal and single-modal contrastive learning. We identify the critical factor, which is the signal-to-noise ratio (SNR), that impacts the generalizability in downstream tasks of both multi-modal and single-modal contrastive learning. Our analysis provides a unified framework that can characterize the optimization and generalization of both single-modal and multi-modal contrastive learning.
  arXiv  Detail & Related papers  (2024-11-05T06:21:17Z)
• Multi-modal Crowd Counting via a Broker Modality [64.5356816448361]
  Multi-modal crowd counting involves estimating crowd density from both visual and thermal/depth images. We propose a novel approach by introducing an auxiliary broker modality and frame the task as a triple-modal learning problem. We devise a fusion-based method to generate this broker modality, leveraging a non-diffusion, lightweight counterpart of modern denoising diffusion-based fusion models.
  arXiv  Detail & Related papers  (2024-07-10T10:13:11Z)
• Generative Multimodal Models are In-Context Learners [60.50927925426832]
  We introduce Emu2, a generative multimodal model with 37 billion parameters, trained on large-scale multimodal sequences. Emu2 exhibits strong multimodal in-context learning abilities, even emerging to solve tasks that require on-the-fly reasoning.
  arXiv  Detail & Related papers  (2023-12-20T18:59:58Z)
• Multimodal Representation Learning by Alternating Unimodal Adaptation [73.15829571740866]
  We propose MLA (Multimodal Learning with Alternating Unimodal Adaptation) to overcome challenges where some modalities appear more dominant than others during multimodal learning. MLA reframes the conventional joint multimodal learning process by transforming it into an alternating unimodal learning process. It captures cross-modal interactions through a shared head, which undergoes continuous optimization across different modalities. Experiments are conducted on five diverse datasets, encompassing scenarios with complete modalities and scenarios with missing modalities.
  arXiv  Detail & Related papers  (2023-11-17T18:57:40Z)
• Improving Unimodal Inference with Multimodal Transformers [88.83765002648833]
  Our approach involves a multi-branch architecture that incorporates unimodal models with a multimodal transformer-based branch. By co-training these branches, the stronger multimodal branch can transfer its knowledge to the weaker unimodal branches through a multi-task objective. We evaluate our approach on tasks of dynamic hand gesture recognition based on RGB and Depth, audiovisual emotion recognition based on speech and facial video, and audio-videotext based sentiment analysis.
  arXiv  Detail & Related papers  (2023-11-16T19:53:35Z)
• 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)
• UniS-MMC: Multimodal Classification via Unimodality-supervised Multimodal Contrastive Learning [29.237813880311943]
  We propose a novel multimodal contrastive method to explore more reliable multimodal representations under the weak supervision of unimodal predicting. Experimental results with fused features on two image-text classification benchmarks show that our proposed Unimodality-Supervised MultiModal Contrastive UniS-MMC learning method outperforms current state-of-the-art multimodal methods.
  arXiv  Detail & Related papers  (2023-05-16T09:18:38Z)
• On Uni-Modal Feature Learning in Supervised Multi-Modal Learning [21.822251958013737]
  We abstract the features (i.e. learned representations) of multi-modal data into 1) uni-modal features, which can be learned from uni-modal training, and 2) paired features, which can only be learned from cross-modal interactions. We demonstrate that, under a simple guiding strategy, we can achieve comparable results to other complex late-fusion or intermediate-fusion methods on various multi-modal datasets.
  arXiv  Detail & Related papers  (2023-05-02T07:15:10Z)
• Multimodal Contrastive Learning via Uni-Modal Coding and Cross-Modal Prediction for Multimodal Sentiment Analysis [19.07020276666615]
  We propose a novel framework named MultiModal Contrastive Learning (MMCL) for multimodal representation to capture intra- and inter-modality dynamics simultaneously. We also design two contrastive learning tasks, instance- and sentiment-based contrastive learning, to promote the process of prediction and learn more interactive information related to sentiment.
  arXiv  Detail & Related papers  (2022-10-26T08:24:15Z)
• Learning Modality-Specific Representations with Self-Supervised Multi-Task Learning for Multimodal Sentiment Analysis [11.368438990334397]
  We develop a self-supervised learning strategy to acquire independent unimodal supervisions. We conduct extensive experiments on three public multimodal baseline datasets. Our method achieves comparable performance than human-annotated unimodal labels.
  arXiv  Detail & Related papers  (2021-02-09T14:05:02Z)

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.