This paper considers contrastive training for cross-modal 0-shot transfer wherein a pre-trained model in one modality is used for representation learning in another domain using pairwise data. The learnt models in the latter domain can then be used for a diverse set of tasks in a 0-shot way, similar to Contrastive Language-Image Pre-training (CLIP) and Locked-image Tuning (LiT) that have recently gained considerable attention. Classical contrastive training employs sets of positive and negative examples to align similar and repel dissimilar training data samples. However, similarity amongst training examples has a more continuous nature, thus calling for a more `non-binary' treatment. To address this, we propose a new contrastive loss function called Continuously Weighted Contrastive Loss (CWCL) that employs a continuous measure of similarity. With CWCL, we seek to transfer the structure of the embedding space from one modality to another. Owing to the continuous nature of similarity in the proposed loss function, these models outperform existing methods for 0-shot transfer across multiple models, datasets and modalities. By using publicly available datasets, we achieve 5-8% (absolute) improvement over previous state-of-the-art methods in 0-shot image classification and 20-30% (absolute) improvement in 0-shot speech-to-intent classification and keyword classification.

Neural Information Processing Systems http://nips.cc/

This work introduces a model that can recognize objects in images even if no training data is available for the object class. The only necessary knowledge about unseen categories comes from unsupervised text corpora. Unlike previous zero-shot learning models, which can only differentiate between unseen classes, our model can operate on a mixture of objects, simultaneously obtaining state of the art performance on classes with thousands of training images and reasonable performance on unseen classes. This is achieved by seeing the distributions of words in texts as a semantic space for understanding what objects look like. Our deep learning model does not require any manually defined semantic or visual features for either words or images. Images are mapped to be close to semantic word vectors corresponding to their classes, and the resulting image embeddings can be used to distinguish whether an image is of a seen or unseen class. Then, a separate recognition model can be employed for each type. We demonstrate two strategies, the first gives high accuracy on unseen classes, while the second is conservative in its prediction of novelty and keeps the seen classes' accuracy high.

Aligning acoustic and linguistic representations is a central challenge to bridge the pre-trained models in knowledge transfer for automatic speech recognition (ASR). This alignment is inherently structured and asymmetric: while multiple consecutive acoustic frames typically correspond to a single linguistic token (many-to-one), certain acoustic transition regions may relate to multiple adjacent tokens (one-to-many). Moreover, acoustic sequences often include frames with no linguistic counterpart, such as background noise or silence may lead to imbalanced matching conditions. In this work, we take a new insight to regard alignment and matching as a detection problem, where the goal is to identify meaningful correspondences with high precision and recall ensuring full coverage of linguistic tokens while flexibly handling redundant or noisy acoustic frames in transferring linguistic knowledge for ASR. Based on this new insight, we propose an unbalanced optimal transport-based alignment model that explicitly handles distributional mismatch and structural asymmetries with soft and partial matching between acoustic and linguistic modalities. Our method ensures that every linguistic token is grounded in at least one acoustic observation, while allowing for flexible, probabilistic mappings from acoustic to linguistic units. We evaluate our proposed model with experiments on an CTC-based ASR system with a pre-trained language model for knowledge transfer. Experimental results demonstrate the effectiveness of our approach in flexibly controlling degree of matching and hence to improve ASR performance.

Recent advances in deep learning have revolutionized seismic monitoring, yet developing a foundation model that performs well across multiple complex tasks remains challenging, particularly when dealing with degraded signals or data scarcity. This work presents SeisMoLLM, the first foundation model that utilizes cross-modal transfer for seismic monitoring, to unleash the power of large-scale pre-training from a large language model without requiring direct pre-training on seismic datasets. Through elaborate waveform tokenization and fine-tuning of pre-trained GPT-2 model, SeisMoLLM achieves state-of-the-art performance on the DiTing and STEAD datasets across five critical tasks: back-azimuth estimation, epicentral distance estimation, magnitude estimation, phase picking, and first-motion polarity classification. It attains 36 best results out of 43 task metrics and 12 top scores out of 16 few-shot generalization metrics, with many relative improvements ranging from 10% to 50%. In addition to its superior performance, SeisMoLLM maintains efficiency comparable to or even better than lightweight models in both training and inference. These findings establish SeisMoLLM as a promising foundation model for practical seismic monitoring and highlight cross-modal transfer as an exciting new direction for earthquake studies, showcasing the potential of advanced deep learning techniques to propel seismology research forward.

This paper considers contrastive training for cross-modal 0-shot transfer wherein a pre-trained model in one modality is used for representation learning in another domain using pairwise data. The learnt models in the latter domain can then be used for a diverse set of tasks in a 0-shot way, similar to Contrastive Language-Image Pre-training (CLIP) and Locked-image Tuning (LiT) that have recently gained considerable attention. Classical contrastive training employs sets of positive and negative examples to align similar and repel dissimilar training data samples. However, similarity amongst training examples has a more continuous nature, thus calling for a more non-binary' treatment. To address this, we propose a new contrastive loss function called Continuously Weighted Contrastive Loss (CWCL) that employs a continuous measure of similarity. With CWCL, we seek to transfer the structure of the embedding space from one modality to another.

Although deep learning models have had great success in natural language processing and computer vision, we do not observe comparable improvements in the case of tabular data, which is still the most common data type used in biological, industrial and financial applications. In particular, it is challenging to transfer large-scale pre-trained models to downstream tasks defined on small tabular datasets. To address this, we propose VisTabNet -- a cross-modal transfer learning method, which allows for adapting Vision Transformer (ViT) with pre-trained weights to process tabular data. By projecting tabular inputs to patch embeddings acceptable by ViT, we can directly apply a pre-trained Transformer Encoder to tabular inputs. This approach eliminates the conceptual cost of designing a suitable architecture for processing tabular data, while reducing the computational cost of training the model from scratch. Experimental results on multiple small tabular datasets (less than 1k samples) demonstrate VisTabNet's superiority, outperforming both traditional ensemble methods and recent deep learning models. The proposed method goes beyond conventional transfer learning practice and shows that pre-trained image models can be transferred to solve tabular problems, extending the boundaries of transfer learning.

Despite living in a multi-sensory world, most AI models are limited to textual and visual interpretations of human motion and behavior. Inertial measurement units (IMUs) provide a salient signal to understand human motion; however, they are challenging to use due to their uninterpretability and scarcity of their data. We investigate a method to transfer knowledge between visual and inertial modalities using the structure of an informative joint representation space designed for human action recognition (HAR). We apply the resulting Fusion and Cross-modal Transfer (FACT) method to a novel setup, where the model does not have access to labeled IMU data during training and is able to perform HAR with only IMU data during testing. Extensive experiments on a wide range of RGB-IMU datasets demonstrate that FACT significantly outperforms existing methods in zero-shot cross-modal transfer.

Humans perceive the world through multiple senses, enabling them to create a comprehensive representation of their surroundings and to generalize information across domains. For instance, when a textual description of a scene is given, humans can mentally visualize it. In fields like robotics and Reinforcement Learning (RL), agents can also access information about the environment through multiple sensors; yet redundancy and complementarity between sensors is difficult to exploit as a source of robustness (e.g. against sensor failure) or generalization (e.g. transfer across domains). Prior research demonstrated that a robust and flexible multimodal representation can be efficiently constructed based on the cognitive science notion of a 'Global Workspace': a unique representation trained to combine information across modalities, and to broadcast its signal back to each modality. Here, we explore whether such a brain-inspired multimodal representation could be advantageous for RL agents. First, we train a 'Global Workspace' to exploit information collected about the environment via two input modalities (a visual input, or an attribute vector representing the state of the agent and/or its environment). Then, we train a RL agent policy using this frozen Global Workspace. In two distinct environments and tasks, our results reveal the model's ability to perform zero-shot cross-modal transfer between input modalities, i.e. to apply to image inputs a policy previously trained on attribute vectors (and vice-versa), without additional training or fine-tuning. Variants and ablations of the full Global Workspace (including a CLIP-like multimodal representation trained via contrastive learning) did not display the same generalization abilities.

Self-supervised pre-training of large-scale transformer models on text corpora followed by finetuning has achieved state-of-the-art on a number of natural language processing tasks. Recently, Lu et al. (2021, arXiv:2103.05247) claimed that frozen pretrained transformers (FPTs) match or outperform training from scratch as well as unfrozen (fine-tuned) pretrained transformers in a set of transfer tasks to other modalities. In our work, we find that this result is, in fact, an artifact of not tuning the learning rates. After carefully redesigning the empirical setup, we find that when tuning learning rates properly, pretrained transformers do outperform or match training from scratch in all of our tasks, but only as long as the entire model is finetuned. Thus, while transfer from pretrained language models to other modalities does indeed provide gains and hints at exciting possibilities for future work, properly tuning hyperparameters is important for arriving at robust findings.