Related papers: Cross-Modal Knowledge Transfer Without Task-Releva…

Supervised learning models are typically trained on a single dataset and the performance of these models rely heavily on the size of the dataset, i.e., amount of data available with the ground truth. Learning algorithms try to generalize…

As the application of deep learning has expanded to real-world problems with insufficient volume of training data, transfer learning recently has gained much attention as means of improving the performance in such small-data regime.…

Decentralized collaborative learning under data heterogeneity and privacy constraints has rapidly advanced. However, existing solutions like federated learning, ensembles, and transfer learning, often fail to adequately serve the unique…

Knowledge transfer has strong potential to improve hyperspectral image (HSI) classification, yet two inherent challenges fundamentally restrict effective cross-domain transfer: spectral variations caused by different sensors and semantic…

Cross-modal retrieval has drawn wide interest for retrieval across different modalities of data. However, existing methods based on DNN face the challenge of insufficient cross-modal training data, which limits the training effectiveness…

Zero-Shot Learning (ZSL) is typically achieved by resorting to a class semantic embedding space to transfer the knowledge from the seen classes to unseen ones. Capturing the common semantic characteristics between the visual modality and…

Surrogate models provide efficient alternatives to computationally demanding real world processes but often require large datasets for effective training. A promising solution to this limitation is the transfer of pre-trained surrogate…

RGB and thermal source data suffer from both shared and specific challenges, and how to explore and exploit them plays a critical role to represent the target appearance in RGBT tracking. In this paper, we propose a novel challenge-aware…

While transfer learning is an effective strategy, it often overlooks the opportunity to leverage knowledge from numerous available models online. Addressing this multi-source transfer learning problem is a promising path to boost…

Recently, deep supervised cross-modal hashing methods have achieve compelling success by learning semantic information in a self-supervised way. However, they still suffer from the key limitation that the multi-label semantic extraction…

DNN-based cross-modal retrieval is a research hotspot to retrieve across different modalities as image and text, but existing methods often face the challenge of insufficient cross-modal training data. In single-modal scenario, similar…

Convolutional neural networks require numerous data for training. Considering the difficulties in data collection and labeling in some specific tasks, existing approaches generally use models pre-trained on a large source domain (e.g.…

The cross-domain recommendation technique is an effective way of alleviating the data sparse issue in recommender systems by leveraging the knowledge from relevant domains. Transfer learning is a class of algorithms underlying these…

When presented with a data stream of two statistically dependent variables, predicting the future of one of the variables (the target stream) can benefit from information about both its history and the history of the other variable (the…

The generalization and performance of stereo matching networks are limited due to the domain gap of the existing synthetic datasets and the sparseness of GT labels in the real datasets. In contrast, monocular depth estimation has achieved…

Multi-modality images have been widely used and provide comprehensive information for medical image analysis. However, acquiring all modalities among all institutes is costly and often impossible in clinical settings. To leverage more…

Recommender systems(RS), especially collaborative filtering(CF) based RS, has been playing an important role in many e-commerce applications. As the information being searched over the internet is rapidly increasing, users often face the…

We propose a pre-training strategy called Multi-modal Multi-task Masked Autoencoders (MultiMAE). It differs from standard Masked Autoencoding in two key aspects: I) it can optionally accept additional modalities of information in the input…

We cast a suite of information extraction tasks into a text-to-triple translation framework. Instead of solving each task relying on task-specific datasets and models, we formalize the task as a translation between task-specific input text…

We introduce a neural reading comprehension model that integrates external commonsense knowledge, encoded as a key-value memory, in a cloze-style setting. Instead of relying only on document-to-question interaction or discrete features as…