相关论文: Source-Free Cross-Modal Knowledge Transfer by Unle…

Multimodal sensing has proven valuable for visual tracking, as different sensor types offer unique strengths in handling one specific challenging scene where object appearance varies. While a generalist model capable of leveraging all…

Multi-source translation is an approach to exploit multiple inputs (e.g. in two different languages) to increase translation accuracy. In this paper, we examine approaches for multi-source neural machine translation (NMT) using an…

This paper addresses the problem of inferring unseen cross-modal image-to-image translations between multiple modalities. We assume that only some of the pairwise translations have been seen (i.e. trained) and infer the remaining unseen…

This paper investigates the accuracy of generative models and the impact of knowledge transfer on their generation precision. Specifically, we examine a generative model for a target task, fine-tuned using a pre-trained model from a source…

Generalized Category Discovery is a crucial real-world task. Despite the improved performance on known categories, current methods perform poorly on novel categories. We attribute the poor performance to two reasons: biased knowledge…

Cross-modal distillation has been widely used to transfer knowledge across different modalities, enriching the representation of the target unimodal one. Recent studies highly relate the temporal synchronization between vision and sound to…

Due to the complementary nature of visible light and thermal infrared modalities, object tracking based on the fusion of visible light images and thermal images (referred to as RGB-T tracking) has received increasing attention from…

There has been a tremendous progress in Domain Adaptation (DA) for visual recognition tasks. Particularly, open-set DA has gained considerable attention wherein the target domain contains additional unseen categories. Existing open-set DA…

Task-oriented communication aims to extract and transmit task-relevant information to significantly reduce the communication overhead and transmission latency. However, the unpredictable distribution shifts between training and test data,…

Cross-modal transfer is helpful to enhance modality-specific discriminative power for scene recognition. To this end, this paper presents a unified framework to integrate the tasks of cross-modal translation and modality-specific…

This work explores the potential of brief inter-agent knowledge transfer (KT) to enhance the robotic object goal navigation (ON) in unseen and unfamiliar environments. Drawing on the analogy of human travelers acquiring local knowledge, we…

Deep learning models exhibit limited generalizability across different domains. Specifically, transferring knowledge from available entangled domain features(source/target domain) and categorical features to new unseen categorical features…

In multi-label learning, a particular case of multi-task learning where a single data point is associated with multiple target labels, it was widely assumed in the literature that, to obtain best accuracy, the dependence among the labels…

The remarkable performance gains realized by large pretrained models, e.g., GPT-3, hinge on the massive amounts of data they are exposed to during training. Analogously, distilling such large models to compact models for efficient…

Reasoning in a temporal knowledge graph (TKG) is a critical task for information retrieval and semantic search. It is particularly challenging when the TKG is updated frequently. The model has to adapt to changes in the TKG for efficient…

Transfer learning aims to transfer knowledge or information from a source domain to a relevant target domain. In this paper, we understand transfer learning from the perspectives of knowledge transferability and trustworthiness. This…

Contextualized entity representations learned by state-of-the-art transformer-based language models (TLMs) like BERT, GPT, T5, etc., leverage the attention mechanism to learn the data context from training data corpus. However, these models…

Annotation scarcity is a long-standing problem in medical image analysis area. To efficiently leverage limited annotations, abundant unlabeled data are additionally exploited in semi-supervised learning, while well-established…

Task-oriented communications, mostly using learning-based joint source-channel coding (JSCC), aim to design a communication-efficient edge inference system by transmitting task-relevant information to the receiver. However, only…

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…