Related papers: 3MVRD: Multimodal Multi-task Multi-teacher Visuall…
Self-supervised learning has achieved remarkable success in learning visual representations from clean data, yet remains challenging when clean observations are sparse or not available at all. In this paper, we demonstrate that pretrained…
Audio-visual representation learning is crucial for advancing multimodal speech processing tasks, such as lipreading and audio-visual speech recognition. Recently, speech foundation models (SFMs) have shown remarkable generalization…
Deploying deep learning models in clinical practice often requires leveraging multiple data modalities, such as images, text, and structured data, to achieve robust and trustworthy decisions. However, not all modalities are always available…
In the surveillance and defense domain, multi-target detection and classification (MTD) is considered essential yet challenging due to heterogeneous inputs from diverse data sources and the computational complexity of algorithms designed…
This work explores knowledge distillation (KD) for visually-rich document (VRD) applications such as document layout analysis (DLA) and document image classification (DIC). While VRD research is dependent on increasingly sophisticated and…
Depth estimation and scene segmentation are two important tasks in intelligent transportation systems. A joint modeling of these two tasks will reduce the requirement for both the storage and training efforts. This work explores how the…
The widespread use of multi-sensor systems has increased research in multi-view action recognition. While existing approaches in multi-view setups with fully overlapping sensors benefit from consistent view coverage, partially overlapping…
Knowledge distillation is an effective method to transfer the knowledge from the cumbersome teacher model to the lightweight student model. Online knowledge distillation uses the ensembled prediction results of multiple student models as…
In visual tasks, large teacher models capture essential features and deep information, enhancing performance. However, distilling this information into smaller student models often leads to performance loss due to structural differences and…
To reduce a model size but retain performance, we often rely on knowledge distillation (KD) which transfers knowledge from a large "teacher" model to a smaller "student" model. However, KD on multimodal datasets such as vision-language…
In this paper, we introduce a new embedding model called M3-Embedding, which is distinguished for its versatility in \textit{Multi-Linguality}, \textit{Multi-Functionality}, and \textit{Multi-Granularity}. It provides a uniform support for…
Understanding visually situated language requires interpreting complex layouts of textual and visual elements. Pre-processing tools, such as optical character recognition (OCR), can map document image inputs to textual tokens, then large…
We propose a unified cross-domain transfer learning framework that leverages knowledge from multiple heterogeneous medical imaging datasets to improve performance across segmentation, classification, and object detection tasks. Our approach…
Knowledge distillation~(KD) is an effective learning paradigm for improving the performance of lightweight student networks by utilizing additional supervision knowledge distilled from teacher networks. Most pioneering studies either learn…
Multi-teacher Knowledge Distillation (KD) transfers diverse knowledge from a teacher pool to a student network. The core problem of multi-teacher KD is how to balance distillation strengths among various teachers. Most existing methods…
Multimodal learning has been a field of increasing interest, aiming to combine various modalities in a single joint representation. Especially in the area of visiolinguistic (VL) learning multiple models and techniques have been developed,…
This paper addresses the challenges of high computational cost and slow inference in deploying large language models. It proposes a distillation strategy guided by multiple teacher models. The method constructs several teacher models and…
Knowledge distillation (KD) aims to transfer the knowledge of a more capable yet cumbersome teacher model to a lightweight student model. In recent years, relation-based KD methods have fallen behind, as their instance-matching counterparts…
Vision-Language Models (VLMs) bring powerful understanding and reasoning capabilities to multimodal tasks. Meanwhile, the great need for capable aritificial intelligence on mobile devices also arises, such as the AI assistant software. Some…
Vision foundation models trained via multi-teacher distillation offer a promising path toward unified visual representations, yet the learning dynamics and data efficiency of such approaches remain underexplored. In this paper, we…