Related papers: MMANet: Margin-aware Distillation and Modality-awa…

While Large Language Models (LLMs) have emerged with remarkable capabilities in complex tasks through Chain-of-Thought reasoning, practical resource constraints have sparked interest in transferring these abilities to smaller models.…

Multimodal Federated Learning frequently encounters challenges of client modality heterogeneity, leading to undesired performances for secondary modality in multimodal learning. It is particularly prevalent in audiovisual learning, with…

It is important to develop mathematically tractable models than can interpret knowledge extracted from the data and provide reasonable predictions. In this paper, we present a Linear Distillation Learning, a simple remedy to improve the…

Tasks that rely on multi-modal information typically include a fusion module that combines information from different modalities. In this work, we develop a Refiner Fusion Network (ReFNet) that enables fusion modules to combine strong…

Dataset distillation reduces the network training cost by synthesizing small and informative datasets from large-scale ones. Despite the success of the recent dataset distillation algorithms, three drawbacks still limit their wider…

Multimodal deep learning has shown strong potential in medical applications by integrating heterogeneous data sources such as medical images and structured clinical variables. However, most existing approaches implicitly assume complete…

Reliable periodic patterns serve as a fundamental basis for accurate multivariate time series forecasting. However, existing methods either implicitly extract periodicity through complex model architectures (e.g., Transformers) with high…

Multi-modal learning, which focuses on utilizing various modalities to improve the performance of a model, is widely used in video recognition. While traditional multi-modal learning offers excellent recognition results, its computational…

As overparameterized models become increasingly prevalent, training loss alone offers limited insight into generalization performance. While smoothness has been linked to improved generalization across various settings, directly enforcing…

Traditional multimodal methods often assume static modality quality, which limits their adaptability in dynamic real-world scenarios. Thus, dynamical multimodal methods are proposed to assess modality quality and adjust their contribution…

Model-Agnostic Meta-Learning (MAML) and its variants are popular few-shot classification methods. They train an initializer across a variety of sampled learning tasks (also known as episodes) such that the initialized model can adapt…

Retrieval and ranking models are the backbone of many applications such as web search, open domain QA, or text-based recommender systems. The latency of neural ranking models at query time is largely dependent on the architecture and…

Ensemble methods are commonly used in classification due to their remarkable performance. Achieving high accuracy in a data stream environment is a challenging task considering disruptive changes in the data distribution, also known as…

Human multimodal emotion recognition (MER) aims to perceive human emotions via language, visual and acoustic modalities. Despite the impressive performance of previous MER approaches, the inherent multimodal heterogeneities still haunt and…

Deep neural networks (DNNs) are often prone to learn the spurious correlations between target classes and bias attributes, like gender and race, inherent in a major portion of training data (bias-aligned samples), thus showing unfair…

The rise of deep learning has greatly advanced human behavior monitoring using wearable sensors, particularly human activity recognition (HAR). While deep models have been widely studied, most assume stationary data distributions - an…

Despite the remarkable developments of recent large models in Embodied Artificial Intelligence (E-AI), their integration into robotics is hampered by their excessive parameter sizes and computational demands. Towards the Vision-and-Language…

Real-world machine learning applications often face simultaneous covariate and semantic shifts, challenging traditional domain generalization and out-of-distribution (OOD) detection methods. We introduce Meta-learned Across Domain…

Previous Knowledge Distillation based efficient image retrieval methods employs a lightweight network as the student model for fast inference. However, the lightweight student model lacks adequate representation capacity for effective…

Recent advancements in Multimodal Emotion Recognition (MER) face challenges in addressing both modality missing and Out-Of-Distribution (OOD) data simultaneously. Existing methods often rely on specific models or introduce excessive…