Related papers: Purify-then-Align: Towards Robust Human Sensing un…

Continually learning in the real world must overcome many challenges, among which noisy labels are a common and inevitable issue. In this work, we present a repla-ybased continual learning framework that simultaneously addresses both…

Learning from noisy labels is an important and long-standing problem in machine learning for real applications. One of the main research lines focuses on learning a label corrector to purify potential noisy labels. However, these methods…

Growing data privacy demands, driven by regulations like GDPR and CCPA, require machine unlearning methods capable of swiftly removing the influence of specific training points. Although verified approaches like SISA, using data slicing and…

Vision-language models like CLIP have achieved remarkable progress in cross-modal representation learning, yet suffer from systematic misclassifications among visually and semantically similar categories. We observe that such confusion…

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…

Multimodal learning has shown great potentials in numerous scenes and attracts increasing interest recently. However, it often encounters the problem of missing modality data and thus suffers severe performance degradation in practice. To…

Modern deep learning faces significant challenges with noisy labels, class ambiguity, as well as the need to robustly reject out-of-distribution or corrupted samples. In this work, we propose a unified framework based on the concept of a…

Model merging has emerged as an efficient and flexible paradigm for multi-task learning, with numerous methods being proposed in recent years. However, these state-of-the-art techniques are typically evaluated on benchmark suites that are…

Pretrained language models (PLMs) such as BERT adopt a training paradigm which first pretrain the model in general data and then finetune the model on task-specific data, and have recently achieved great success. However, PLMs are notorious…

Multimodal reward models are crucial for aligning multimodal large language models with human preferences. Recent works have incorporated reasoning capabilities into these models, achieving promising results. However, training these models…

In the context of label-efficient learning on video data, the distillation method and the structural design of the teacher-student architecture have a significant impact on knowledge distillation. However, the relationship between these…

Multimodal sentiment analysis (MSA) aims to understand human sentiment through multimodal data. In real-world scenarios, practical factors often lead to uncertain modality missingness. Existing methods for handling modality missingness are…

In this paper, we propose to use a Conditional Generative Adversarial Network (CGAN) for distilling (i.e. transferring) knowledge from sensor data and enhancing low-resolution target detection. In unconstrained surveillance settings, sensor…

Vision-language retrieval aims to search for similar instances in one modality based on queries from another modality. The primary objective is to learn cross-modal matching representations in a latent common space. Actually, the assumption…

Knowledge distillation deploys complex machine learning models in resource-constrained environments by training a smaller student model to emulate internal representations of a complex teacher model. However, the teacher's representations…

Knowledge distillation is a popular technique to transfer knowledge from large teacher models to a small student model. Typically, the student learns to imitate the teacher by minimizing the KL divergence of its output distribution with the…

Recent methods exploit the powerful text-to-image (T2I) diffusion models for real-world image super-resolution (Real-ISR) and achieve impressive results compared to previous models. However, we observe two kinds of inconsistencies in…

Dataset distillation compresses large-scale datasets into compact synthetic sets while preserving training performance, but existing methods are largely restricted to single-modal or bimodal settings. Extending dataset distillation to…

Knowledge distillation establishes a learning paradigm that leverages both data supervision and teacher guidance. However, determining the optimal balance between learning from data and learning from the teacher is challenging, as some…

Samples with ground truth labels may not always be available in numerous domains. While learning from crowdsourcing labels has been explored, existing models can still fail in the presence of sparse, unreliable, or diverging annotations.…