Related papers: Constructing Enhanced Mutual Information for Onlin…

Domain incremental learning aims to adapt to a sequence of domains with access to only a small subset of data (i.e., memory) from previous domains. Various methods have been proposed for this problem, but it is still unclear how they are…

Multimodal Entity Linking (MEL) aims to link ambiguous mentions within multimodal contexts to associated entities in a multimodal knowledge base. Existing approaches to MEL introduce multimodal interaction and fusion mechanisms to bridge…

While humans excel at continual learning (CL), deep neural networks (DNNs) exhibit catastrophic forgetting. A salient feature of the brain that allows effective CL is that it utilizes multiple modalities for learning and inference, which is…

We introduce a novel Mutual Information (MI) estimator that fundamentally reframes the discriminative approach. Instead of training a classifier to discriminate between joint and marginal distributions, we learn a normalizing flow that…

Cross-modal retrieval is crucial in understanding latent correspondences across modalities. However, existing methods implicitly assume well-matched training data, which is impractical as real-world data inevitably involves imperfect…

Learning disentangled representations is a fundamental task in multi-modal learning. In modern applications such as single-cell multi-omics, both shared and modality-specific features are critical for characterizing cell states and…

Continual learning aims to rapidly and continually learn the current task from a sequence of tasks. Compared to other kinds of methods, the methods based on experience replay have shown great advantages to overcome catastrophic forgetting.…

In 3D action recognition, there exists rich complementary information between skeleton modalities. Nevertheless, how to model and utilize this information remains a challenging problem for self-supervised 3D action representation learning.…

Federated Learning (FL) enables collaborative model training among participants while guaranteeing the privacy of raw data. Mainstream FL methodologies overlook the dynamic nature of real-world data, particularly its tendency to grow in…

In recent years, model-agnostic meta-learning (MAML) has become a popular research area. However, the stochastic optimization of MAML is still underdeveloped. Existing MAML algorithms rely on the ``episode'' idea by sampling a few tasks and…

Self-supervised learning (SSL) is now a serious competitor for supervised learning, even though it does not require data annotation. Several baselines have attempted to make SSL models exploit information about data distribution, and less…

Unsupervised learning visible-infrared person re-identification (USL-VI-ReID) aims to learn modality-invariant features from unlabeled cross-modality datasets and reduce the inter-modality gap. However, the existing methods lack…

In this work, we perform unsupervised learning of representations by maximizing mutual information between an input and the output of a deep neural network encoder. Importantly, we show that structure matters: incorporating knowledge about…

Continual learning (CL) remains a significant challenge for deep neural networks, as it is prone to forgetting previously acquired knowledge. Several approaches have been proposed in the literature, such as experience rehearsal,…

Knowledge distillation (KD) is an effective model compression technique where a compact student network is taught to mimic the behavior of a complex and highly trained teacher network. In contrast, Mutual Learning (ML) provides an…

Multi-view learning methods often focus on improving decision accuracy, while neglecting the decision uncertainty, limiting their suitability for safety-critical applications. To mitigate this, researchers propose trusted multi-view…

Incremental learning targets at achieving good performance on new categories without forgetting old ones. Knowledge distillation has been shown critical in preserving the performance on old classes. Conventional methods, however,…

Multimodal learning has increasingly become a focal point in research, primarily due to its ability to integrate complementary information from diverse modalities. Nevertheless, modality imbalance, stemming from factors such as insufficient…

Stacked intelligent metasurface (SIM) is a promising enabler for next-generation high-capacity networks that exhibit better performance compared to its single-layer counterpart by means of just wave propagation. However, the study of…

In autonomous driving, environment perception has significantly advanced with the utilization of deep learning techniques for diverse sensors such as cameras, depth sensors, or infrared sensors. The diversity in the sensor stack increases…