Related papers: Cross-modal Subspace Learning via Kernel Correlati…

Multimodal remote sensing data provide complementary information for semantic segmentation, but in real-world deployments, some modalities may be unavailable due to sensor failures, acquisition issues, or challenging atmospheric conditions.…

We propose HILBERT (HIerarchical Long-sequence Balanced Embedding with Reciprocal contrastive Training), a cross-attentive multimodal framework for learning document-level audio-text representations from long, segmented sequences in…

The main objective of the Multiple Kernel k-Means (MKKM) algorithm is to extract non-linear information and achieve optimal clustering by optimizing base kernel matrices. Current methods enhance information diversity and reduce redundancy…

Multi-modal Contrastive Representation learning aims to encode different modalities into a semantically aligned shared space. This paradigm shows remarkable generalization ability on numerous downstream tasks across various modalities.…

In recent years, cross-modal domain adaptation has been studied on the paired 2D image and 3D LiDAR data to ease the labeling costs for 3D LiDAR semantic segmentation (3DLSS) in the target domain. However, in such a setting the paired 2D…

Most knowledge distillation (KD) methodologies predominantly focus on teacher-student pairs with similar architectures, such as both being convolutional neural networks (CNNs). However, the potential and flexibility of KD can be greatly…

Generalized Category Discovery (GCD) aims to identify novel categories in unlabeled data while leveraging a small labeled subset of known classes. Training a parametric classifier solely on image features often leads to overfitting to old…

Kernel alignment measures the degree of similarity between two kernels. In this paper, inspired from kernel alignment, we propose a new Linear Discriminant Analysis (LDA) formulation, kernel alignment LDA (kaLDA). We first define two…

Cross-modality distillation arises as an important topic for data modalities containing limited knowledge such as depth maps and high-quality sketches. Such techniques are of great importance, especially for memory and privacy-restricted…

Semi-supervised learning has become increasingly popular in medical image segmentation due to its ability to leverage large amounts of unlabeled data to extract additional information. However, most existing semi-supervised segmentation…

Multimodal object detection has attracted significant attention in both academia and industry for its enhanced robustness. Although numerous studies have focused on improving modality fusion strategies, most neglect fusion degradation, and…

Unsupervised Change Detection (UCD) in multimodal Remote Sensing (RS) images remains a difficult challenge due to the inherent spatio-temporal complexity within data, and the heterogeneity arising from different imaging sensors. Inspired by…

This paper presents a novel kernel-based generative classifier which is defined in a distortion subspace using polynomial series expansion, named Kernel-Distortion (KD) classifier. An iterative kernel selection algorithm is developed to…

In this paper, we introduce a new image representation based on a multilayer kernel machine. Unlike traditional kernel methods where data representation is decoupled from the prediction task, we learn how to shape the kernel with…

In large-scale distributed scenarios, increasingly complex tasks demand more intelligent collaboration across networks, requiring the joint extraction of structural representations from data samples. However, conventional task-specific…

Parameterizing the approximate posterior of a generative model with neural networks has become a common theme in recent machine learning research. While providing appealing flexibility, this approach makes it difficult to impose or assess…

Deep neural networks (DNNs) have witnessed great successes in semantic segmentation, which requires a large number of labeled data for training. We present a novel learning framework called Uncertainty guided Cross-head Co-training (UCC)…

The kernel matrix used in kernel methods encodes all the information required for solving complex nonlinear problems defined on data representations in the input space using simple, but implicitly defined, solutions. Spectral analysis on…

Deep neural networks (DNNs) excel on fixed datasets but struggle with incremental and shifting data in real-world scenarios. Continual learning addresses this challenge by allowing models to learn from new data while retaining previously…

Image-text retrieval is a central problem for understanding the semantic relationship between vision and language, and serves as the basis for various visual and language tasks. Most previous works either simply learn coarse-grained…