Related papers: Multi-view Feature Extraction based on Triple Cont…
Overlapping sound events are ubiquitous in real-world environments, but existing end-to-end sound event detection (SED) methods still struggle to detect them effectively. A critical reason is that these methods represent overlapping events…
Most previous few-shot learning algorithms are based on meta-training with fake few-shot tasks as training samples, where large labeled base classes are required. The trained model is also limited by the type of tasks. In this paper we…
Contrastive learning has gained popularity and pushes state-of-the-art performance across numerous large-scale benchmarks. In contrastive learning, the contrastive loss function plays a pivotal role in discerning similarities between…
We investigate contrastive learning in the federated setting through the lens of SimCLR and multi-view mutual information maximization. In doing so, we uncover a connection between contrastive representation learning and user verification;…
What matters for contrastive learning? We argue that contrastive learning heavily relies on informative features, or "hard" (positive or negative) features. Early works include more informative features by applying complex data…
The goal of few-shot classification is to classify new categories with few labeled examples within each class. Nowadays, the excellent performance in handling few-shot classification problems is shown by metric-based meta-learning methods.…
Unsupervised region representation learning aims to extract dense and effective features from unlabeled urban data. While some efforts have been made for solving this problem based on multiple views, existing methods are still insufficient…
Mitochondria segmentation in electron microscopy images is essential in neuroscience. However, due to the image degradation during the imaging process, the large variety of mitochondrial structures, as well as the presence of noise,…
The features used in many image analysis-based applications are frequently of very high dimension. Feature extraction offers several advantages in high-dimensional cases, and many recent studies have used multi-task feature extraction…
Self-supervised contrastive learning heavily relies on the view variance brought by data augmentation, so that it can learn a view-invariant pre-trained representation. Beyond increasing the view variance for contrast, this work focuses on…
Traditional supervised learning with deep neural networks requires a tremendous amount of labelled data to converge to a good solution. For 3D medical images, it is often impractical to build a large homogeneous annotated dataset for a…
Multi-view (or -modality) representation learning aims to understand the relationships between different view representations. Existing methods disentangle multi-view representations into consistent and view-specific representations by…
Language-supervised vision models have recently attracted great attention in computer vision. A common approach to build such models is to use contrastive learning on paired data across the two modalities, as exemplified by Contrastive…
Currently, there are two popular approaches for addressing real-world image super-resolution problems: degradation-estimation-based and blind-based methods. However, degradation-estimation-based methods may be inaccurate in estimating the…
Self-supervised learning enables networks to learn discriminative features from massive data itself. Most state-of-the-art methods maximize the similarity between two augmentations of one image based on contrastive learning. By utilizing…
Multifold observations are common for different data modalities, e.g., a 3D shape can be represented by multi-view images and an image can be described with different captions. Existing cross-modal contrastive representation learning…
Knowledge distillation enhances the performance of compact student networks by transferring knowledge from more powerful teacher networks without introducing additional parameters. In the feature space, local regions within an individual…
Multi-view contrastive clustering (MVCC) has gained significant attention for generating consistent clustering structures from multiple views through contrastive learning. However, most existing MVCC methods create cross-views by combining…
Multi-view clustering has received much attention recently. Most of the existing multi-view clustering methods only focus on one-sided clustering. As the co-occurring data elements involve the counts of sample-feature co-occurrences, it is…
Few-shot learning (FSL) aims to address the data-scarce problem. A standard FSL framework is composed of two components: (1) Pre-train. Employ the base data to generate a CNN-based feature extraction model (FEM). (2) Meta-test. Apply the…