相关论文: i-Mix: A Domain-Agnostic Strategy for Contrastive …

Current contrastive learning methods use random transformations sampled from a large list of transformations, with fixed hyperparameters, to learn invariance from an unannotated database. Following previous works that introduce a small…

It has been reported that deep learning models are extremely vulnerable to small but intentionally chosen perturbations of its input. In particular, a deep network, despite its near-optimal accuracy on the clean images, often mis-classifies…

In many real-world machine learning applications, samples belong to a set of domains e.g., for product reviews each review belongs to a product category. In this paper, we study multi-domain imbalanced learning (MIL), the scenario that…

Deep convolutional neural networks have considerably improved state-of-the-art results for semantic segmentation. Nevertheless, even modern architectures lack the ability to generalize well to a test dataset that originates from a different…

Contrastive learning is among the most popular and powerful approaches for self-supervised representation learning, where the goal is to map semantically similar samples close together while separating dissimilar ones in the latent space.…

The promise of active learning (AL) is to reduce labelling costs by selecting the most valuable examples to annotate from a pool of unlabelled data. Identifying these examples is especially challenging with high-dimensional data (e.g.…

Establishing voxelwise semantic correspondence across distinct imaging modalities is a foundational yet formidable computer vision task. Current multi-modality registration techniques maximize hand-crafted inter-domain similarity functions,…

Authentication is the task of confirming the matching relationship between a data instance and a given identity. Typical examples of authentication problems include face recognition and person re-identification. Data-driven authentication…

Recently, contrastive learning has achieved great results in self-supervised learning, where the main idea is to push two augmentations of an image (positive pairs) closer compared to other random images (negative pairs). We argue that not…

Detecting anomalies is one fundamental aspect of a safety-critical software system, however, it remains a long-standing problem. Numerous branches of works have been proposed to alleviate the complication and have demonstrated their…

Contrastive learning has shown remarkable results in recent self-supervised approaches for visual representation. By learning to contrast positive pairs' representation from the corresponding negatives pairs, one can train good visual…

Contrastive learning (CL) has been successful as a powerful representation learning method. In this work we propose CLIM: Contrastive Learning with mutual Information Maximization, to explore the potential of CL on cross-domain sentiment…

While supervised learning has enabled great progress in many applications, unsupervised learning has not seen such widespread adoption, and remains an important and challenging endeavor for artificial intelligence. In this work, we propose…

Traditional domain generalization methods often rely on domain alignment to reduce inter-domain distribution differences and learn domain-invariant representations. However, domain shifts are inherently difficult to eliminate, which limits…

Creating representations of shapes that are invari-ant to isometric or almost-isometric transforma-tions has long been an area of interest in shape anal-ysis, since enforcing invariance allows the learningof more effective and robust shape…

Contrastive learning has become a key component of self-supervised learning approaches for computer vision. By learning to embed two augmented versions of the same image close to each other and to push the embeddings of different images…

We present a novel unsupervised domain adaptation method for semantic segmentation that generalizes a model trained with source images and corresponding ground-truth labels to a target domain. A key to domain adaptive semantic segmentation…

Representation learning constitutes a pivotal cornerstone in contemporary deep learning paradigms, offering a conduit to elucidate distinctive features within the latent space and interpret the deep models. Nevertheless, the inherent…

We introduce a novel approach to unsupervised and semi-supervised domain adaptation for semantic segmentation. Unlike many earlier methods that rely on adversarial learning for feature alignment, we leverage contrastive learning to bridge…

Semantic segmentation models struggle to generalize in the presence of domain shift. In this paper, we introduce contrastive learning for feature alignment in cross-domain adaptation. We assemble both in-domain contrastive pairs and…