Related papers: DCL: Differential Contrastive Learning for Geometr…

Due to the abundance of 2D product images from the Internet, developing efficient and scalable algorithms to recover the missing depth information is central to many applications. Recent works have addressed the single-view depth estimation…

Originally designed for applications in computer graphics, visual computing (VC) methods synthesize information about physical and virtual worlds, using prescribed algorithms optimized for spatial computing. VC is used to analyze geometry,…

Graph-level contrastive learning, aiming to learn the representations for each graph by contrasting two augmented graphs, has attracted considerable attention. Previous studies usually simply assume that a graph and its augmented graph as a…

Contrastive learning has demonstrated promising potential in recommender systems. Existing methods typically construct sparser views by randomly perturbing the original interaction graph, as they have no idea about the authentic user…

Recent studies have demonstrated that gradient matching-based dataset synthesis, or dataset condensation (DC), methods can achieve state-of-the-art performance when applied to data-efficient learning tasks. However, in this study, we prove…

The state-of-the-art in discriminative unsupervised surface anomaly detection relies on external datasets for synthesizing anomaly-augmented training images. Such approaches are prone to failure on near-in-distribution anomalies since these…

Prototypical contrastive learning (PCL) has been widely used to learn class-wise domain-invariant features recently. These methods are based on the assumption that the prototypes, which are represented as the central value of the same class…

Recently, the cycle-consistent generative adversarial networks (CycleGAN) has been widely used for synthesis of multi-domain medical images. The domain-specific nonlinear deformations captured by CycleGAN make the synthesized images…

Self-supervised contrastive learning (CL) effectively learns transferable representations from unlabeled data containing images or image-text pairs but suffers vulnerability to data poisoning backdoor attacks (DPCLs). An adversary can…

Recently, deep learning based methods have demonstrated promising results on the graph matching problem, by relying on the descriptive capability of deep features extracted on graph nodes. However, one main limitation with existing deep…

Learning single image deraining (SID) networks from an unpaired set of clean and rainy images is practical and valuable as acquiring paired real-world data is almost infeasible. However, without the paired data as the supervision, learning…

View synthesis aims to produce unseen views from a set of views captured by two or more cameras at different positions. This task is non-trivial since it is hard to conduct pixel-level matching among different views. To address this issue,…

We present a method for inferring dense depth maps from images and sparse depth measurements by leveraging synthetic data to learn the association of sparse point clouds with dense natural shapes, and using the image as evidence to validate…

Contrastive pretraining can substantially increase model generalisation and downstream performance. However, the quality of the learned representations is highly dependent on the data augmentation strategy applied to generate positive…

Dense correspondence across semantically related images has been extensively studied, but still faces two challenges: 1) large variations in appearance, scale and pose exist even for objects from the same category, and 2) labeling…

A persistent structural weakness in deep clustering is the disconnect between feature learning and cluster assignment. Most architectures invoke an external clustering step, typically k-means, to produce pseudo-labels that guide training,…

Differential phase-contrast computed tomography (DPC-CT) is a powerful analysis tool for soft-tissue and low-atomic-number samples. Limited by the implementation conditions, DPC-CT with incomplete projections happens quite often.…

Contrastive learning (CL) is one of the most successful paradigms for self-supervised learning (SSL). In a principled way, it considers two augmented "views" of the same image as positive to be pulled closer, and all other images as…

Deep networks trained on the source domain show degraded performance when tested on unseen target domain data. To enhance the model's generalization ability, most existing domain generalization methods learn domain invariant features by…

Large language models (LLMs) are trained on huge amounts of textual data, and concerns have been raised that the limits of such data may soon be reached. A potential solution is to train on synthetic data sampled from LLMs. In this work, we…