100 citations · 193 across the 12 of their papers we have counts for
12 papers
OpenKD: Opening Prompt Diversity for Zero- and Few-shot Keypoint Detection
Changsheng Lu, Zheyuan Liu, Piotr Koniusz
Exploiting the foundation models (e.g., CLIP) to build a versatile keypoint detector has gained increasing attention. Most existing models accept either the text prompt (e.g., ``th…
Few-shot Shape Recognition by Learning Deep Shape-aware Features
Wenlong Shi, Changsheng Lu, Ming Shao +3
Traditional shape descriptors have been gradually replaced by convolutional neural networks due to their superior performance in feature extraction and classification. The state-of…
Understanding and Mitigating Hyperbolic Dimensional Collapse in Graph Contrastive Learning
Yifei Zhang, Hao Zhu, Menglin Yang +4
Learning generalizable self-supervised graph representations for downstream tasks is challenging. To this end, Contrastive Learning (CL) has emerged as a leading approach. The embe…
Transductive Few-shot Learning with Prototype-based Label Propagation by Iterative Graph Refinement
Hao Zhu, Piotr Koniusz
Few-shot learning (FSL) is popular due to its ability to adapt to novel classes. Compared with inductive few-shot learning, transductive models typically perform better as they lev…
From Saliency to DINO: Saliency-guided Vision Transformer for Few-shot Keypoint Detection
Changsheng Lu, Hao Zhu, Piotr Koniusz
Unlike current deep keypoint detectors that are trained to recognize limited number of body parts, few-shot keypoint detection (FSKD) attempts to localize any keypoints, including…
Spectral Feature Augmentation for Graph Contrastive Learning and Beyond
Yifei Zhang, Hao Zhu, Zixing Song +2
Although augmentations (e.g., perturbation of graph edges, image crops) boost the efficiency of Contrastive Learning (CL), feature level augmentation is another plausible, compleme…
COSTA: Covariance-Preserving Feature Augmentation for Graph Contrastive Learning
Yifei Zhang, Hao Zhu, Zixing Song +2
Graph contrastive learning (GCL) improves graph representation learning, leading to SOTA on various downstream tasks. The graph augmentation step is a vital but scarcely studied st…
Graph-adaptive Rectified Linear Unit for Graph Neural Networks
Yifei Zhang, Hao Zhu, Ziqiao Meng +2
Graph Neural Networks (GNNs) have achieved remarkable success by extending traditional convolution to learning on non-Euclidean data. The key to the GNNs is adopting the neural mes…
Contrastive Laplacian Eigenmaps
Hao Zhu, Ke Sun, Piotr Koniusz
Graph contrastive learning attracts/disperses node representations for similar/dissimilar node pairs under some notion of similarity. It may be combined with a low-dimensional embe…
Few-shot Keypoint Detection with Uncertainty Learning for Unseen Species
Changsheng Lu, Piotr Koniusz
Current non-rigid object keypoint detectors perform well on a chosen kind of species and body parts, and require a large amount of labelled keypoints for training. Moreover, their…
REFINE: Random RangE FInder for Network Embedding
Hao Zhu, Piotr Koniusz
Network embedding approaches have recently attracted considerable interest as they learn low-dimensional vector representations of nodes. Embeddings based on the matrix factorizati…
Graph Convolutional Network with Generalized Factorized Bilinear Aggregation
Hao Zhu, Piotr Koniusz
Although Graph Convolutional Networks (GCNs) have demonstrated their power in various applications, the graph convolutional layers, as the most important component of GCN, are stil…