Related papers: MS$^2$L: Multi-Task Self-Supervised Learning for S…
This study addresses the challenge of self-supervised learning for 3D mesh analysis. It presents an new approach that uses random walks as a form of data augmentation to generate diverse representations of mesh surfaces. Furthermore, it…
Pareto set learning (PSL) is an emerging paradigm in multi-objective optimization that trains neural networks to map preference vectors to Pareto optimal solutions. However, existing PSL methods primarily focus on solving a single…
Previous deep learning based Computer Aided Diagnosis (CAD) system treats multiple views of the same lesion as independent images. Since an ultrasound image only describes a partial 2D projection of a 3D lesion, such paradigm ignores the…
The integration of different imaging modalities, such as structural, diffusion tensor, and functional magnetic resonance imaging, with deep learning models has yielded promising outcomes in discerning phenotypic characteristics and…
Visual place recognition is a key to unlocking spatial navigation for animals, humans and robots. While state-of-the-art approaches are trained in a supervised manner and therefore hardly capture the information needed for generalizing to…
Large Language Models (LLMs) hold rich implicit knowledge and powerful transferability. In this paper, we explore the combination of LLMs with the human skeleton to perform action classification and description. However, when treating LLM…
Incorporating heterogeneous representations from different architectures has facilitated various vision tasks, e.g., some hybrid networks combine transformers and convolutions. However, complementarity between such heterogeneous…
Recent methods in self-supervised learning have demonstrated that masking-based pretext tasks extend beyond NLP, serving as useful pretraining objectives in computer vision. However, existing approaches apply random or ad hoc masking…
Local discriminative representation is needed in many medical image analysis tasks such as identifying sub-types of lesion or segmenting detailed components of anatomical structures. However, the commonly applied supervised representation…
Semi-supervised learning has recently been attracting attention as an alternative to fully supervised models that require large pools of labeled data. Moreover, optimizing a model for multiple tasks can provide better generalizability than…
The popularity of self-supervised learning has made it possible to train models without relying on labeled data, which saves expensive annotation costs. However, most existing self-supervised contrastive learning methods often overlook the…
An increasingly popular machine learning paradigm is to pretrain a neural network (NN) on many tasks offline, then adapt it to downstream tasks, often by re-training only the last linear layer of the network. This approach yields strong…
Self-supervised representation learning (SSL) on biomedical networks provides new opportunities for drug discovery. However, how to effectively combine multiple SSL models is still challenging and has been rarely explored. Therefore, we…
Current state-of-the-art methods for skeleton-based action recognition are supervised and rely on labels. The reliance is limiting the performance due to the challenges involved in annotation and mislabeled data. Unsupervised methods have…
Human action recognition aims at classifying the category of human action from a segment of a video. Recently, people have dived into designing GCN-based models to extract features from skeletons for performing this task, because skeleton…
Self-paced learning has been beneficial for tasks where some initial knowledge is available, such as weakly supervised learning and domain adaptation, to select and order the training sample sequence, from easy to complex. However its…
We present a new framework for self-supervised representation learning by formulating it as a ranking problem in an image retrieval context on a large number of random views (augmentations) obtained from images. Our work is based on two…
One-shot action recognition allows the recognition of human-performed actions with only a single training example. This can influence human-robot-interaction positively by enabling the robot to react to previously unseen behaviour. We…
Skeleton-based action recognition is a central task in computer vision and human-robot interaction. However, most previous methods suffer from overlooking the explicit exploitation of the latent data distributions (i.e., the intra-class…
This work considers supervised contrastive learning for semantic segmentation. We apply contrastive learning to enhance the discriminative power of the multi-scale features extracted by semantic segmentation networks. Our key methodological…