Related papers: jBOT: Semantic Jet Representation Clustering Emerg…
In this work, we propose to learn local descriptors for point clouds in a self-supervised manner. In each iteration of the training, the input of the network is merely one unlabeled point cloud. On top of our previous work, that directly…
An increasing number of datasets sharing similar domains for semantic segmentation have been published over the past few years. But despite the growing amount of overall data, it is still difficult to train bigger and better models due to…
State-of-the-art 3D object detectors are often trained on massive labeled datasets. However, annotating 3D bounding boxes remains prohibitively expensive and time-consuming, particularly for LiDAR. Instead, recent works demonstrate that…
Visual recognition tasks are often limited to dealing with a small subset of classes simply because the labels for the remaining classes are unavailable. We are interested in identifying novel concepts in a dataset through representation…
Self-supervised pre-trained models such as HuBERT and WavLM leverage unlabeled speech data for representation learning and offer significantly improve for numerous downstream tasks. Despite the success of these methods, their large memory…
This paper presents a novel methodology for improving the performance of machine learning based space traffic management tasks through the use of a pre-trained orbit model. Taking inspiration from BERT-like self-supervised language models…
We address the problem of learning new classes for semantic segmentation models from few examples, which is challenging because of the following two reasons. Firstly, it is difficult to learn from limited novel data to capture the…
Deep networks tend to learn spurious feature-label correlations in real-world supervised learning tasks. This vulnerability is aggravated in distillation, where a student model may have lesser representational capacity than the…
Knowledge distillation is typically conducted by training a small model (the student) to mimic a large and cumbersome model (the teacher). The idea is to compress the knowledge from the teacher by using its output probabilities as…
Deep clustering against self-supervised learning is a very important and promising direction for unsupervised visual representation learning since it requires little domain knowledge to design pretext tasks. However, the key component,…
Autoencoders offer a general way of learning low-dimensional, non-linear representations from data without labels. This is achieved without making any particular assumptions about the data type or other domain knowledge. The generality and…
Deep Learning has emerged as a promising approach for skin lesion analysis. However, existing methods mostly rely on fully supervised learning, requiring extensive labeled data, which is challenging and costly to obtain. To alleviate this…
Deep learning is the essential building block of state-of-the-art person detectors in 2D range data. However, only a few annotated datasets are available for training and testing these deep networks, potentially limiting their performance…
Metric learning projects samples into an embedded space, where similarities and dissimilarities are quantified based on their learned representations. However, existing methods often rely on label-guided representation learning, where…
Inducing semantic representations directly from speech signals is a highly challenging task but has many useful applications in speech mining and spoken language understanding. This study tackles the unsupervised learning of semantic…
In semi-supervised learning, methods that rely on confidence learning to generate pseudo-labels have been widely proposed. However, increasing research finds that when faced with noisy and biased data, the model's representation network is…
Supervised classification approaches can predict labels for unknown data because of the supervised training process. The success of classification is heavily dependent on the labeled training data. Differently, clustering is effective in…
Convolutional Neural Networks (CNNs) are prone to overfit small training datasets. We present a novel two-phase pipeline that leverages self-supervised learning and knowledge distillation to improve the generalization ability of CNN models…
Two competing paradigms exist for self-supervised learning of data representations. Joint Embedding Predictive Architecture (JEPA) is a class of architectures in which semantically similar inputs are encoded into representations that are…
This paper studies the problem of novel category discovery on single- and multi-modal data with labels from different but relevant categories. We present a generic, end-to-end framework to jointly learn a reliable representation and assign…