Related papers: Unsupervised Video Continual Learning via Non-Para…
Deep neural networks are efficient learning machines which leverage upon a large amount of manually labeled data for learning discriminative features. However, acquiring substantial amount of supervised data, especially for videos can be a…
Self-supervised learning allows for better utilization of unlabelled data. The feature representation obtained by self-supervision can be used in downstream tasks such as classification, object detection, segmentation, and anomaly…
Vision-and-Language (V+L) pre-training models have achieved tremendous success in recent years on various multi-modal benchmarks. However, the majority of existing models require pre-training on a large set of parallel image-text data,…
The recently advanced unsupervised learning approaches use the siamese-like framework to compare two "views" from the same image for learning representations. Making the two views distinctive is a core to guarantee that unsupervised methods…
Unsupervised approaches to learning in neural networks are of substantial interest for furthering artificial intelligence, both because they would enable the training of networks without the need for large numbers of expensive annotations,…
A key challenge for machine intelligence is to learn new visual concepts without forgetting the previously acquired knowledge. Continual learning is aimed towards addressing this challenge. However, there is a gap between existing…
Neural net classifiers trained on data with annotated class labels can also capture apparent visual similarity among categories without being directed to do so. We study whether this observation can be extended beyond the conventional…
Video instance segmentation requires classifying, segmenting, and tracking every object across video frames. Unlike existing approaches that rely on masks, boxes, or category labels, we propose UVIS, a novel Unsupervised Video Instance…
Continual learning (CL) models are designed to learn new tasks arriving sequentially without re-training the network. However, real-world ML applications have very limited label information and these models suffer from catastrophic…
We introduce S$^2$VS, a video similarity learning approach with self-supervision. Self-Supervised Learning (SSL) is typically used to train deep models on a proxy task so as to have strong transferability on target tasks after fine-tuning.…
Unsupervised learning has been popular in various computer vision tasks, including visual object tracking. However, prior unsupervised tracking approaches rely heavily on spatial supervision from template-search pairs and are still unable…
We study unsupervised video representation learning that seeks to learn both motion and appearance features from unlabeled video only, which can be reused for downstream tasks such as action recognition. This task, however, is extremely…
Novelty detection is a critical task in various engineering fields. Numerous approaches to novelty detection rely on supervised or semi-supervised learning, which requires labelled datasets for training. However, acquiring labelled data,…
Many important classification problems, such as object classification, speech recognition, and machine translation, have been tackled by the supervised learning paradigm in the past, where training corpora of parallel input-output pairs are…
Cross-modal representation learning has become a new normal for bridging the semantic gap between text and visual data. Learning modality agnostic representations in a continuous latent space, however, is often treated as a black-box…
Recent developed deep unsupervised methods allow us to jointly learn representation and cluster unlabelled data. These deep clustering methods mainly focus on the correlation among samples, e.g., selecting high precision pairs to gradually…
A steady momentum of innovations and breakthroughs has convincingly pushed the limits of unsupervised image representation learning. Compared to static 2D images, video has one more dimension (time). The inherent supervision existing in…
For challenging machine learning problems such as zero-shot learning and fine-grained categorization, embedding learning is the machinery of choice because of its ability to learn generic notions of similarity, as opposed to class-specific…
Due to the costliness of labelled data in real-world applications, semi-supervised learning, underpinned by pseudo labelling, is an appealing solution. However, handling confusing samples is nontrivial: discarding valuable confusing samples…
Semi-supervised learning has substantially advanced medical image segmentation since it alleviates the heavy burden of acquiring the costly expert-examined annotations. Especially, the consistency-based approaches have attracted more…