Related papers: Positive and negative sampling strategies for self…

Self-supervised learning (SSL) approaches, such as contrastive and generative methods, have advanced environmental sound representation learning using unlabeled data. However, how these approaches can complement each other within a unified…

Feature selection is essential for effective visual recognition. We propose an efficient joint classifier learning and feature selection method that discovers sparse, compact representations of input features from a vast sea of candidates,…

Existing audio analysis methods generally first transform the audio stream to spectrogram, and then feed it into CNN for further analysis. A standard CNN recognizes specific visual patterns over feature map, then pools for high-level…

Learning visual representations through self-supervision is an extremely challenging task as the network needs to sieve relevant patterns from spurious distractors without the active guidance provided by supervision. This is achieved…

Recently, Semi-Supervised Learning (SSL) has shown much promise in leveraging unlabeled data while being provided with very few labels. In this paper, we show that ignoring the labels altogether for whole epochs intermittently during…

We present a self-supervised learning (SSL) method suitable for semi-global tasks such as object detection and semantic segmentation. We enforce local consistency between self-learned features, representing corresponding image locations of…

In many applications, training machine learning models involves using large amounts of human-annotated data. Obtaining precise labels for the data is expensive. Instead, training with weak supervision provides a low-cost alternative. We…

Large-scale audio tagging datasets inevitably contain imperfect labels, such as clip-wise annotated (temporally weak) tags with no exact on- and offsets, due to a high manual labeling cost. This work proposes pseudo strong labels (PSL), a…

In this work, we focus on label efficient learning for video action detection. We develop a novel semi-supervised active learning approach which utilizes both labeled as well as unlabeled data along with informative sample selection for…

Audio-visual automatic speech recognition (AV-ASR) models are very effective at reducing word error rates on noisy speech, but require large amounts of transcribed AV training data. Recently, audio-visual self-supervised learning (SSL)…

Following the success of supervised learning, semi-supervised learning (SSL) is now becoming increasingly popular. SSL is a family of methods, which in addition to a labeled training set, also use a sizable collection of unlabeled data for…

Advances in deep learning are re-defining how visual data is processed and understand by the machines. Vision Transformers (ViTs) have recently demonstrated prominent performance in computer vision related tasks. However, their performance…

Recently, learning from vast unlabeled data, especially self-supervised learning, has been emerging and attracted widespread attention. Self-supervised learning followed by the supervised fine-tuning on a few labeled examples can…

Voice conversion (VC) systems are widely used for several applications, from speaker anonymisation to personalised speech synthesis. Supervised approaches learn a mapping between different speakers using parallel data, which is expensive to…

Network traffic classification (NTC) is vital for efficient network management, security, and performance optimization, particularly with 5G/6G technologies. Traditional methods, such as deep packet inspection (DPI) and port-based…

In Self-Supervised Learning (SSL), pre-training and evaluation are resource intensive. In the speech domain, current indicators of the quality of SSL models during pre-training, such as the loss, do not correlate well with downstream…

Consistency learning plays a crucial role in semi-supervised medical image segmentation as it enables the effective utilization of limited annotated data while leveraging the abundance of unannotated data. The effectiveness and efficiency…

The success of deep learning in medical imaging is mostly achieved at the cost of a large labeled data set. Semi-supervised learning (SSL) provides a promising solution by leveraging the structure of unlabeled data to improve learning from…

We are interested in representation learning from labeled or unlabeled data. Inspired by recent success of self-supervised learning (SSL), we develop a non-contrastive representation learning method that can exploit additional knowledge.…

Self-supervised learning (SSL), as a newly emerging unsupervised representation learning paradigm, generally follows a two-stage learning pipeline: 1) learning invariant and discriminative representations with auto-annotation pretext(s),…