Related papers: SIGNL: A Label-Efficient Audio Deepfake Detection …

Classical machine learning implicitly assumes that labels of the training data are sampled from a clean distribution, which can be too restrictive for real-world scenarios. However, statistical-learning-based methods may not train deep…

Semi-supervised learning (SSL) can reduce the need for large labelled datasets by incorporating unlabelled data into the training. This is particularly interesting for semantic segmentation, where labelling data is very costly and…

Label-efficient time series representation learning, which aims to learn effective representations with limited labeled data, is crucial for deploying deep learning models in real-world applications. To address the scarcity of labeled time…

Artefacts that differentiate spoofed from bona-fide utterances can reside in spectral or temporal domains. Their reliable detection usually depends upon computationally demanding ensemble systems where each subsystem is tuned to some…

Training deep neural networks on real-world datasets is often hampered by the presence of noisy labels, which can be memorized by over-parameterized models, leading to significant degradation in generalization performance. While existing…

It is hard to directly implement Graph Neural Networks (GNNs) on large scaled graphs. Besides of existed neighbor sampling techniques, scalable methods decoupling graph convolutions and other learnable transformations into preprocessing and…

Extracting image semantics effectively and assigning corresponding labels to multiple objects or attributes for natural images is challenging due to the complex scene contents and confusing label dependencies. Recent works have focused on…

The Audio-Visual Video Parsing task aims to identify and temporally localize the events that occur in either or both the audio and visual streams of audible videos. It often performs in a weakly-supervised manner, where only video event…

Semi-supervised action recognition aims to improve spatio-temporal reasoning ability with a few labeled data in conjunction with a large amount of unlabeled data. Albeit recent advancements, existing powerful methods are still prone to…

Speech deepfake detection has achieved remarkable success in clean environments but faces significant challenges in complex, real-world scenarios where speech is often mixed with background music or noise. Current state-of-the-art methods…

Existing shadow detection datasets often contain missing or mislabeled shadows, which can hinder the performance of deep learning models trained directly on such data. To address this issue, we propose SILT, the Shadow-aware Iterative Label…

Due to the publicly available thematic maps and crowd-sourced data, remote sensing (RS) image annotations can be gathered at zero cost for training deep neural networks (DNNs). However, such annotation sources may increase the risk of…

Deep neural networks have proven to be highly effective when large amounts of data with clean labels are available. However, their performance degrades when training data contains noisy labels, leading to poor generalization on the test…

Deep learning has shown remarkable success in medical image analysis, but its reliance on large volumes of high-quality labeled data limits its applicability. While noisy labeled data are easier to obtain, directly incorporating them into…

Deep semi-supervised learning (SSL) has experienced significant attention in recent years, to leverage a huge amount of unlabeled data to improve the performance of deep learning with limited labeled data. Pseudo-labeling is a popular…

Modern deep neural networks (DNNs) become frail when the datasets contain noisy (incorrect) class labels. Robust techniques in the presence of noisy labels can be categorized into two folds: developing noise-robust functions or using…

Several types of spoofed audio, such as mimicry, replay attacks, and deepfakes, have created societal challenges to information integrity. Recently, researchers have worked with sociolinguistics experts to label spoofed audio samples with…

Large pre-trained vision-language models (VLMs), such as CLIP, have shown unprecedented zero-shot performance across a wide range of tasks. Nevertheless, these models may be unreliable under distributional shifts, as their performance is…

Audio tagging aims to predict one or several labels in an audio clip. Many previous works use weakly labelled data (WLD) for audio tagging, where only presence or absence of sound events is known, but the order of sound events is unknown.…

Self-supervised contrastive representation learning has proved incredibly successful in the vision and natural language domains, enabling state-of-the-art performance with orders of magnitude less labeled data. However, such methods are…