Related papers: Meta-Learn Unimodal Signals with Weak Supervision …
Deep ConvNets have shown great performance for single-label image classification (e.g. ImageNet), but it is necessary to move beyond the single-label classification task because pictures of everyday life are inherently multi-label.…
Collecting large-scale medical datasets with fine-grained annotations is time-consuming and requires experts. For this reason, weakly supervised learning aims at optimising machine learning models using weaker forms of annotations, such as…
Training deep neural networks (DNNs) under weak supervision has attracted increasing research attention as it can significantly reduce the annotation cost. However, labels from weak supervision can be noisy, and the high capacity of DNNs…
Multi-label image classification, which can be categorized into label-dependency and region-based methods, is a challenging problem due to the complex underlying object layouts. Although region-based methods are less likely to encounter…
The popularity of multimodal sensors and the accessibility of the Internet have brought us a massive amount of unlabeled multimodal data. Since existing datasets and well-trained models are primarily unimodal, the modality gap between a…
Learning with noisy labels (LNL) is essential for training deep neural networks with imperfect data. Meta-learning approaches have achieved success by using a clean unbiased labeled set to train a robust model. However, this approach…
In ML-aided decision-making tasks, such as fraud detection or medical diagnosis, the human-in-the-loop, usually a domain-expert without technical ML knowledge, prefers high-level concept-based explanations instead of low-level explanations…
Simultaneously using multimodal inputs from multiple sensors to train segmentors is intuitively advantageous but practically challenging. A key challenge is unimodal bias, where multimodal segmentors over rely on certain modalities, causing…
Multimodal learning systems often encounter challenges related to modality imbalance, where a dominant modality may overshadow others, thereby hindering the learning of weak modalities. Conventional approaches often force weak modalities to…
Predicting all applicable labels for a given image is known as multi-label classification. Compared to the standard multi-class case (where each image has only one label), it is considerably more challenging to annotate training data for…
Large repositories of image-caption pairs are essential for the development of vision-language models. However, these datasets are often extracted from noisy data scraped from the web, and contain many mislabeled instances. In order to…
Noisy labels are ubiquitous in real-world datasets, especially in the large-scale ones derived from crowdsourcing and web searching. It is challenging to train deep neural networks with noisy datasets since the networks are prone to…
For training a video-based action recognition model that accepts multi-view video, annotating frame-level labels is tedious and difficult. However, it is relatively easy to annotate sequence-level labels. This kind of coarse annotations are…
Deep learning has made many remarkable achievements in many fields but suffers from noisy labels in datasets. The state-of-the-art learning with noisy label method Co-teaching and Co-teaching+ confronts the noisy label by mutual-information…
Annotators exhibit disagreement during data labeling, which can be termed as annotator label uncertainty. Annotator label uncertainty manifests in variations of labeling quality. Training with a single low-quality annotation per sample…
The prevalence of memes on social media has created the need to sentiment analyze their underlying meanings for censoring harmful content. Meme censoring systems by machine learning raise the need for a semi-supervised learning solution to…
Supervised deep learning methods require a large repository of annotated data; hence, label noise is inevitable. Training with such noisy data negatively impacts the generalization performance of deep neural networks. To combat label noise,…
Human activity recognition (HAR) will be an essential function of various emerging applications. However, HAR typically encounters challenges related to modality limitations and label scarcity, leading to an application gap between current…
Multi-label classification is a widely encountered problem in daily life, where an instance can be associated with multiple classes. In theory, this is a supervised learning method that requires a large amount of labeling. However,…
The original ImageNet benchmark enforces a single-label assumption, despite many images depicting multiple objects. This leads to label noise and limits the richness of the learning signal. Multi-label annotations more accurately reflect…