Related papers: Audio Set classification with attention model: A p…

Strongly supervised learning requires detailed knowledge of truth labels at instance levels, and in many machine learning applications this is a major drawback. Multiple instance learning (MIL) is a popular weakly supervised learning method…

Noisy training labels can hurt model performance. Most approaches that aim to address label noise assume label noise is independent from the input features. In practice, however, label noise is often feature or \textit{instance-dependent},…

Inspired by the remarkable zero-shot generalization capacity of vision-language pre-trained model, we seek to leverage the supervision from CLIP model to alleviate the burden of data labeling. However, such supervision inevitably contains…

Ontologies encompass a formal representation of knowledge through the definition of concepts or properties of a domain, and the relationships between those concepts. In this work, we seek to investigate whether using this ontological…

A growing number of applications, e.g. video surveillance and medical image analysis, require training recognition systems from large amounts of weakly annotated data while some targeted interactions with a domain expert are allowed to…

State-of-the-art audio classification often employs a zero-shot approach, which involves comparing audio embeddings with embeddings from text describing the respective audio class. These embeddings are usually generated by neural networks…

The paper proposes a novel problem in multi-class Multiple-Instance Learning (MIL) called Learning from the Majority Label (LML). In LML, the majority class of instances in a bag is assigned as the bag's label. LML aims to classify…

In this paper, we consider a novel machine learning problem, that is, learning a classifier from noisy label distributions. In this problem, each instance with a feature vector belongs to at least one group. Then, instead of the true label…

Weakly-supervised audio-visual violence detection aims to distinguish snippets containing multimodal violence events with video-level labels. Many prior works perform audio-visual integration and interaction in an early or intermediate…

The massive growth of self-supervised learning (SSL) has been witnessed in language, vision, speech, and audio domains over the past few years. While discrete label prediction is widely adopted for other modalities, the state-of-the-art…

Immune repertoire classification, a typical multiple instance learning (MIL) problem, is a frontier research topic in computational biology that makes transformative contributions to new vaccines and immune therapies. However, the…

Histopathology image analysis can be considered as a Multiple instance learning (MIL) problem, where the whole slide histopathology image (WSI) is regarded as a bag of instances (i.e, patches) and the task is to predict a single class label…

Despite deep learning has achieved great success, it often relies on a large amount of training data with accurate labels, which are expensive and time-consuming to collect. A prominent direction to reduce the cost is to learn with noisy…

Anomalous Sound Detection (ASD) is often formulated as a machine attribute classification task, a strategy necessitated by the common scenario where only normal data is available for training. However, the exhaustive collection of machine…

Multiple instance learning is qualified for many pattern recognition tasks with weakly annotated data. The combination of artificial neural network and multiple instance learning offers an end-to-end solution and has been widely utilized.…

Multiple-instance learning is a subset of weakly supervised learning where labels are applied to sets of instances rather than the instances themselves. Under the standard assumption, a set is positive only there is if at least one instance…

Weakly supervised instance labeling using only image-level labels, in lieu of expensive fine-grained pixel annotations, is crucial in several applications including medical image analysis. In contrast to conventional instance segmentation…

This study defines a new evaluation metric for audio tagging tasks to overcome the limitation of the conventional mean average precision (mAP) metric, which treats different kinds of sound as independent classes without considering their…

We introduce in this work an efficient approach for audio scene classification using deep recurrent neural networks. An audio scene is firstly transformed into a sequence of high-level label tree embedding feature vectors. The vector…

The paper proposes a novel multi-class Multiple-Instance Learning (MIL) problem called Learning from Majority Label (LML). In LML, the majority class of instances in a bag is assigned as the bag-level label. The goal of LML is to train a…