Related papers: Weakly Supervised Clustering by Exploiting Unique …

Existing weakly-supervised semantic segmentation methods using image-level annotations typically rely on initial responses to locate object regions. However, such response maps generated by the classification network usually focus on…

We present a weakly supervised instance segmentation algorithm based on deep community learning with multiple tasks. This task is formulated as a combination of weakly supervised object detection and semantic segmentation, where individual…

High-quality labels are often very scarce, whereas unlabeled data with inferred weak labels occurs more naturally. In many cases, these weak labels dictate the frequency of each respective class over a set of instances. In this paper, we…

This document describes a novel learning algorithm that classifies "bags" of instances rather than individual instances. A bag is labeled positive if it contains at least one positive instance (which may or may not be specifically…

Weakly supervised learning aims to empower machine learning when the perfect supervision is unavailable, which has drawn great attention from researchers. Among various types of weak supervision, one of the most challenging cases is to…

Unsupervised visual representation learning has gained much attention from the computer vision community because of the recent achievement of contrastive learning. Most of the existing contrastive learning frameworks adopt the instance…

Class-agnostic counting (CAC) has numerous potential applications across various domains. The goal is to count objects of an arbitrary category during testing, based on only a few annotated exemplars. In this paper, we point out that the…

Multiple instance learning (MIL) problem is currently solved from either bag-classification or instance-classification perspective, both of which ignore important information contained in some instances and result in limited performance.…

The pioneering method for unsupervised meta-learning, CACTUs, is a clustering-based approach with pseudo-labeling. This approach is model-agnostic and can be combined with supervised algorithms to learn from unlabeled data. However, it…

Semantic labelling and instance segmentation are two tasks that require particularly costly annotations. Starting from weak supervision in the form of bounding box detection annotations, we propose a new approach that does not require…

Recently neural networks and multiple instance learning are both attractive topics in Artificial Intelligence related research fields. Deep neural networks have achieved great success in supervised learning problems, and multiple instance…

In recent years, weakly supervised object detection (WSOD) has attracted much attention due to its low labeling cost. The success of recent WSOD models is often ascribed to the two-stage multi-class classification (MCC) task, i.e., multiple…

Since acquiring perfect supervision is usually difficult, real-world machine learning tasks often confront inaccurate, incomplete, or inexact supervision, collectively referred to as weak supervision. In this work, we present WSAUC, a…

Certain cancer types, notably pancreatic cancer, are difficult to detect at an early stage, motivating robust biomarker-based screening. Liquid biopsies enable non-invasive monitoring of circulating biomarkers, but typical machine learning…

Clustering algorithms have significantly improved along with Deep Neural Networks which provide effective representation of data. Existing methods are built upon deep autoencoder and self-training process that leverages the distribution of…

Learning to detect real-world anomalous events through video-level labels is a challenging task due to the rare occurrence of anomalies as well as noise in the labels. In this work, we propose a weakly supervised anomaly detection method…

Constrained clustering allows the training of classification models using pairwise constraints only, which are weak and relatively easy to mine, while still yielding full-supervision-level model performance. While they perform well even in…

Consider a classification problem where we do not have access to labels for individual training examples, but only have average labels over subpopulations. We give practical examples of this setup and show how such a classification task can…

The positive-unlabeled (PU) classification is a common scenario in real-world applications such as healthcare, text classification, and bioinformatics, in which we only observe a few samples labeled as "positive" together with a large…

Visual attributes, from simple objects (e.g., backpacks, hats) to soft-biometrics (e.g., gender, height, clothing) have proven to be a powerful representational approach for many applications such as image description and human…