Related papers: Revisiting Vicinal Risk Minimization for Partially…

In semantic segmentation, the creation of pixel-level labels for training data incurs significant costs. To address this problem, semi-supervised learning, which utilizes a small number of labeled images alongside unlabeled images to…

Labeling training data has become one of the major roadblocks to using machine learning. Among various weak supervision paradigms, programmatic weak supervision (PWS) has achieved remarkable success in easing the manual labeling bottleneck…

Partial-label learning (PLL) is a typical weakly supervised learning problem, where each training instance is equipped with a set of candidate labels among which only one is the true label. Most existing methods elaborately designed…

One of the largest problems in medical image processing is the lack of annotated data. Labeling medical images often requires highly trained experts and can be a time-consuming process. In this paper, we evaluate a method of reducing the…

Audio classification has seen great progress with the increasing availability of large-scale datasets. These large datasets, however, are often only partially labeled as collecting full annotations is a tedious and expensive process. This…

Classification predicts classes of objects using the knowledge learned during the training phase. This process requires learning from labeled samples. However, the labeled samples usually limited. Annotation process is annoying, tedious,…

Multi-label learning is a challenging computer vision task that requires assigning multiple categories to each image. However, fully annotating large-scale datasets is often impractical due to high costs and effort, motivating the study of…

Despite significant advances, the performance of state-of-the-art continual learning approaches hinges on the unrealistic scenario of fully labeled data. In this paper, we tackle this challenge and propose an approach for continual…

In the context of noisy partial label learning (NPLL), each training sample is associated with a set of candidate labels annotated by multiple noisy annotators. With the emergence of high-performance pre-trained vision-language models…

Methods that move towards less supervised scenarios are key for image segmentation, as dense labels demand significant human intervention. Generally, the annotation burden is mitigated by labeling datasets with weaker forms of supervision,…

The major challenge of learning from multi-label data has arisen from the overwhelming size of label space which makes this problem NP-hard. This problem can be alleviated by gradually involving easy to hard tags into the learning process.…

Multi-label image recognition with partial labels (MLR-PL) is designed to train models using a mix of known and unknown labels. Traditional methods rely on semantic or feature correlations to create pseudo-labels for unidentified labels…

Partial label learning deals with the problem where each training instance is assigned a set of candidate labels, only one of which is correct. This paper provides the first attempt to leverage the idea of self-training for dealing with…

Noisy labeled data represent a rich source of information that often are easily accessible and cheap to obtain, but label noise might also have many negative consequences if not accounted for. How to fully utilize noisy labels has been…

Weakly supervised learning with scribble annotations uses sparse user-drawn strokes to indicate segmentation labels on a small subset of pixels. This annotation reduces the cost of dense pixel-wise labeling, but suffers inherently from…

Data imbalance is easily found in annotated data when the observations of certain continuous label values are difficult to collect for regression tasks. When they come to molecule and polymer property predictions, the annotated graph…

We propose a new approach to address the text classification problems when learning with partial labels is beneficial. Instead of offering each training sample a set of candidate labels, we assign negative-oriented labels to the ambiguous…

Unpaired Multi-Modal Learning (UMML) which leverages unpaired multi-modal data to boost model performance on each individual modality has attracted a lot of research interests in medical image analysis. However, existing UMML methods…

Pixel-level dense labeling is both resource-intensive and time-consuming, whereas weak labels such as scribble present a more feasible alternative to full annotations. However, training segmentation networks with weak supervision from…

Semi-supervised segmentation tackles the scarcity of annotations by leveraging unlabeled data with a small amount of labeled data. A prominent way to utilize the unlabeled data is by consistency training which commonly uses a…