Related papers: Semi-Supervised Semantic Segmentation via Gentle T…

We propose a method for semi-supervised semantic segmentation using an adversarial network. While most existing discriminators are trained to classify input images as real or fake on the image level, we design a discriminator in a fully…

Cross domain object detection learns an object detector for an unlabeled target domain by transferring knowledge from an annotated source domain. Promising results have been achieved via Mean Teacher, however, pseudo labeling which is the…

Semantic segmentation is a key computer vision task that has been actively researched for decades. In recent years, supervised methods have reached unprecedented accuracy, however they require many pixel-level annotations for every new…

The divergence between labeled training data and unlabeled testing data is a significant challenge for recent deep learning models. Unsupervised domain adaptation (UDA) attempts to solve such a problem. Recent works show that self-training…

Synthetic data, an appealing alternative to extensive expert-annotated data for medical image segmentation, consistently fails to improve segmentation performance despite its visual realism. The reason being that synthetic and real medical…

In medical image analysis, semi-supervised learning is an effective method to extract knowledge from a small amount of labeled data and a large amount of unlabeled data. This paper focuses on a popular pipeline known as self learning, and…

Domain adaptation (DA) aims to transfer knowledge from a fully labeled source to a scarcely labeled or totally unlabeled target under domain shift. Recently, semi-supervised learning-based (SSL) techniques that leverage pseudo labeling have…

Active learning is an iterative labeling process that is used to obtain a small labeled subset, despite the absence of labeled data, thereby enabling to train a model for supervised tasks such as text classification. While active learning…

We propose a simple but efficient method termed Guided Learning for weakly-labeled semi-supervised sound event detection (SED). There are two sub-targets implied in weakly-labeled SED: audio tagging and boundary detection. Instead of…

The recently proposed self-ensembling methods have achieved promising results in deep semi-supervised learning, which penalize inconsistent predictions of unlabeled data under different perturbations. However, they only consider adding…

Existing semi-supervised medical segmentation co-learning frameworks have realized that model performance can be diminished by the biases in model recognition caused by low-quality pseudo-labels. Due to the averaging nature of their…

Semi-supervised learning (SSL) addresses the lack of labeled data by exploiting large unlabeled data through pseudolabeling. However, in the extremely low-label regime, pseudo labels could be incorrect, a.k.a. the confirmation bias, and the…

Pseudo-label learning is widely used in semantic segmentation, particularly in label-scarce scenarios such as unsupervised domain adaptation (UDA) and semisupervised learning (SSL). Despite its success, this paradigm can generate erroneous…

Self-training methods have been explored in recent years and have exhibited great performance in improving semi-supervised learning. This work presents a Simple instance-Adaptive self-Training method (SAT) for semi-supervised text…

Semi-supervised temporal action segmentation (SS-TA) aims to perform frame-wise classification in long untrimmed videos, where only a fraction of videos in the training set have labels. Recent studies have shown the potential of contrastive…

This paper describes a method of domain adaptive training for semantic segmentation using multiple source datasets that are not necessarily relevant to the target dataset. We propose a soft pseudo-label generation method by integrating…

3D point cloud semantic segmentation is a challenging topic in the computer vision field. Most of the existing methods in literature require a large amount of fully labeled training data, but it is extremely time-consuming to obtain these…

Remote sensing projects typically generate large amounts of imagery that can be used to train powerful deep neural networks. However, the amount of labeled images is often small, as remote sensing applications generally require expert…

Scribble-based weakly supervised semantic segmentation leverages only a few annotated pixels as labels to train a segmentation model, presenting significant potential for reducing the human labor involved in the annotation process. This…

Recently, pseudo label based semi-supervised learning has achieved great success in many fields. The core idea of the pseudo label based semi-supervised learning algorithm is to use the model trained on the labeled data to generate pseudo…