Related papers: More Reliable Pseudo-labels, Better Performance: A…

Traditional supervised learning heavily relies on human-annotated datasets, especially in data-hungry neural approaches. However, various tasks, especially multi-label tasks like document-level relation extraction, pose challenges in fully…

Treating texts as images, combining prompts with textual labels for prompt tuning, and leveraging the alignment properties of CLIP have been successfully applied in zero-shot multi-label image recognition. Nonetheless, relying solely on…

Several works in computer vision have demonstrated the effectiveness of active learning for adapting the recognition model when new unlabeled data becomes available. Most of these works consider that labels obtained from the annotator are…

Deep learning perception models require a massive amount of labeled training data to achieve good performance. While unlabeled data is easy to acquire, the cost of labeling is prohibitive and could create a tremendous burden on companies or…

Positive and Unlabeled (PU) learning, a binary classification model trained with only positive and unlabeled data, generally suffers from overfitted risk estimation due to inconsistent data distributions. To address this, we introduce a…

Self-supervised learning (SSL) has demonstrated its effectiveness in learning representations through comparison methods that align with human intuition. However, mainstream SSL methods heavily rely on high body datasets with single label,…

Designing robust algorithms capable of training accurate neural networks on uncurated datasets from the web has been the subject of much research as it reduces the need for time consuming human labor. The focus of many previous research…

In the era of deep learning, loss functions determine the range of tasks available to models and algorithms. To support the application of deep learning in multi-label classification (MLC) tasks, we propose the ZLPR (zero-bounded…

A weakly-supervised learning framework named as complementary-label learning has been proposed recently, where each sample is equipped with a single complementary label that denotes one of the classes the sample does not belong to. However,…

In this paper we revisit the idea of pseudo-labeling in the context of semi-supervised learning where a learning algorithm has access to a small set of labeled samples and a large set of unlabeled samples. Pseudo-labeling works by applying…

This paper proposes a novel pseudo-labeling method for medical image segmentation that can perform learning on ``individual images'' to select effective pseudo-labels. We introduce Positive and Unlabeled Learning (PU learning), which uses…

Due to the expensive costs of collecting labels in multi-label classification datasets, partially annotated multi-label classification has become an emerging field in computer vision. One baseline approach to this task is to assume…

In this paper, we introduce a unique variant of the denoising Auto-Encoder and combine it with the perceptual loss to classify images in an unsupervised manner. The proposed method, called Pseudo Labelling, consists of first applying a…

Deep neural networks (DNNs) are typically evaluated under the assumption that each image has a single correct label. However, many images in benchmarks like ImageNet contain multiple valid labels, creating a mismatch between evaluation…

The task of medical image recognition is notably complicated by the presence of varied and multiple pathological indications, presenting a unique challenge in multi-label classification with unseen labels. This complexity underlines the…

Distance Metric Learning (DML) has typically dominated the audio-visual speaker verification problem space, owing to strong performance in new and unseen classes. In our work, we explored multitask learning techniques to further enhance…

Deep neural networks trained with standard cross-entropy loss are more prone to memorize noisy labels, which degrades their performance. Negative learning using complementary labels is more robust when noisy labels intervene but with an…

In this paper we propose a novel learning framework called Supervised and Weakly Supervised Learning where the goal is to learn simultaneously from weakly and strongly labeled data. Strongly labeled data can be simply understood as fully…

Semi-supervised 3D object detection (SS3DOD) aims to reduce costly 3D annotations utilizing unlabeled data. Recent studies adopt pseudo-label-based teacher-student frameworks and demonstrate impressive performance. The main challenge of…

Semi-supervised learning in automatic speech recognition (ASR) typically relies on pseudo-labeling, which often suffers from confirmation bias and error accumulation due to noisy supervision. To address this limitation, we propose ReHear, a…