Related papers: Siamese Labels Auxiliary Learning

Diffusion Language Models (DLMs) offer attractive advantages over Auto-Regressive (AR) models, such as full-attention parallel decoding and flexible generation. However, standard DLM training uses a static, single-step masked prediction…

Automatic emotion recognition plays a significant role in the process of human computer interaction and the design of Internet of Things (IOT) technologies. Yet, a common problem in emotion recognition systems lies in the scarcity of…

Semi-supervised semantic segmentation (SSS) is an important task that utilizes both labeled and unlabeled data to reduce expenses on labeling training examples. However, the effectiveness of SSS algorithms is limited by the difficulty of…

Current deep learning paradigms largely benefit from the tremendous amount of annotated data. However, the quality of the annotations often varies among labelers. Multi-observer studies have been conducted to study these annotation…

Robust training of machine learning models in the presence of outliers has garnered attention across various domains. The use of robust losses is a popular approach and is known to mitigate the impact of outliers. We bring to light two…

Complementary-label learning (CLL) is a weakly supervised paradigm where instances are labeled with classes they do not belong to. Despite a decade of research, CLL methods remain competitive mainly on 10-class classification, with scaling…

Active learning (AL) is a widely used technique for optimizing data labeling in machine learning by iteratively selecting, labeling, and training on the most informative data. However, its integration with formal privacy-preserving methods,…

The increasing availability of biomedical data is helping to design more robust deep learning (DL) algorithms to analyze biomedical samples. Currently, one of the main limitations to train DL algorithms to perform a specific task is the…

In this paper, we introduce a novel self-supervised learning (SSL) loss for image representation learning. There is a growing belief that generalization in deep neural networks is linked to their ability to discriminate object shapes. Since…

Deep neural state-space models (SSMs) provide a powerful tool for modeling dynamical systems solely using operational data. Typically, neural SSMs are trained using data collected from the actual system under consideration, despite the…

Fine-tuning on task-specific data to boost downstream performance is a crucial step for leveraging Large Language Models (LLMs). However, previous studies have demonstrated that fine-tuning the models on several adversarial samples or even…

Recent advances in pre-trained vision-language models have demonstrated remarkable zero-shot generalization capabilities. To further enhance these models' adaptability to various downstream tasks, prompt tuning has emerged as a…

Active learning aims to develop label-efficient algorithms by querying the most informative samples to be labeled by an oracle. The design of efficient training methods that require fewer labels is an important research direction that…

Deep learning models have been successfully used in medical image analysis problems but they require a large amount of labeled images to obtain good performance.Deep learning models have been successfully used in medical image analysis…

Large Language Models (LLMs) can justify or critique their predictions through discussions with other models or humans, thereby enriching their intrinsic understanding of instances. While proactive discussions in the inference phase have…

At its core, this thesis aims to enhance the practicality of deep learning by improving the label and training efficiency of deep learning models. To this end, we investigate data subset selection techniques, specifically active learning…

Given data with label noise (i.e., incorrect data), deep neural networks would gradually memorize the label noise and impair model performance. To relieve this issue, curriculum learning is proposed to improve model performance and…

We introduce the SaaS Algorithm for semi-supervised learning, which uses learning speed during stochastic gradient descent in a deep neural network to measure the quality of an iterative estimate of the posterior probability of unknown…

We propose self-teaching networks to improve the generalization capacity of deep neural networks. The idea is to generate soft supervision labels using the output layer for training the lower layers of the network. During the network…

Continual learning, the ability to acquire knowledge from new data while retaining previously learned information, is a fundamental challenge in machine learning. Various approaches, including memory replay, knowledge distillation, model…