Related papers: Task-Oriented Pre-Training for Drivable Area Detec…

Multi-Task Learning (MTL) aims to enhance the model generalization by sharing representations between related tasks for better performance. Typical MTL methods are jointly trained with the complete multitude of ground-truths for all tasks…

Semantic segmentation enables robots to perceive and reason about their environments beyond geometry. Most of such systems build upon deep learning approaches. As autonomous robots are commonly deployed in initially unknown environments,…

Self-supervised pretraining has been observed to be effective at improving feature representations for transfer learning, leveraging large amounts of unlabelled data. This review summarizes recent research into its usage in X-ray, computed…

Recent advances in Deep Learning have greatly improved performance on various tasks such as object detection, image segmentation, sentiment analysis. The focus of most research directions up until very recently has been on beating…

Training foundation models on extensive datasets and then finetuning them on specific tasks has emerged as the mainstream approach in artificial intelligence. However, the model robustness, which is a critical aspect for safety, is often…

Although the pre-training followed by fine-tuning paradigm is used extensively in many fields, there is still some controversy surrounding the impact of pre-training on the fine-tuning process. Currently, experimental findings based on text…

Recent advances in self-supervised learning have dramatically improved the state of the art on a wide variety of tasks. However, research in language model pre-training has mostly focused on natural languages, and it is unclear whether…

Software is constantly changing, requiring developers to perform several derived tasks in a timely manner, such as writing a description for the intention of the code change, or identifying the defect-prone code changes. Considering that…

This paper proposes a novel approach to address the challenge that pretrained VLA models often fail to effectively improve performance and reduce adaptation costs during standard supervised finetuning (SFT). Some advanced finetuning methods…

Image-level contrastive representation learning has proven to be highly effective as a generic model for transfer learning. Such generality for transfer learning, however, sacrifices specificity if we are interested in a certain downstream…

Whole slide image (WSI) classification is a critical task in computational pathology, requiring the processing of gigapixel-sized images, which is challenging for current deep-learning methods. Current state of the art methods are based on…

In the realm of recommendation systems, users exhibit a diverse array of behaviors when interacting with items. This phenomenon has spurred research into learning the implicit semantic relationships between these behaviors to enhance…

This paper proposes a novel self-supervised learning method for semantic segmentation using selective masking image reconstruction as the pretraining task. Our proposed method replaces the random masking augmentation used in most masked…

Annotation scarcity has become a major obstacle for training powerful deep-learning models for medical image segmentation, restricting their deployment in clinical scenarios. To address it, semi-supervised learning by exploiting abundant…

While interests in tabular deep learning has significantly grown, conventional tree-based models still outperform deep learning methods. To narrow this performance gap, we explore the innovative retrieval mechanism, a methodology that…

Many successful methods developed for medical image analysis that are based on machine learning use supervised learning approaches, which often require large datasets annotated by experts to achieve high accuracy. However, medical data…

Despite their popularity in the chatbot literature, retrieval-based models have had modest impact on task-oriented dialogue systems, with the main obstacle to their application being the low-data regime of most task-oriented dialogue tasks.…

Localizing object parts precisely is essential for tasks such as object recognition and robotic manipulation. Recent part segmentation methods require extensive training data and labor-intensive annotations. Segment-Anything Model (SAM) has…

In this work, we study computational approaches to detect online dialogic instructions, which are widely used to help students understand learning materials, and build effective study habits. This task is rather challenging due to the…

Pre-trained representation is one of the key elements in the success of modern deep learning. However, existing works on continual learning methods have mostly focused on learning models incrementally from scratch. In this paper, we explore…