Related papers: Model Failure or Data Corruption? Exploring Incons…

Concerns about the environmental footprint of machine learning are increasing. While studies of energy use and emissions of ML models are a growing subfield, most ML researchers and developers still do not incorporate energy measurement as…

In a binary classification problem where the goal is to fit an accurate predictor, the presence of corrupted labels in the training data set may create an additional challenge. However, in settings where likelihood maximization is poorly…

Pre-trained neural language models give high performance on natural language inference (NLI) tasks. But whether they actually understand the meaning of the processed sequences remains unclear. We propose a new diagnostics test suite which…

Data annotation plays a crucial role in ensuring your named entity recognition (NER) projects are trained with the right information to learn from. Producing the most accurate labels is a challenge due to the complexity involved with…

Text classification models, especially neural networks based models, have reached very high accuracy on many popular benchmark datasets. Yet, such models when deployed in real world applications, tend to perform badly. The primary reason is…

Question answering-based summarization evaluation metrics must automatically determine whether the QA model's prediction is correct or not, a task known as answer verification. In this work, we benchmark the lexical answer verification…

Fire is characterized by its sudden onset and destructive power, making early fire detection crucial for ensuring human safety and protecting property. With the advancement of deep learning, the application of computer vision in fire…

Construction and operating of buildings is one of the major contributors to global greenhouse emissions. With the inefficient usage of energy due to human behavior and manual operation, the energy consumption of buildings is further…

Leveraging data collected from smart meters in buildings can aid in developing policies towards energy conservation. Significant energy savings could be realised if deviations in the building operating conditions are detected early, and…

In this paper, we focus on a critical component of the city: its building stock, which holds much of its socio-economic activities. In our case, the lack of a comprehensive database about their features and its limitation to a surveyed…

Contrastive learning has achieved state-of-the-art performance in various self-supervised learning tasks and even outperforms its supervised counterpart. Despite its empirical success, theoretical understanding of the superiority of…

In the context of global sustainability, buildings are significant consumers of energy, emphasizing the necessity for innovative strategies to enhance efficiency and reduce environmental impact. This research leverages extensive raw data…

Self-supervised contrastive learning has emerged as a powerful tool in machine learning and computer vision to learn meaningful representations from unlabeled data. Meanwhile, its empirical success has encouraged many theoretical studies to…

Contrastive learning techniques have been widely used in the field of computer vision as a means of augmenting datasets. In this paper, we extend the use of these contrastive learning embeddings to sentiment analysis tasks and demonstrate…

Accurate and reliable measurement of energy consumption is critical for making well-informed design choices when choosing and training large scale NLP models. In this work, we show that existing software-based energy measurements are not…

Transformer-based retrieval and reranking models for text document search are often refined through knowledge distillation together with contrastive learning. A tight distribution matching between the teacher and student models can be hard…

The CRESST experiment employs cryogenic calorimeters for the sensitive measurement of nuclear recoils induced by dark matter particles. The recorded signals need to undergo a careful cleaning process to avoid wrongly reconstructed recoil…

Semi-supervised learning methods have shown promising results in solving many practical problems when only a few labels are available. The existing methods assume that the class distributions of labeled and unlabeled data are equal;…

In developing countries, building codes often are outdated or not enforced. As a result, a large portion of the housing stock is substandard and vulnerable to natural hazards and climate related events. Assessing housing quality is key to…

Assessing the blurriness of an object image is fundamentally important to improve the performance for object recognition and retrieval. The main challenge lies in the lack of abundant images with reliable labels and effective learning…