Dataset pruning for targeted knowledge distillation

In this technical report, we describe our submission for Task 1 Data-Efficient Low-Complexity Acoustic Scene Classification [1]. We adopt the baseline model and add a specialised knowledge distillation process before proceeding with the baseline training process. Our...

Message-Passing on Directed Acyclic Graphs Prevents Over-Smoothing

Despite the rising popularity of message-passing neural networks (MPNNs), their ability to fit complex functions over graphs is limited as node representations become more similar with increasing depth—a phenomenon known as over-smoothing. Most approaches to mitigate...

OoDIS: Anomaly Instance Segmentation Benchmark

Safe navigation of self-driving cars and robots requires a precise understanding of their environment. Training data for perception systems cannot cover the wide variety of objects that may appear during deployment. Thus, reliable identification of unknown objects,...

RadLink: Linking Clinical Entities from Radiology Reports

Radiology reports are a critical source of information for patient diagnosis and treatment in the medical domain. However, the vast amount of data contained in these reports is often unstructured, making it challenging to extract and normalize relevant clinical...