Related papers: Ensemble-Guided Distillation for Compact and Robus…

While deep models have shown promising performance in medical image segmentation, they heavily rely on a large amount of well-annotated data, which is difficult to access, especially in clinical practice. On the other hand, high-accuracy…

Previous works on unsupervised industrial anomaly detection mainly focus on local structural anomalies such as cracks and color contamination. While achieving significantly high detection performance on this kind of anomaly, they are faced…

Anomaly detection and localization in automated industrial manufacturing can significantly enhance production efficiency and product quality. Existing methods are capable of detecting surface defects in pre-defined or controlled imaging…

Recent advances in collaborative knowledge distillation have demonstrated cutting-edge performance for resource-constrained distributed multimedia learning scenarios. However, achieving such competitiveness requires addressing a fundamental…

Sound can convey significant information for spatial reasoning in our daily lives. To endow deep networks with such ability, we address the challenge of dense indoor prediction with sound in both 2D and 3D via cross-modal knowledge…

Scaling architectures have been proven effective for improving Scene Text Recognition (STR), but the individual contribution of vision encoder and text decoder scaling remain under-explored. In this work, we present an in-depth empirical…

In this paper, we propose a sub-utterance unit selection framework to remove acoustic segments in audio recordings that carry little information for acoustic scene classification (ASC). Our approach is built upon a universal set of acoustic…

Sound event detection (SED) and acoustic scene classification (ASC) are important research topics in environmental sound analysis. Many research groups have addressed SED and ASC using neural-network-based methods, such as the convolutional…

Recent efforts have been made on acoustic scene classification in the audio signal processing community. In contrast, few studies have been conducted on acoustic scene clustering, which is a newly emerging problem. Acoustic scene clustering…

Semantic scene completion, also known as semantic occupancy prediction, can provide dense geometric and semantic information for autonomous vehicles, which attracts the increasing attention of both academia and industry. Unfortunately,…

In this report, the Brno University of Technology (BUT) team submissions for Task 1 (Acoustic Scene Classification, ASC) of the DCASE-2019 challenge are described. Also, the analysis of different methods is provided. The proposed approach…

Acoustic scene classification (ASC) aims to classify an audio clip based on the characteristic of the recording environment. In this regard, deep learning based approaches have emerged as a useful tool for ASC problems. Conventional…

Self-supervised speech pre-training enables deep neural network models to capture meaningful and disentangled factors from raw waveform signals. The learned universal speech representations can then be used across numerous downstream tasks.…

Current state-of-the-art object detectors are at the expense of high computational costs and are hard to deploy to low-end devices. Knowledge distillation, which aims at training a smaller student network by transferring knowledge from a…

In this paper, we present deep learning frameworks for audio-visual scene classification (SC) and indicate how individual visual and audio features as well as their combination affect SC performance. Our extensive experiments, which are…

Motion forecasting has become an increasingly critical component of autonomous robotic systems. Onboard compute budgets typically limit the accuracy of real-time systems. In this work we propose methods of improving motion forecasting…

Knowledge distillation is considered as a training and compression strategy in which two neural networks, namely a teacher and a student, are coupled together during training. The teacher network is supposed to be a trustworthy predictor…

Significant improvement has been achieved in automated audio captioning (AAC) with recent models. However, these models have become increasingly large as their performance is enhanced. In this work, we propose a knowledge distillation (KD)…

This technical report describes the details of our TASK1A submission of the DCASE2021 challenge. The goal of the task is to design an audio scene classification system for device-imbalanced datasets under the constraints of model…

Deep neural networks have achieved impressive performance across a wide range of tasks, but this success often comes with substantial computational and storage costs due to large-scale training data. Dataset distillation addresses this…