Related papers: Guided Masked Self-Distillation Modeling for Distr…

Event management in sensor networks is a multidisciplinary field involving several steps across the processing chain. In this paper, we discuss the major steps that should be performed in real- or near real-time event handling including…

Depth estimation and scene segmentation are two important tasks in intelligent transportation systems. A joint modeling of these two tasks will reduce the requirement for both the storage and training efforts. This work explores how the…

Existing methods for distillation do not efficiently utilize the training data. This work presents a novel approach to perform distillation using only a subset of the training data, making it more data-efficient. For this purpose, the…

Recently published graph neural networks (GNNs) show promising performance at social event detection tasks. However, most studies are oriented toward monolingual data in languages with abundant training samples. This has left the more…

This paper introduces PriMaL, a general PRIvacy-preserving MAchine-Learning method for reducing the privacy cost of information transmitted through a network. Distributed sensor networks are often used for automated classification and…

We propose a new semi-supervised learning method on face-related tasks based on Multi-Task Learning (MTL) and data distillation. The proposed method exploits multiple datasets with different labels for different-but-related tasks such as…

The rise of deep learning has greatly advanced human behavior monitoring using wearable sensors, particularly human activity recognition (HAR). While deep models have been widely studied, most assume stationary data distributions - an…

There is a growing need for social robots and intelligent agents that can effectively interact with and support users. For the interactions to be seamless, the agents need to analyse social scenes and behavioural cues from their (robot's)…

Federated Learning, a new machine learning paradigm enhancing the use of edge devices, is receiving a lot of attention in the pervasive community to support the development of smart services. Nevertheless, this approach still needs to be…

Accurate prediction of future trajectories of traffic agents is essential for ensuring safe autonomous driving. However, partially observed trajectories can significantly degrade the performance of even state-of-the-art models. Previous…

Knowledge distillation has been applied to various tasks successfully. The current distillation algorithm usually improves students' performance by imitating the output of the teacher. This paper shows that teachers can also improve…

Recent years have witnessed the remarkable success of deep learning in remote sensing image interpretation, driven by the availability of large-scale benchmark datasets. However, this reliance on massive training data also brings two major…

While diffusion models can learn complex distributions, sampling requires a computationally expensive iterative process. Existing distillation methods enable efficient sampling, but have notable limitations, such as performance degradation…

Self-supervised learning (SSL) has made remarkable progress in visual representation learning. Some studies combine SSL with knowledge distillation (SSL-KD) to boost the representation learning performance of small models. In this study, we…

Recent advancements in camera-based 3D object detection have introduced cross-modal knowledge distillation to bridge the performance gap with LiDAR 3D detectors, leveraging the precise geometric information in LiDAR point clouds. However,…

Despite the success that metric learning based approaches have achieved in few-shot learning, recent works reveal the ineffectiveness of their episodic training mode. In this paper, we point out two potential reasons for this problem: 1)…

Knowledge distillation conducts an effective model compression method while holding some limitations:(1) the feature based distillation methods only focus on distilling the feature map but are lack of transferring the relation of data…

Diverse input data modalities can provide complementary cues for several tasks, usually leading to more robust algorithms and better performance. However, while a (training) dataset could be accurately designed to include a variety of…

In stereo matching, CNNs have traditionally served as the predominant architectures. Although Transformer-based stereo models have been studied recently, their performance still lags behind CNN-based stereo models due to the inherent data…

Masked image modeling (MIM) is a highly effective self-supervised learning (SSL) approach to extract useful feature representations from unannotated data. Predominantly used random masking methods make SSL less effective for medical images…