LAUSR

About LAUSR
Donate
Contact Us

Follow us:

You are not signed in:

Sign Up!


   Articles with "self distillation" as a keyword



SelfMatch: Robust semisupervised time‐series classification with self‐distillation

Sign Up to like & get
recommendations! Published in 2022 at "International Journal of Intelligent Systems"

DOI: 10.1002/int.22957

Abstract: Over the years, a number of semisupervised deep‐learning algorithms have been proposed for time‐series classification (TSC). In semisupervised deep learning, from the point of view of representation hierarchy, semantic information extracted from lower levels is… read more here.

Keywords: semantic information; time series; selfmatch; robust semisupervised ... See more keywords

Federated Class-Incremental Learning with New-Class Augmented Self-Distillation

Sign Up to like & get
recommendations! Published in 2024 at "Journal of Computer Science and Technology"

DOI: 10.1007/s11390-025-5186-5

Abstract: Federated learning (FL) enables collaborative model training among participants while guaranteeing the privacy of raw data. Mainstream FL methodologies overlook the dynamic nature of real-world data, particularly its tendency to grow in volume and diversify… read more here.

Keywords: class incremental; class; self distillation; new class ... See more keywords

Exploiting the Potential of Self-Supervised Monocular Depth Estimation via Patch-Based Self-Distillation

Sign Up to like & get
recommendations! Published in 2025 at "IEEE Internet of Things Journal"

DOI: 10.1109/jiot.2025.3540917

Abstract: Perceiving scene depth and 3-D structure is one of the key tasks for Internet of Video Things (IoVT) devices to understand and interact with the environment. Self-supervised monocular depth estimation has demonstrated significant potential in… read more here.

Keywords: depth estimation; based self; depth; self distillation ... See more keywords

A Self-Distillation Contrastive Learning Architecture for Global and Local Underwater Terrain Feature Extraction and Matching

Sign Up to like & get
recommendations! Published in 2024 at "IEEE Sensors Journal"

DOI: 10.1109/jsen.2024.3395017

Abstract: Terrain matching is a core component of underwater terrain-aided navigation system, which determines the accuracy of the underwater vehicle’s localization. Traditional terrain matching methods are lacking in improving the matching performance by extracting effective terrain… read more here.

Keywords: terrain; distillation contrastive; self distillation; underwater terrain ... See more keywords

LaST: Label-Free Self-Distillation Contrastive Learning With Transformer Architecture for Remote Sensing Image Scene Classification

Sign Up to like & get
recommendations! Published in 2022 at "IEEE Geoscience and Remote Sensing Letters"

DOI: 10.1109/lgrs.2022.3185088

Abstract: The increase in self-supervised learning (SSL), especially contrastive learning, has enabled one to train deep neural network models with unlabeled data for remote sensing image (RSI) scene classification. Nevertheless, it still suffers from the following… read more here.

Keywords: scene classification; remote sensing; architecture; contrastive learning ... See more keywords

Two-Stage Domain Adaptation for Hyperspectral Image Classification Based on Self-Distillation and Test-Time Adaptation

Sign Up to like & get
recommendations! Published in 2025 at "IEEE Geoscience and Remote Sensing Letters"

DOI: 10.1109/lgrs.2025.3566951

Abstract: Unsupervised domain adaptation (UDA) methods can effectively mitigate the spectral drift in cross-scene hyperspectral image (HSI) classification. Among them, adversarial training methods are particularly noteworthy due to their outstanding performance. However, due to the inherent… read more here.

Keywords: adaptation; training; self distillation; domain adaptation ... See more keywords

A Self-Distillation-Based Multimodal Feature Alignment Network for Hyperspectral Image and LiDAR Classification

Sign Up to like & get
recommendations! Published in 2025 at "IEEE Geoscience and Remote Sensing Letters"

DOI: 10.1109/lgrs.2025.3570391

Abstract: The joint classification of hyperspectral image (HSI) and light detection and ranging (LiDAR) data seeks to provide a more comprehensive characterization of target objects. Multimodal data possess distinct semantic structures in both spectral and spatial… read more here.

Keywords: classification; feature alignment; lidar; self distillation ... See more keywords

SD-FSOD: Self-Distillation Paradigm via Distribution Calibration for Few-Shot Object Detection

Sign Up to like & get
recommendations! Published in 2024 at "IEEE Transactions on Circuits and Systems for Video Technology"

DOI: 10.1109/tcsvt.2023.3343397

Abstract: Few-shot object detection (FSOD) aims to detect novel targets with only a few instances of the associated samples. Although combinations of distillation techniques and meta-learning paradigms have been acknowledged as the primary strategies for FSOD… read more here.

Keywords: fsod; distribution; self distillation; distillation paradigm ... See more keywords

Self-Distillation With Augmentation in Feature Space

Sign Up to like & get
recommendations! Published in 2024 at "IEEE Transactions on Circuits and Systems for Video Technology"

DOI: 10.1109/tcsvt.2024.3400368

Abstract: Compared with traditional knowledge distillation, self-distillation does not require a pre-trained teacher network, which is more concise. Among them, data augmentation-based methods provide an elegant solution without modifying the network structure or additional memory consumption.… read more here.

Keywords: space; feature distribution; self distillation; augmentation ... See more keywords

Diffusion Self-Distillation for Remote Sensing Scene Classification

Sign Up to like & get
recommendations! Published in 2025 at "IEEE Transactions on Geoscience and Remote Sensing"

DOI: 10.1109/tgrs.2025.3569616

Abstract: Remote sensing scene classification, a fundamental task in remote image analysis, has obtained rapid progress due to the powerful capabilities of convolutional neural networks (CNNs). Achieving precise classification performance heavily relies on the feature extraction… read more here.

Keywords: classification; self distillation; remote sensing; distillation ... See more keywords

Self-Distillation Attention for Efficient and Accurate Motion Prediction in Autonomous Driving

Sign Up to like & get
recommendations! Published in 2025 at "IEEE Transactions on Intelligent Transportation Systems"

DOI: 10.1109/tits.2025.3535772

Abstract: The accuracy and stability of motion prediction are crucial for the safe planning of autonomous driving systems. The widely used attention mechanisms effectively improve prediction accuracy. However, their computational cost grows quadratically with sequence length,… read more here.

Keywords: attention; self distillation; prediction; motion prediction ... See more keywords