Applications of knowledge distillation in remote sensing: A survey

Y Himeur, N Aburaed, O Elharrouss, I Varlamis… - Information …, 2024 - Elsevier
With the ever-growing complexity of models in the field of remote sensing (RS), there is an
increasing demand for solutions that balance model accuracy with computational efficiency …

[HTML][HTML] A Survey on Knowledge Distillation: Recent Advancements

A Moslemi, A Briskina, Z Dang, J Li - Machine Learning with Applications, 2024 - Elsevier
Deep learning has achieved notable success across academia, medicine, and industry. Its
ability to identify complex patterns in large-scale data and to manage millions of parameters …

Neuron: Learning context-aware evolving representations for zero-shot skeleton action recognition

Y Chen, J Guo, S Guo, D Tao - arxiv preprint arxiv:2411.11288, 2024 - arxiv.org
Zero-shot skeleton action recognition is a non-trivial task that requires robust unseen
generalization with prior knowledge from only seen classes and shared semantics. Existing …

Knowledge Transfer Across Modalities with Natural Language Supervision

CA Barbano, L Molinaro, E Aiello… - arxiv preprint arxiv …, 2024 - arxiv.org
We present a way to learn novel concepts by only using their textual description. We call this
method Knowledge Transfer. Similarly to human perception, we leverage cross-modal …

Exploring Transferable Homogeneous Groups for Compositional Zero-Shot Learning

Z Rao, J Guo, M Li, Y Chen - arxiv preprint arxiv:2501.10695, 2025 - arxiv.org
Conditional dependency present one of the trickiest problems in Compositional Zero-Shot
Learning, leading to significant property variations of the same state (object) across different …

On Accelerating Edge AI: Optimizing Resource-Constrained Environments

J Sander, A Cohen, VR Dasari, B Venable… - arxiv preprint arxiv …, 2025 - arxiv.org
Resource-constrained edge deployments demand AI solutions that balance high
performance with stringent compute, memory, and energy limitations. In this survey, we …

RoMA: Robust Malware Attribution via Byte-level Adversarial Training with Global Perturbations and Adversarial Consistency Regularization

Y Sun, H Chen, J Guo, A Sun, Z Li, H Liu - arxiv preprint arxiv:2502.07492, 2025 - arxiv.org
Attributing APT (Advanced Persistent Threat) malware to their respective groups is crucial for
threat intelligence and cybersecurity. However, APT adversaries often conceal their …

FedAPA: Server-side Gradient-Based Adaptive Personalized Aggregation for Federated Learning on Heterogeneous Data

Y Sun, A Sun, S Pan, Z Fu, J Guo - arxiv preprint arxiv:2502.07456, 2025 - arxiv.org
Personalized federated learning (PFL) tailors models to clients' unique data distributions
while preserving privacy. However, existing aggregation-weight-based PFL methods often …

Improving Factuality of 3D Brain MRI Report Generation with Paired Image-domain Retrieval and Text-domain Augmentation

J Lee, Y Oh, D Lee, HK Joh, CH Sohn, SH Baik… - arxiv preprint arxiv …, 2024 - arxiv.org
Acute ischemic stroke (AIS) requires time-critical management, with hours of delayed
intervention leading to an irreversible disability of the patient. Since diffusion weighted …

Towards Robust and Realistic Human Pose Estimation via WiFi Signals

Y Chen, J Guo, S Guo, J Zhou, D Tao - arxiv preprint arxiv:2501.09411, 2025 - arxiv.org
Robust WiFi-based human pose estimation is a challenging task that bridges discrete and
subtle WiFi signals to human skeletons. This paper revisits this problem and reveals two …