Applications of knowledge distillation in remote sensing: A survey
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 …
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 …
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
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 …
generalization with prior knowledge from only seen classes and shared semantics. Existing …
Knowledge Transfer Across Modalities with Natural Language Supervision
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 …
method Knowledge Transfer. Similarly to human perception, we leverage cross-modal …
Exploring Transferable Homogeneous Groups for Compositional Zero-Shot Learning
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 …
Learning, leading to significant property variations of the same state (object) across different …
On Accelerating Edge AI: Optimizing Resource-Constrained Environments
Resource-constrained edge deployments demand AI solutions that balance high
performance with stringent compute, memory, and energy limitations. In this survey, we …
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 …
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 …
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 …
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 …
subtle WiFi signals to human skeletons. This paper revisits this problem and reveals two …