PulseAugur
EN
LIVE 17:21:04

New HumP-KD framework efficiently distills fire classification models

By PulseAugur Editorial · [2 sources] ·

Researchers have developed HumP-KD, a novel framework for efficient fire classification using knowledge distillation. This method distills knowledge from larger transformer models like Swin-Tiny and ViT-Base into a smaller, lightweight MobileViT-S student model. The framework achieves a high F1 score of 0.9876 on the Dataset-II, significantly outperforming the baseline student model while maintaining a compact size and high processing speed suitable for real-time deployment. AI

IMPACT Enables more efficient and deployable AI models for real-time classification tasks on resource-constrained hardware.

RANK_REASON The cluster describes a new academic paper detailing a novel framework for a specific machine learning task.

Read on arXiv cs.LG →

AI-generated summary · Google Gemini · from 2 sources. How we write summaries →

New HumP-KD framework efficiently distills fire classification models

COVERAGE [2]

  1. arXiv cs.LG TIER_1 English(EN) · Mohammed Arif Mainuddin, Najifa Tabassum, Omar Ibne Shahid, Riasat Khan ·

    HumP-KD: A Hybrid Uncertainty-Aware Multi-Stage Progressive Knowledge Distillation Framework for Efficient Fire Classification

    arXiv:2606.14684v1 Announce Type: cross Abstract: Real-time fire classification systems require models that are simultaneously accurate, computationally efficient, and deployable on resource-constrained hardware. This work proposes \textbf{HumP-KD}, a Hybrid Uncertainty-aware Mul…

  2. arXiv cs.CV TIER_1 English(EN) · Riasat Khan ·

    HumP-KD: A Hybrid Uncertainty-Aware Multi-Stage Progressive Knowledge Distillation Framework for Efficient Fire Classification

    Real-time fire classification systems require models that are simultaneously accurate, computationally efficient, and deployable on resource-constrained hardware. This work proposes \textbf{HumP-KD}, a Hybrid Uncertainty-aware Multi-stage Progressive Knowledge Distillation framew…

RELATED ENTITIES

RELATED TOPICS