GlimmerNet: A Lightweight Grouped Dilated Depthwise Convolutions for UAV-Based Emergency Monitoring
This provides an efficient solution for real-time emergency monitoring on resource-constrained UAV platforms.
The paper tackles the problem of achieving global perception in convolutional neural networks for UAV-based emergency monitoring without computational overhead, and presents GlimmerNet which achieves a state-of-the-art weighted F1-score of 0.966 on the AIDERv2 dataset with only 31K parameters and 29% fewer FLOPs than baselines.
Convolutional Neural Networks (CNNs) have proven highly effective for edge and mobile vision tasks due to their computational efficiency. While many recent works seek to enhance CNNs with global contextual understanding via self-attention-based Vision Transformers, these approaches often introduce significant computational overhead. In this work, we demonstrate that it is possible to retain strong global perception without relying on computationally expensive components. We present GlimmerNet, an ultra-lightweight convolutional network built on the principle of separating receptive field diversity from feature recombination. GlimmerNet introduces Grouped Dilated Depthwise Convolutions(GDBlocks), which partition channels into groups with distinct dilation rates, enabling multi-scale feature extraction at no additional parameter cost. To fuse these features efficiently, we design a novel Aggregator module that recombines cross-group representations using grouped pointwise convolution, significantly lowering parameter overhead. With just 31K parameters and 29% fewer FLOPs than the most recent baseline, GlimmerNet achieves a new state-of-the-art weighted F1-score of 0.966 on the UAV-focused AIDERv2 dataset. These results establish a new accuracy-efficiency trade-off frontier for real-time emergency monitoring on resource-constrained UAV platforms. Our implementation is publicly available at https://github.com/djordjened92/gdd-cnn.