EXTD: Extremely Tiny Face Detector via Iterative Filter Reuse
This work addresses the need for efficient face detection in resource-constrained environments, though it is incremental as it builds on existing multi-scale detection methods.
The paper tackled the problem of reducing model size in multi-scale face detection by proposing EXTD, an extremely tiny face detector with less than 0.1 million parameters, which achieved comparable performance to much larger detectors on the WIDER FACE dataset.
In this paper, we propose a new multi-scale face detector having an extremely tiny number of parameters (EXTD),less than 0.1 million, as well as achieving comparable performance to deep heavy detectors. While existing multi-scale face detectors extract feature maps with different scales from a single backbone network, our method generates the feature maps by iteratively reusing a shared lightweight and shallow backbone network. This iterative sharing of the backbone network significantly reduces the number of parameters, and also provides the abstract image semantics captured from the higher stage of the network layers to the lower-level feature map. The proposed idea is employed by various model architectures and evaluated by extensive experiments. From the experiments from WIDER FACE dataset, we show that the proposed face detector can handle faces with various scale and conditions, and achieved comparable performance to the more massive face detectors that few hundreds and tens times heavier in model size and floating point operations.