Filter-Pruning of Lightweight Face Detectors Using a Geometric Median Criterion

• URL: http://arxiv.org/abs/2311.16613v1
• Date: Tue, 28 Nov 2023 09:02:38 GMT
• Title: Filter-Pruning of Lightweight Face Detectors Using a Geometric Median Criterion
• Authors: Konstantinos Gkrispanis, Nikolaos Gkalelis, Vasileios Mezaris
• Abstract summary: We implement filter pruning on two already small and compact face detectors, named EXTD and EResFD. The proposed approach has the potential to further reduce the model size of already lightweight face detectors.
• Score: 9.284740716447342
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: Face detectors are becoming a crucial component of many applications, including surveillance, that often have to run on edge devices with limited processing power and memory. Therefore, there's a pressing demand for compact face detection models that can function efficiently across resource-constrained devices. Over recent years, network pruning techniques have attracted a lot of attention from researchers. These methods haven't been well examined in the context of face detectors, despite their expanding popularity. In this paper, we implement filter pruning on two already small and compact face detectors, named EXTD (Extremely Tiny Face Detector) and EResFD (Efficient ResNet Face Detector). The main pruning algorithm that we utilize is Filter Pruning via Geometric Median (FPGM), combined with the Soft Filter Pruning (SFP) iterative procedure. We also apply L1 Norm pruning, as a baseline to compare with the proposed approach. The experimental evaluation on the WIDER FACE dataset indicates that the proposed approach has the potential to further reduce the model size of already lightweight face detectors, with limited accuracy loss, or even with small accuracy gain for low pruning rates.

Related papers

• ESOD: Efficient Small Object Detection on High-Resolution Images [36.80623357577051]
  Small objects are usually sparsely distributed and locally clustered. Massive feature extraction computations are wasted on the non-target background area of images. We propose to reuse the detector's backbone to conduct feature-level object-seeking and patch-slicing.
  arXiv  Detail & Related papers  (2024-07-23T12:21:23Z)
• Learning to Make Keypoints Sub-Pixel Accurate [80.55676599677824]
  This work addresses the challenge of sub-pixel accuracy in detecting 2D local features. We propose a novel network that enhances any detector with sub-pixel precision by learning an offset vector for detected features.
  arXiv  Detail & Related papers  (2024-07-16T12:39:56Z)
• MoE-FFD: Mixture of Experts for Generalized and Parameter-Efficient Face Forgery Detection [54.545054873239295]
  Deepfakes have recently raised significant trust issues and security concerns among the public. ViT-based methods take advantage of the expressivity of transformers, achieving superior detection performance. This work introduces Mixture-of-Experts modules for Face Forgery Detection (MoE-FFD), a generalized yet parameter-efficient ViT-based approach.
  arXiv  Detail & Related papers  (2024-04-12T13:02:08Z)
• Small Object Detection via Coarse-to-fine Proposal Generation and Imitation Learning [52.06176253457522]
  We propose a two-stage framework tailored for small object detection based on the Coarse-to-fine pipeline and Feature Imitation learning. CFINet achieves state-of-the-art performance on the large-scale small object detection benchmarks, SODA-D and SODA-A.
  arXiv  Detail & Related papers  (2023-08-18T13:13:09Z)
• EResFD: Rediscovery of the Effectiveness of Standard Convolution for Lightweight Face Detection [13.357235715178584]
  We re-examine the effectiveness of the standard convolutional block as a lightweight backbone architecture for face detection. We show that heavily channel-pruned standard convolution layers can achieve better accuracy and inference speed. Our proposed detector EResFD obtained 80.4% mAP on WIDER FACE Hard subset which only takes 37.7 ms for VGA image inference on CPU.
  arXiv  Detail & Related papers  (2022-04-04T02:30:43Z)
• MRDet: A Multi-Head Network for Accurate Oriented Object Detection in Aerial Images [51.227489316673484]
  We propose an arbitrary-oriented region proposal network (AO-RPN) to generate oriented proposals transformed from horizontal anchors. To obtain accurate bounding boxes, we decouple the detection task into multiple subtasks and propose a multi-head network. Each head is specially designed to learn the features optimal for the corresponding task, which allows our network to detect objects accurately.
  arXiv  Detail & Related papers  (2020-12-24T06:36:48Z)
• Dense Label Encoding for Boundary Discontinuity Free Rotation Detection [69.75559390700887]
  This paper explores a relatively less-studied methodology based on classification. We propose new techniques to push its frontier in two aspects. Experiments and visual analysis on large-scale public datasets for aerial images show the effectiveness of our approach.
  arXiv  Detail & Related papers  (2020-11-19T05:42:02Z)
• Multiple Infrared Small Targets Detection based on Hierarchical Maximal Entropy Random Walk [12.10092482860325]
  We establish a detection method derived from maximal entropy random walk (MERW) to robustly detect multiple small targets. The proposed method is superior to the state-of-the-art methods in terms of target enhancement, background suppression and multiple small targets detection.
  arXiv  Detail & Related papers  (2020-10-02T11:11:34Z)
• Line-Circle-Square (LCS): A Multilayered Geometric Filter for Edge-Based Detection [2.4054377316708964]
  The proposed filter applies detection, tracking and learning to each defined expert to extract higher level information for judging scenes without over-calculation. The experiment validates the effectiveness of the proposed filter in terms of detection precision and resource usage in both experimental and real-world scenarios.
  arXiv  Detail & Related papers  (2020-08-21T05:28:12Z)
• Anchor-free Small-scale Multispectral Pedestrian Detection [88.7497134369344]
  We propose a method for effective and efficient multispectral fusion of the two modalities in an adapted single-stage anchor-free base architecture. We aim at learning pedestrian representations based on object center and scale rather than direct bounding box predictions. Results show our method's effectiveness in detecting small-scaled pedestrians.
  arXiv  Detail & Related papers  (2020-08-19T13:13:01Z)
• KPNet: Towards Minimal Face Detector [27.68740638740399]
  In this work, we find that the appearance feature of a generic face is discriminative enough for a tiny and shallow neural network to verify from the background. The proposed KPNet detects small facial keypoints instead of the whole face by in a bottom-up manner.
  arXiv  Detail & Related papers  (2020-03-17T05:37:45Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.