HAMBox: Delving into Online High-quality Anchors Mining for Detecting Outer Faces

2019-12-19 · Yang Liu, Xu Tang, Xiang Wu, Junyu Han, Jingtuo Liu, Errui Ding

Current face detectors utilize anchors to frame a multi-task learning problem which combines classification and bounding box regression. Effective anchor design and anchor matching strategy enable face detectors to localize faces under large pose and scale variations. However, we observe that more than 80% correctly predicted bounding boxes are regressed from the unmatched anchors (the IoUs between anchors and target faces are lower than a threshold) in the inference phase. It indicates that these unmatched anchors perform excellent regression ability, but the existing methods neglect to learn from them. In this paper, we propose an Online High-quality Anchor Mining Strategy (HAMBox), which explicitly helps outer faces compensate with high-quality anchors. Our proposed HAMBox method could be a general strategy for anchor-based single-stage face detection. Experiments on various datasets, including WIDER FACE, FDDB, AFW and PASCAL Face, demonstrate the superiority of the proposed method. Furthermore, our team win the championship on the Face Detection test track of WIDER Face and Pedestrian Challenge 2019. We will release the codes with PaddlePaddle.

📄 PDF Abstract BibTeX arXiv:1912.09231

Code (0)

등록된 구현이 없습니다.

Tasks

Face Detection Multi-Task Learning regression Vocal Bursts Intensity Prediction

Methods 이 논문이 사용한 방법론

Test 설명 없음

HAMBox: Delving Into Mining High-Quality Anchors on Face Detection

2020-06-01 · CVPR 2020 6 · Yang Liu, Xu Tang, Junyu Han, Jingtuo Liu 외

Face Detection Multi-Task Learning regression Vocal Bursts Intensity Prediction

Delving into the Cyclic Mechanism in Semi-supervised Video Object Segmentation

2020-10-23 · NeurIPS 2020 12 · Yuxi Li, Ning Xu, Jinlong Peng, John See 외

In this paper, we address several inadequacies of current video object segmentation pipelines. Firstly, a cyclic mechanism is incorporated to the standard semi-supervised process to produce more robust representations. B…

Object One-shot visual object segmentation Segmentation Semantic Segmentation+3

Delving into Deep Image Prior for Adversarial Defense: A Novel Reconstruction-based Defense Framework

2021-07-31 · Li Ding, Yongwei Wang, Xin Ding, Kaiwen Yuan 외

Deep learning based image classification models are shown vulnerable to adversarial attacks by injecting deliberately crafted noises to clean images. To defend against adversarial attacks in a training-free and attack-ag…

Adversarial Defense image-classification Image Classification Image Reconstruction

Hubness and Pollution: Delving into Cross-Space Mapping for Zero-Shot Learning

2015-07-01 · IJCNLP 2015 7 · Angeliki Lazaridou, Georgiana Dinu, Marco Baroni

Semantic Textual Similarity Zero-Shot Learning

Delving into: the quantification of Ai-generated content on the internet (synthetic data)

2025-03-29 · Dirk HR Spennemann

While it is increasingly evident that the internet is becoming saturated with content created by generated Ai large language models, accurately measuring the scale of this phenomenon has proven challenging. By analyzing …