DSFD: Dual Shot Face Detector
Not on the map. Why?
Abstract (arXiv)
In this paper, we propose a novel face detection network with three novel contributions that address three key aspects of face detection, including better feature learning, progressive loss design and anchor assign based data augmentation, respectively. First, we propose a Feature Enhance Module (FEM) for enhancing the original feature maps to extend the single shot detector to dual shot detector. Second, we adopt Progressive Anchor Loss (PAL) computed by two different sets of anchors to effectively facilitate the features. Third, we use an Improved Anchor Matching (IAM) by integrating novel anchor assign strategy into data augmentation to provide better initialization for the regressor. Since these techniques are all related to the two-stream design, we name the proposed network as Dual Shot Face Detector (DSFD). Extensive experiments on popular benchmarks, WIDER FACE and FDDB, demonstrate the superiority of DSFD over the state-of-the-art face detectors.
Key facts. Cited by 115 papers in the map (data through 7 Oct 2026). First posted on arXiv 24 Oct 2018.
Builds on
No reference list yet.
Built on by
Citing papers per year: 2021: 35; 2022: 21; 2023: 29; 2024: 12; 2025: 16; 2026: 2.
115 papers.
Sort:
By area:
- 2022Visual Programming: Compositional visual reasoning without trainingcited by 507
- 2021Learning to Enhance Low-Light Image via Zero-Reference Deep Curve Estimationcited by 192
- 2023How Robust is Google's Bard to Adversarial Image Attacks?cited by 177
- 2021Low-Light Image and Video Enhancement Using Deep Learning: A Surveycited by 148
- 2024Exploring the Reasoning Abilities of Multimodal Large Language Models (MLLMs): A Comprehensive Survey on Emerging Trends in Multimodal Reasoningcited by 136
- 2023Low-Light Image Enhancement with Wavelet-based Diffusion Modelscited by 126
- 2022Towards Large-Scale Small Object Detection: Survey and Benchmarkscited by 119
- 2021R2RNet: Low-light Image Enhancement via Real-low to Real-normal Networkcited by 106
- 2021Dual Contrastive Learning for General Face Forgery Detectioncited by 100
- 2021Face Forensics in the Wildcited by 87
- 2021Sample and Computation Redistribution for Efficient Face Detectioncited by 86
- 2021Exploiting Fine-grained Face Forgery Clues via Progressive Enhancement Learningcited by 60
38 more
- 2022DeepPrivacy2: Towards Realistic Full-Body Anonymizationcited by 51
- 2023Towards General Visual-Linguistic Face Forgery Detectioncited by 45
- 2021YOLO5Face: Why Reinventing a Face Detectorcited by 44
- 2023CLOVA: A Closed-Loop Visual Assistant with Tool Usage and Updatecited by 42
- 2021Disentangle Your Dense Object Detectorcited by 37
- 2021Automatic Gaze Analysis: A Survey of Deep Learning based Approachescited by 33
- 2022FSGANv2: Improved Subject Agnostic Face Swapping and Reenactmentcited by 33
- 2021HLA-Face: Joint High-Low Adaptation for Low Light Face Detectioncited by 28
- 2023FarSight: A Physics-Driven Whole-Body Biometric System at Large Distance and Altitudecited by 27
- 2021Pre-training strategies and datasets for facial representation learningcited by 25
- 2023Continual Face Forgery Detection via Historical Distribution Preservingcited by 23
- 2021Learning with Nested Scene Modeling and Cooperative Architecture Search for Low-Light Visioncited by 22
- 2023LDFA: Latent Diffusion Face Anonymization for Self-driving Applicationscited by 21
- 20213D High-Fidelity Mask Face Presentation Attack Detection Challengecited by 18
- 2022Low-Light Image and Video Enhancement: A Comprehensive Survey and Beyondcited by 17
- 2023Boosting Object Detection with Zero-Shot Day-Night Domain Adaptationcited by 17
- 2023Lip Reading for Low-resource Languages by Learning and Combining General Speech Knowledge and Language-specific Knowledgecited by 16
- 2022Realistic Full-Body Anonymization with Surface-Guided GANscited by 15
- 2022YOLO-FaceV2: A Scale and Occlusion Aware Face Detectorcited by 15
- 2021Finding Facial Forgery Artifacts with Parts-Based Detectorscited by 14
- 2022A Guide to Image and Video based Small Object Detection using Deep Learning : Case Study of Maritime Surveillancecited by 14
- 2023Boosting Detection in Crowd Analysis via Underutilized Output Featurescited by 14
- 2022Crowd Localization from Gaussian Mixture Scoped Knowledge and Scoped Teachercited by 12
- 2022PSENet: Progressive Self-Enhancement Network for Unsupervised Extreme-Light Image Enhancementcited by 12
- 2023Does Image Anonymization Impact Computer Vision Training?cited by 12
- 2021Going Deeper Into Face Detection: A Surveycited by 10
- 2023PVG: Progressive Vision Graph for Vision Recognitioncited by 10
- 2021MogFace: Towards a Deeper Appreciation on Face Detectioncited by 9
- 2021CASIA-Face-Africa: A Large-scale African Face Image Databasecited by 9
- 2022ASFD: Automatic and Scalable Face Detectorcited by 9
- 2023Racial Bias within Face Recognition: A Surveycited by 9
- 2023GANonymization: A GAN-based Face Anonymization Framework for Preserving Emotional Expressionscited by 9
- 2023DisguisOR: Holistic Face Anonymization for the Operating Roomcited by 9
- 2025TSCnet: A Text-driven Semantic-level Controllable Framework for Customized Low-Light Image Enhancementcited by 9
- 2022DeePhy: On Deepfake Phylogenycited by 8
- 2021RaidaR: A Rich Annotated Image Dataset of Rainy Street Scenescited by 7
- 2024Deep Portrait Quality Assessment. A NTIRE 2024 Challenge Surveycited by 7
- 2024Relational Programming with Foundation Modelscited by 7
50 most cited of 115 All 115 (JSON)
- 2026NeoLoc-68: End-to-end 68-point neonatal facial landmark localisation in neonatal clinical environments18 Jun 2026
- 2026InfantFace: Detecting infant faces in neonatal clinical environments18 Jun 2026
- 2025Depth-Copy-Paste: Multimodal and Depth-Aware Compositing for Robust Face Detection12 Dec 2025
- 2025MATRIX: Multimodal Agent Tuning for Robust Tool-Use Reasoning9 Oct 2025
- 2025Towards Unified Multimodal Misinformation Detection in Social Media: A Benchmark Dataset and Baseline30 Sep 2025
- 2025Beyond Artificial Misalignment: Detecting and Grounding Semantic-Coordinated Multimodal Manipulations16 Sep 2025
- 2025Boosting Active Defense Persistence: A Two-Stage Defense Framework Combining Interruption and Poisoning Against Deepfake11 Aug 2025
- 2025From Enhancement to Understanding: Build a Generalized Bridge for Low-light Vision via Semantically Consistent Unsupervised Fine-tuning11 Jul 2025
- 2025Towards Lightest Low-Light Image Enhancement Architecture for Mobile Devices6 Jul 2025
- 2025Facial Attribute Based Text Guided Face Anonymization27 May 2025
- 2025MIKU-PAL: An Automated and Standardized Multi-Modal Method for Speech Paralinguistic and Affect Labeling21 May 2025
- 2025Automated Visual Attention Detection using Mobile Eye Tracking in Behavioral Classroom Studies12 May 2025
38 more
- 2025Archival Faces: Detection of Faces in Digitized Historical Documents1 Apr 2025
- 2025FairDeFace: Evaluating the Fairness and Adversarial Robustness of Face Obfuscation Methods11 Mar 2025
- 2025TSCnet: A Text-driven Semantic-level Controllable Framework for Customized Low-Light Image Enhancement11 Mar 2025
- 2025Towards General Visual-Linguistic Face Forgery Detection(V2)28 Feb 2025
- 2025Striving for Faster and Better: A One-Layer Architecture with Auto Re-parameterization for Low-Light Image Enhancement27 Feb 2025
- 2025B-FPGM: Lightweight Face Detection via Bayesian-Optimized Soft FPGM Pruning28 Jan 2025
- 2024Relational Programming with Foundation Models19 Dec 2024
- 2024Hiding Faces in Plain Sight: Defending DeepFakes by Disrupting Face Detection2 Dec 2024
- 2024A Survey on Physical Adversarial Attacks against Face Recognition Systems10 Oct 2024
- 2024Seeing Faces in Things: A Model and Dataset for Pareidolia24 Sep 2024
- 2024Tracking Virtual Meetings in the Wild: Re-identification in Multi-Participant Virtual Meetings15 Sep 2024
- 2024FDLite: A Single Stage Lightweight Face Detector Network27 Jun 2024
- 2024SynthForge: Synthesizing High-Quality Face Dataset with Controllable 3D Generative Models12 Jun 2024
- 2024Exploring AI-based Anonymization of Industrial Image and Video Data in the Context of Feature Preservation29 May 2024
- 2024Deep Portrait Quality Assessment. A NTIRE 2024 Challenge Survey17 Apr 2024
- 2024DI-Retinex: Digital-Imaging Retinex Theory for Low-Light Image Enhancement4 Apr 2024
- 2024AnnoTheia: A Semi-Automatic Annotation Toolkit for Audio-Visual Speech Technologies20 Feb 2024
- 2024Exploring the Reasoning Abilities of Multimodal Large Language Models (MLLMs): A Comprehensive Survey on Emerging Trends in Multimodal Reasoning10 Jan 2024
- 2023CLOVA: A Closed-Loop Visual Assistant with Tool Usage and Update18 Dec 2023
- 2023Boosting Object Detection with Zero-Shot Day-Night Domain Adaptation2 Dec 2023
- 2023Filter-Pruning of Lightweight Face Detectors Using a Geometric Median Criterion28 Nov 2023
- 2023Zero-Shot Enhancement of Low-Light Image Based on Retinex Decomposition6 Nov 2023
- 2023Fully Quantized Always-on Face Detector Considering Mobile Image Sensors2 Nov 2023
- 2023Skipped Feature Pyramid Network with Grid Anchor for Object Detection22 Oct 2023
- 2023How Robust is Google's Bard to Adversarial Image Attacks?21 Sep 2023
- 2023Trash to Treasure: Low-Light Object Detection via Decomposition-and-Aggregation7 Sep 2023
- 2023Boosting Detection in Crowd Analysis via Underutilized Output Features30 Aug 2023
- 2023Lip Reading for Low-resource Languages by Learning and Combining General Speech Knowledge and Language-specific Knowledge18 Aug 2023
- 2023Neural Networks at a Fraction with Pruned Quaternions13 Aug 2023
- 2023Continual Face Forgery Detection via Historical Distribution Preserving11 Aug 2023
- 2023Bilevel Generative Learning for Low-Light Vision7 Aug 2023
- 2023PVG: Progressive Vision Graph for Vision Recognition1 Aug 2023
- 2023Towards General Visual-Linguistic Face Forgery Detection31 Jul 2023
- 2023Learning with Constraint Learning: New Perspective, Solution Strategy and Various Applications28 Jul 2023
- 2023DisguisOR: Holistic Face Anonymization for the Operating Room26 Jul 2023
- 2023FarSight: A Physics-Driven Whole-Body Biometric System at Large Distance and Altitude29 Jun 2023
- 2023Does Image Anonymization Impact Computer Vision Training?8 Jun 2023
- 2023Unsupervised network for low-light enhancement5 Jun 2023
50 newest of 115 All 115 (JSON)
- 2022Visual Programming: Compositional visual reasoning without trainingcited by 507
- 2024Exploring the Reasoning Abilities of Multimodal Large Language Models (MLLMs): A Comprehensive Survey on Emerging Trends in Multimodal Reasoningcited by 136
- 2025MATRIX: Multimodal Agent Tuning for Robust Tool-Use Reasoningcited by 1
- 2025MATRIX: Multimodal Agent Tuning for Robust Tool-Use Reasoning9 Oct 2025
- 2024Exploring the Reasoning Abilities of Multimodal Large Language Models (MLLMs): A Comprehensive Survey on Emerging Trends in Multimodal Reasoning10 Jan 2024
- 2022Visual Programming: Compositional visual reasoning without training18 Nov 2022
- 2023How Robust is Google's Bard to Adversarial Image Attacks?cited by 177
- 2023How Robust is Google's Bard to Adversarial Image Attacks?21 Sep 2023
- 2021Learning to Enhance Low-Light Image via Zero-Reference Deep Curve Estimationcited by 192
- 2021Low-Light Image and Video Enhancement Using Deep Learning: A Surveycited by 148
- 2022Towards Large-Scale Small Object Detection: Survey and Benchmarkscited by 119
- 2021R2RNet: Low-light Image Enhancement via Real-low to Real-normal Networkcited by 106
- 2021Dual Contrastive Learning for General Face Forgery Detectioncited by 100
- 2021Face Forensics in the Wildcited by 87
- 2021Sample and Computation Redistribution for Efficient Face Detectioncited by 86
- 2021Exploiting Fine-grained Face Forgery Clues via Progressive Enhancement Learningcited by 60
- 2022DeepPrivacy2: Towards Realistic Full-Body Anonymizationcited by 51
- 2023Towards General Visual-Linguistic Face Forgery Detectioncited by 45
- 2021YOLO5Face: Why Reinventing a Face Detectorcited by 44
- 2023CLOVA: A Closed-Loop Visual Assistant with Tool Usage and Updatecited by 42
12 most cited of 109 All 109 (JSON)
- 2026NeoLoc-68: End-to-end 68-point neonatal facial landmark localisation in neonatal clinical environments18 Jun 2026
- 2026InfantFace: Detecting infant faces in neonatal clinical environments18 Jun 2026
- 2025Depth-Copy-Paste: Multimodal and Depth-Aware Compositing for Robust Face Detection12 Dec 2025
- 2025Towards Unified Multimodal Misinformation Detection in Social Media: A Benchmark Dataset and Baseline30 Sep 2025
- 2025Beyond Artificial Misalignment: Detecting and Grounding Semantic-Coordinated Multimodal Manipulations16 Sep 2025
- 2025Boosting Active Defense Persistence: A Two-Stage Defense Framework Combining Interruption and Poisoning Against Deepfake11 Aug 2025
- 2025From Enhancement to Understanding: Build a Generalized Bridge for Low-light Vision via Semantically Consistent Unsupervised Fine-tuning11 Jul 2025
- 2025Towards Lightest Low-Light Image Enhancement Architecture for Mobile Devices6 Jul 2025
- 2025Facial Attribute Based Text Guided Face Anonymization27 May 2025
- 2025MIKU-PAL: An Automated and Standardized Multi-Modal Method for Speech Paralinguistic and Affect Labeling21 May 2025
- 2025Automated Visual Attention Detection using Mobile Eye Tracking in Behavioral Classroom Studies12 May 2025
- 2025Archival Faces: Detection of Faces in Digitized Historical Documents1 Apr 2025
12 newest of 109 All 109 (JSON)