Methods › Computer Vision › One-Stage Object Detection Models › RetinaNet
RetinaNet
Introduced by Tsung-Yi Lin et al. in Focal Loss for Dense Object Detection
archive 2025-07-28 Description, source and code snippet are the archive's method entry.
RetinaNet is a one-stage object detection model that utilizes a focal loss function to address class imbalance during training. Focal loss applies a modulating term to the cross entropy loss in order to focus learning on hard negative examples. RetinaNet is a single, unified network composed of a backbone network and two task-specific subnetworks. The backbone is responsible for computing a convolutional feature map over an entire input image and is an off-the-shelf convolutional network. The first subnet performs convolutional object classification on the backbone's output; the second subnet performs convolutional bounding box regression. The two subnetworks feature a simple design that the authors propose specifically for one-stage, dense detection.
We can see the motivation for focal loss by comparing with two-stage object detectors. Here class imbalance is addressed by a two-stage cascade and sampling heuristics. The proposal stage (e.g., Selective Search, EdgeBoxes, DeepMask, RPN) rapidly narrows down the number of candidate object locations to a small number (e.g., 1-2k), filtering out most background samples. In the second classification stage, sampling heuristics, such as a fixed foreground-to-background ratio, or online hard example mining (OHEM), are performed to maintain a manageable balance between foreground and background.
In contrast, a one-stage detector must process a much larger set of candidate object locations regularly sampled across an image. To tackle this, RetinaNet uses a focal loss function, a dynamically scaled cross entropy loss, where the scaling factor decays to zero as confidence in the correct class increases. Intuitively, this scaling factor can automatically down-weight the contribution of easy examples during training and rapidly focus the model on hard examples.
Formally, the Focal Loss adds a factor (1 - pₜ)^γ to the standard cross entropy criterion. Setting γ>0 reduces the relative loss for well-classified examples (pₜ>.5), putting more focus on hard, misclassified examples. Here there is tunable focusing parameter γ≥0.
FL(pₜ) = - (1 - pₜ)^γ log(pₜ)
In Syntology name not resolved (unknown_name). The lookup matched no method, paper or venue by this name; that asserts nothing about whether code exists.
Syntology's have check for this name (free, it answers coverage only), read 2026-10-05; ask it again live. A level is the served verification level of that one answer; nothing here is summed across methods.
Papers archive 2025-07-28
archive papers tagged: 209 · with a code link: 124 · where Syntology ran a sample: 32 (26 with a run with no instrument failure, 6 where every run was a failure of Syntology's instrument) Syntology
Show: all tagged papersonly where code ran (32 of 209 tagged: 26 with a run with no instrument failure, 6 where every run was a failure of Syntology's instrument)
Page 1 of 3: papers 1 to 100 of 209, newest first by the archive's date (ties by slug), in archive order.
Repository counts are the archive's code-links table. A Syntology line states what Syntology ran from that paper's harvested code, as “N ran (of which C constructed an object rather than computing a result; K with no instrument failure: H honoured, V violated, P with no contract checked; I where Syntology's instrument failed) · U unverified”; the instrument figure counts failures of Syntology's instrument, not of the code. It is per sample and not a correctness claim. When the archive marks a repository official for the paper, the line starts with that repository's state (the archive's flag, not a verdict on who wrote the code; “community repositories only” when every sample that ran came from a community repository, “official: no sample here; runs from other or unrecorded repositories” when some came from a repository the paper names or has in its text, or from none recorded); hover it for the repositories the samples that ran came from.
-
PaniCar: Securing the Perception of Advanced Driving Assistance Systems Against Emergency Vehicle Lighting 8 May 2025 · 0 repositories · arXiv:2505.05183
-
Class Imbalance Correction for Improved Universal Lesion Detection and Tagging in CT 8 Apr 2025 · 0 repositories · arXiv:2504.05591
-
Fast-COS: A Fast One-Stage Object Detector Based on Reparameterized Attention Vision Transformer for Autonomous Driving 11 Feb 2025 · 0 repositories · arXiv:2502.07417
-
Dual Scale-aware Adaptive Masked Knowledge Distillation for Object Detection 13 Jan 2025 · 0 repositories · arXiv:2501.07101
-
Detection of Body Packs in Abdominal CT scans Through Artificial Intelligence 26 Dec 2024 · 1 repository
-
Distortion-Aware Adversarial Attacks on Bounding Boxes of Object Detectors 25 Dec 2024 · 1 repository · arXiv:2412.18815
-
EMOv2: Pushing 5M Vision Model Frontier 9 Dec 2024 · 1 repository · arXiv:2412.06674
-
Psych-Occlusion: Using Visual Psychophysics for Aerial Detection of Occluded Persons during Search and Rescue 7 Dec 2024 · 1 repository · arXiv:2412.05553
-
One-Stage-TFS: Thai One-Stage Fingerspelling Dataset for Fingerspelling Recognition Frameworks 5 Nov 2024 · 0 repositories · arXiv:2411.02768
-
Explicitly Modeling Pre-Cortical Vision with a Neuro-Inspired Front-End Improves CNN Robustness 25 Sep 2024 · 1 repository · arXiv:2409.16838
-
LithoHoD: A Litho Simulator-Powered Framework for IC Layout Hotspot Detection 16 Sep 2024 · 0 repositories · arXiv:2409.10021
-
On Feasibility of Intent Obfuscating Attacks 22 Jul 2024 · 1 repository · arXiv:2408.02674
-
FAD-SAR: A Novel Fishing Activity Detection System via Synthetic Aperture Radar Images Based on Deep Learning Method 28 Apr 2024 · 0 repositories · arXiv:2404.18245
-
FlightScope: An Experimental Comparative Review of Aircraft Detection Algorithms in Satellite Imagery 3 Apr 2024 · 1 repository · arXiv:2404.02877
-
Investigation of the Impact of Synthetic Training Data in the Industrial Application of Terminal Strip Object Detection 6 Mar 2024 · 0 repositories · arXiv:2403.04809
-
A Safety-Adapted Loss for Pedestrian Detection in Automated Driving 5 Feb 2024 · 0 repositories · arXiv:2402.02986
-
pLitterStreet: Street Level Plastic Litter Detection and Mapping 26 Jan 2024 · 1 repository · arXiv:2401.14719
-
DyRA: Portable Dynamic Resolution Adjustment Network for Existing Detectors 28 Nov 2023 · 2 repositories · arXiv:2311.17098
-
P2RBox: Point Prompt Oriented Object Detection with SAM 22 Nov 2023 · 0 repositories · arXiv:2311.13128
-
Anchor-Intermediate Detector: Decoupling and Coupling Bounding Boxes for Accurate Object Detection 9 Oct 2023 · 1 repository · arXiv:2310.05666
-
HalluciDet: Hallucinating RGB Modality for Person Detection Through Privileged Information 7 Oct 2023 · 1 repository · arXiv:2310.04662
-
AI-Dentify: Deep learning for proximal caries detection on bitewing x-ray -- HUNT4 Oral Health Study 30 Sep 2023 · 0 repositories · arXiv:2310.00354
-
UniHead: Unifying Multi-Perception for Detection Heads 23 Sep 2023 · 1 repository · arXiv:2309.13242
-
DMKD: Improving Feature-based Knowledge Distillation for Object Detection Via Dual Masking Augmentation 6 Sep 2023 · 0 repositories · arXiv:2309.02719
-
Learning Lightweight Object Detectors via Multi-Teacher Progressive Distillation 17 Aug 2023 · 0 repositories · arXiv:2308.09105
-
AlignDet: Aligning Pre-training and Fine-tuning in Object Detection 20 Jul 2023 · 1 repository · arXiv:2307.11077Syntology official (archive's flag): 2 ran · 2 ran (of which 0 constructed an object rather than computing a result; 0 with no instrument failure: 0 honoured, 0 violated, 0 with no contract checked; 2 where Syntology's instrument failed) · 0 unverified (of 2 harvested samples)
-
DeepScribe: Localization and Classification of Elamite Cuneiform Signs Via Deep Learning 2 Jun 2023 · 1 repository · arXiv:2306.01268
-
Deep-learning Assisted Detection and Quantification of (oo)cysts of Giardia and Cryptosporidium on Smartphone Microscopy Images 11 Apr 2023 · 1 repository · arXiv:2304.05339
-
Adaptive Sparse Convolutional Networks with Global Context Enhancement for Faster Object Detection on Drone Images 25 Mar 2023 · 1 repository · arXiv:2303.14488Syntology official (archive's flag): 4 ran · 4 ran (of which 0 constructed an object rather than computing a result; 2 with no instrument failure: 0 honoured, 0 violated, 2 with no contract checked; 2 where Syntology's instrument failed) · 2 unverified (of 6 harvested samples) · 4 pointer-only (licence)
-
Adaptive Rotated Convolution for Rotated Object Detection 14 Mar 2023 · 1 repository · arXiv:2303.07820Syntology official (archive's flag): 3 ran · 3 ran (of which 1 constructed an object rather than computing a result; 1 with no instrument failure: 0 honoured, 0 violated, 1 with no contract checked; 2 where Syntology's instrument failed) · 0 unverified (of 3 harvested samples)
-
Diffusion-Based Hierarchical Multi-Label Object Detection to Analyze Panoramic Dental X-rays 11 Mar 2023 · 2 repositories · arXiv:2303.06500Syntology official (archive's flag): 1 ran · 1 ran (of which 0 constructed an object rather than computing a result; 0 with no instrument failure: 0 honoured, 0 violated, 0 with no contract checked; 1 where Syntology's instrument failed) · 0 unverified (of 1 harvested sample)
-
R-TOSS: A Framework for Real-Time Object Detection using Semi-Structured Pruning 3 Mar 2023 · 0 repositories · arXiv:2303.02191
-
Optimizing YOLOv7 for Semiconductor Defect Detection 19 Feb 2023 · 0 repositories · arXiv:2302.09565
-
Efficient Teacher: Semi-Supervised Object Detection for YOLOv5 15 Feb 2023 · 4 repositories · arXiv:2302.07577Syntology official (archive's flag): 3 ran · 3 ran (of which 0 constructed an object rather than computing a result; 3 with no instrument failure: 2 honoured, 1 violated, 0 with no contract checked; 0 where Syntology's instrument failed) · 0 unverified (of 3 harvested samples) · 3 pointer-only (licence)
-
Threatening Patch Attacks on Object Detection in Optical Remote Sensing Images 13 Feb 2023 · 1 repository · arXiv:2302.06060
-
Dual Relation Knowledge Distillation for Object Detection 11 Feb 2023 · 1 repository · arXiv:2302.05637
-
AMD: Adaptive Masked Distillation for Object Detection 31 Jan 2023 · 0 repositories · arXiv:2301.13538
-
Masked Autoencoders Are Stronger Knowledge Distillers 1 Jan 2023 · 0 repositories
-
Cattle Detection Occlusion Problem 21 Dec 2022 · 0 repositories · arXiv:2212.11418
-
Deep-Learning-Based Computer Vision Approach For The Segmentation Of Ball Deliveries And Tracking In Cricket 22 Nov 2022 · 1 repository · arXiv:2211.12009
-
Benchmarking Edge Computing Devices for Grape Bunches and Trunks Detection using Accelerated Object Detection Single Shot MultiBox Deep Learning Models 21 Nov 2022 · 0 repositories · arXiv:2211.11647
-
TSAA: A Two-Stage Anchor Assignment Method towards Anchor Drift in Crowded Object Detection 2 Nov 2022 · 0 repositories · arXiv:2211.00826
-
Deep Learning Object Detection Approaches to Signal Identification 27 Oct 2022 · 0 repositories · arXiv:2210.16173
-
Distilling Object Detectors With Global Knowledge 17 Oct 2022 · 1 repository · arXiv:2210.09022
-
Towards Discriminative and Transferable One-Stage Few-Shot Object Detectors 11 Oct 2022 · 0 repositories · arXiv:2210.05783
-
Deep object detection for waterbird monitoring using aerial imagery 10 Oct 2022 · 1 repository · arXiv:2210.04868
-
Query-based Hard-Image Retrieval for Object Detection at Test Time 23 Sep 2022 · 1 repository · arXiv:2209.11559
-
Optimizing Anchor-based Detectors for Autonomous Driving Scenes 11 Aug 2022 · 0 repositories · arXiv:2208.06062
-
Learning to Identify Drilling Defects in Turbine Blades with Single Stage Detectors 8 Aug 2022 · 0 repositories · arXiv:2208.04363
-
Task-Balanced Distillation for Object Detection 5 Aug 2022 · 0 repositories · arXiv:2208.03006
-
Classification of Bark Beetle-Induced Forest Tree Mortality using Deep Learning 15 Jul 2022 · 1 repository · arXiv:2207.07241
-
HEAD: HEtero-Assists Distillation for Heterogeneous Object Detectors 12 Jul 2022 · 1 repository · arXiv:2207.05345
-
Shadow-Background-Noise 3D Spatial Decomposition Using Sparse Low-Rank Gaussian Properties for Video-SAR Moving Target Shadow Enhancement 7 Jul 2022 · 0 repositories · arXiv:2207.03064
-
PKD: General Distillation Framework for Object Detectors via Pearson Correlation Coefficient 5 Jul 2022 · 1 repository · arXiv:2207.02039
-
Deep Learning-Based Defect Classification and Detection in SEM Images 20 Jun 2022 · 0 repositories · arXiv:2206.13505
-
Selective Multi-Scale Learning for Object Detection 16 Jun 2022 · 0 repositories · arXiv:2206.08206
-
Efficient Decoder-free Object Detection with Transformers 14 Jun 2022 · 2 repositories · arXiv:2206.06829Syntology community repositories only · 1 ran (of which 0 constructed an object rather than computing a result; 1 with no instrument failure: 0 honoured, 0 violated, 1 with no contract checked; 0 where Syntology's instrument failed) · 0 unverified (of 1 harvested sample) · 1 pointer-only (licence)
-
MoCoViT: Mobile Convolutional Vision Transformer 25 May 2022 · 1 repository · arXiv:2205.12635
-
The Impact of Partial Occlusion on Pedestrian Detectability 10 May 2022 · 2 repositories · arXiv:2205.04812
-
Masked Generative Distillation 3 May 2022 · 3 repositories · arXiv:2205.01529
-
Sparsely-gated Mixture-of-Expert Layers for CNN Interpretability 22 Apr 2022 · 0 repositories · arXiv:2204.10598
-
What's in the Black Box? The False Negative Mechanisms Inside Object Detectors 15 Mar 2022 · 1 repository · arXiv:2203.07662
-
SEA: Bridging the Gap Between One- and Two-stage Detector Distillation via SEmantic-aware Alignment 2 Mar 2022 · 0 repositories · arXiv:2203.00862
-
Knowledge Distillation for Object Detection via Rank Mimicking and Prediction-guided Feature Imitation 9 Dec 2021 · 0 repositories · arXiv:2112.04840
-
Searching Parameterized AP Loss for Object Detection 9 Dec 2021 · 1 repository · arXiv:2112.05138Syntology official (archive's flag): 1 ran · 1 ran (of which 1 constructed an object rather than computing a result; 1 with no instrument failure: 0 honoured, 0 violated, 1 with no contract checked; 0 where Syntology's instrument failed) · 0 unverified; the one sample that ran constructed an object rather than computing a result (of 1 harvested sample)
-
Container: Context Aggregation Networks 1 Dec 2021 · 2 repositories
-
Focal and Global Knowledge Distillation for Detectors 23 Nov 2021 · 1 repository · arXiv:2111.11837
-
Rethinking Drone-Based Search and Rescue with Aerial Person Detection 17 Nov 2021 · 1 repository · arXiv:2111.09406
-
Fracture Detection in Wrist X-ray Images Using Deep Learning-Based Object Detection Models 14 Nov 2021 · 0 repositories · arXiv:2111.07355
-
First steps on Gamification of Lung Fluid Cells Annotations in the Flower Domain 5 Nov 2021 · 0 repositories · arXiv:2111.03663
-
Remote Sensing Image Super-resolution and Object Detection: Benchmark and State of the Art 5 Nov 2021 · 0 repositories · arXiv:2111.03260
-
Distilling Object Detectors with Feature Richness 1 Nov 2021 · 1 repository · arXiv:2111.00674
-
Instance-Conditional Knowledge Distillation for Object Detection 25 Oct 2021 · 1 repository · arXiv:2110.12724
-
RCNet: Reverse Feature Pyramid and Cross-scale Shift Network for Object Detection 23 Oct 2021 · 0 repositories · arXiv:2110.12130
-
Automated Multi-Process CTC Detection using Deep Learning 26 Sep 2021 · 0 repositories · arXiv:2109.12709
-
LGD: Label-guided Self-distillation for Object Detection 23 Sep 2021 · 1 repository · arXiv:2109.11496
-
MitoDet: Simple and robust mitosis detection 2 Sep 2021 · 0 repositories · arXiv:2109.01485
-
Assessing domain adaptation techniques for mitosis detection in multi-scanner breast cancer histopathology images 1 Sep 2021 · 1 repository · arXiv:2109.00869
-
Deployment of Deep Neural Networks for Object Detection on Edge AI Devices with Runtime Optimization 18 Aug 2021 · 0 repositories · arXiv:2108.08166
-
Mobile-Former: Bridging MobileNet and Transformer 12 Aug 2021 · 4 repositories · arXiv:2108.05895
-
Towards Robust Object Detection: Bayesian RetinaNet for Homoscedastic Aleatoric Uncertainty Modeling 2 Aug 2021 · 0 repositories · arXiv:2108.00784
-
DPT: Deformable Patch-based Transformer for Visual Recognition 30 Jul 2021 · 1 repository · arXiv:2107.14467Syntology official (archive's flag): 1 ran · 1 ran (of which 0 constructed an object rather than computing a result; 0 with no instrument failure: 0 honoured, 0 violated, 0 with no contract checked; 1 where Syntology's instrument failed) · 0 unverified (of 1 harvested sample)
-
Object Tracking and Geo-localization from Street Images 13 Jul 2021 · 0 repositories · arXiv:2107.06257
-
Disentangle Your Dense Object Detector 7 Jul 2021 · 2 repositories · arXiv:2107.02963
-
Simple Training Strategies and Model Scaling for Object Detection 30 Jun 2021 · 1 repository · arXiv:2107.00057
-
SRPN: similarity-based region proposal networks for nuclei and cells detection in histology images 25 Jun 2021 · 1 repository · arXiv:2106.13556
-
RankDetNet: Delving Into Ranking Constraints for Object Detection 19 Jun 2021 · 0 repositories
-
Potato Crop Stress Identification in Aerial Images using Deep Learning-based Object Detection 14 Jun 2021 · 0 repositories · arXiv:2106.07770
-
RetinaNet Object Detector based on Analog-to-Spiking Neural Network Conversion 10 Jun 2021 · 1 repository · arXiv:2106.05624
-
Oriented Object Detection with Transformer 6 Jun 2021 · 0 repositories · arXiv:2106.03146
-
Container: Context Aggregation Network 2 Jun 2021 · 4 repositories · arXiv:2106.01401Syntology official (archive's flag): 1 ran · 4 ran (of which 0 constructed an object rather than computing a result; 3 with no instrument failure: 0 honoured, 0 violated, 3 with no contract checked; 1 where Syntology's instrument failed) · 3 unverified (of 7 harvested samples)
-
Augmenting Anchors by the Detector Itself 28 May 2021 · 1 repository · arXiv:2105.14086
-
An interpretable object detection based model for the diagnosis of neonatal lung diseases using Ultrasound images 21 May 2021 · 0 repositories · arXiv:2105.10081
-
Scene Understanding for Autonomous Driving 11 May 2021 · 0 repositories · arXiv:2105.04905
-
Active Terahertz Imaging Dataset for Concealed Object Detection 8 May 2021 · 1 repository · arXiv:2105.03677
-
Artificial and beneficial -- Exploiting artificial images for aerial vehicle detection 7 Apr 2021 · 0 repositories · arXiv:2104.03054
-
Multiple instance active learning for object detection 6 Apr 2021 · 1 repository · arXiv:2104.02324Syntology official (archive's flag): 1 ran · 1 ran (of which 0 constructed an object rather than computing a result; 1 with no instrument failure: 0 honoured, 0 violated, 1 with no contract checked; 0 where Syntology's instrument failed) · 0 unverified (of 1 harvested sample)
-
Uncertainty for Identifying Open-Set Errors in Visual Object Detection 3 Apr 2021 · 1 repository · arXiv:2104.01328
-
Anchor Pruning for Object Detection 1 Apr 2021 · 1 repository · arXiv:2104.00432
-
Scale-aware Automatic Augmentation for Object Detection 31 Mar 2021 · 1 repository · arXiv:2103.17220
Tasks archive 2025-07-28
20 shown of 153 tasks the archive attaches to papers tagged with this method, by distinct papers. A task without a page in the catalog is plain text.
Usage over time archive 2025-07-28
Components: the archive holds no method-to-method composition, so PwC's Components table cannot be rebuilt; the Papers list carries no Results column for the same reason (the archive does not join its leaderboard rows to method tags).
Categories archive 2025-07-28
Report a problem or propose a change · a person checks every report against the paper or source before anything changes; decisions are listed on /corrections