Browse State-of-the-Art › Semi-Supervised Object Detection
Semi-Supervised Object Detection
51 papers with code · 7 benchmarks · 1 dataset archive 2025-07-28
Semi-supervised object detection uses both labeled data and unlabeled data for training. It not only reduces the annotation burden for training high-performance object detectors but also further improves the object detector by using a large number of unlabeled data.
Description from the archive archive 2025-07-28.
Benchmarks archive 2025-07-28
7 leaderboard tables shown for this task, 7 with rows (a “benchmark” on this site is a table with at least one row, as on /sota), ordered by row count. “Best model” is the first row in the archive's own order at snapshot; nothing is re-ranked here and metric direction is not recorded in the archive. PwC's Trend sparklines are not in the archive, so that column is omitted.
| Dataset | Best model (first row in archive order) | Paper | Code | Syntology | Compare |
|---|---|---|---|---|---|
| COCO 10% labeled data (27 rows) | MixPL | Mixed Pseudo Labels for Semi-Supervised Object Detection | code | — | Compare |
| COCO 5% labeled data (23 rows) | Semi-DETR | Semi-DETR: Semi-Supervised Object Detection with Detection Transformers | code | — | Compare |
| COCO 1% labeled data (22 rows) | MixPL | Mixed Pseudo Labels for Semi-Supervised Object Detection | code | — | Compare |
| COCO 2% labeled data (19 rows) | MixPL | Mixed Pseudo Labels for Semi-Supervised Object Detection | code | — | Compare |
| COCO 100% labeled data (13 rows) | MixPL | Mixed Pseudo Labels for Semi-Supervised Object Detection | code | — | Compare |
| COCO 0.5% labeled data (5 rows) | Unbiased Teacher v2 | Unbiased Teacher v2: Semi-supervised Object Detection for... | code | — | Compare |
| COCO (1 row) | Sparse Semi-DETR | Sparse Semi-DETR: Sparse Learnable Queries for Semi-Supervised... | — | — | Compare |
Syntology column: samples harvested from the paper's repositories and executed on synthesized fixtures; “ran” is not a correctness claim and does not order the table. Each line reads “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. When the archive marks a repository official for the row's paper, the line starts with that repository's state (“official” is 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. A dash means no Syntology record for that paper, not a recorded non-run. Each “ran” line links to that paper's sample list. Syntology's record for this page last changed ; when this build read Syntology's graph is in the build record. For agents: get_harvested_code_for_paper(arxiv_id) lists each paper's samples; how to connect.
Libraries
Not in the archive: the export carries no per-task library table, so there is nothing to show at snapshot 2025-07-28.
Datasets archive 2025-07-28
1 dataset whose archive record lists this task, ordered by the archive's paper count.
Subtasks archive 2025-07-28
No subtask under this task in the archive's task tree.
Parent tasks archive 2025-07-28
Papers archive 2025-07-28
archive papers tagged: 115 · with a code link: 51 · where Syntology ran a sample: 10 (10 with a run with no instrument failure, 0 where every run was a failure of Syntology's instrument) Syntology
Show: all tagged papersonly where code ran (10 of 115 tagged: 10 with a run with no instrument failure, 0 where every run was a failure of Syntology's instrument)
Page 1 of 2: papers 1 to 100 of 115, in archive order: by repositories listed in the archive (most first), then newest first, not by stars (the archive holds no stars, so PwC's “Social” and “Latest” sorts cannot be reproduced). Papers that list no repository come after every paper that lists one.
Papers without a page here are shown as plain text. A Syntology line reads “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 figure “where Syntology's instrument failed” counts failures of Syntology's instrument, not of the code. 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); hover it for the repositories the samples that ran came from. The first sentence of the abstract is shown for the first 30 papers; every abstract is on its paper's page.
-
16 Jun 2021 8 repositories listedThis paper presents an end-to-end semi-supervised object detection approach, in contrast to previous more complex multi-stage methods.
-
10 May 2020 7 repositories listed Syntology 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)Semi-supervised learning (SSL) has a potential to improve the predictive performance of machine learning models using unlabeled data.
-
15 Feb 2023 4 repositories listed Syntology 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)The Pseudo Label Assigner prevents the occurrence of bias caused by a large number of low-quality pseudo labels that may interfere with the Dense Detector during the student-teacher mutual learning mechanism, and the…
-
18 Feb 2021 4 repositories listedTo address this, we introduce Unbiased Teacher, a simple yet effective approach that jointly trains a student and a gradually progressing teacher in a mutually-beneficial manner.
-
16 Jul 2023 3 repositories listedSpecifically, we propose a Stage-wise Hybrid Matching strategy that combines the one-to-many assignment and one-to-one assignment strategies to improve the training efficiency of the first stage and thus provide…
-
14 Jun 2022 3 repositories listedTo remedy this issue, we present a novel label assignment mechanism for self-training framework, namely proposal self-assignment, which injects the proposals from student into teacher and generates accurate pseudo…
-
6 Jul 2022 2 repositories listed Syntology official (archive's flag): 2 ran · 2 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; 0 where Syntology's instrument failed) · 1 unverified (of 3 harvested samples)To date, the most powerful semi-supervised object detectors (SS-OD) are based on pseudo-boxes, which need a sequence of post-processing with fine-tuned hyper-parameters.
-
1 Dec 2019 2 repositories listedMaking a precise annotation in a large dataset is crucial to the performance of object detection.
-
28 Dec 2024 1 repository listedRecent years have witnessed tremendous advances on modern visual recognition systems.
-
8 Jul 2024 1 repository listedWe experimentally find three gaps between general and oriented object detection in semi-supervised learning: 1) Sampling inconsistency: the common center sampling is not suitable for oriented objects with larger aspect…
-
1 Jul 2024 1 repository listedSpecifically, we observe that objects from aerial images are usually arbitrary orientations, small scales, and aggregation, which inspires the following core designs: a Simple Instance-aware Dense Sampling (SIDS)…
-
31 May 2024 1 repository listedTo address these two issues, we have constructed a multi-class 3D LiDAR dataset reflecting diverse urban environments and object characteristics, and developed a robust 3D semi-supervised object detection (SSOD) based…
-
22 Mar 2024 1 repository listedTo tackle the confirmation bias from incorrect pseudo labels of minority classes, the class-rebalancing sampling module resamples unlabeled data following the guidance of the gradient-based reweighting module.
-
12 Dec 2023 1 repository listedWhile the pseudo-label method has demonstrated considerable success in semi-supervised object detection tasks, this paper uncovers notable limitations within this approach.
-
5 Dec 2023 1 repository listed Syntology official (archive's flag): 5 ran · 5 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; 4 where Syntology's instrument failed) · 3 unverified (of 8 harvested samples) · 8 pointer-only (licence)Semi-supervised object detection is crucial for 3D scene understanding, efficiently addressing the limitation of acquiring large-scale 3D bounding box annotations.
-
29 Nov 2023 1 repository listed Syntology official (archive's flag): 4 ran · 4 ran (of which 0 constructed an object rather than computing a result; 4 with no instrument failure: 0 honoured, 0 violated, 4 with no contract checked; 0 where Syntology's instrument failed) · 0 unverified (of 4 harvested samples)On 1Mpx, RVT-S with 10% labels even surpasses its fully-supervised counterpart using 100% labels.
-
21 Nov 2023 1 repository listedTherefore, we propose Density-Guided Dense Pseudo Label Selection (DDPLS) for semi-supervised oriented object detection.
-
30 Oct 2023 1 repository listedFor specialized and dense downstream tasks such as object detection, labeling data requires expertise and can be very expensive, making few-shot and semi-supervised models much more attractive alternatives.
-
26 Oct 2023 1 repository listed Syntology official (archive's flag): 2 ran · 2 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; 0 where Syntology's instrument failed) · 0 unverified (of 2 harvested samples)Federated Learning (FL) has emerged as a potent framework for training models across distributed data sources while maintaining data privacy.
-
9 Oct 2023 1 repository listedSemi-supervised object detection (SSOD) methods tackle this issue by generating pseudo-labels for the unlabeled data, assuming that all classes found in the unlabeled dataset are also represented in the labeled data.
-
14 Sep 2023 1 repository listedIn this work, we propose ALWOD, a new framework that addresses this problem by fusing active learning (AL) with weakly and semi-supervised object detection paradigms.
-
9 Aug 2023 1 repository listedOne of the important bottlenecks in training modern object detectors is the need for labeled images where bounding box annotations have to be produced for each object present in the image.
-
10 Apr 2023 1 repository listedSemi-Supervised Object Detection (SSOD), aiming to explore unlabeled data for boosting object detectors, has become an active task in recent years.
-
4 Apr 2023 1 repository listed Syntology official (archive's flag): 4 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) · 2 unverified (of 6 harvested samples)State-of-the-art 3D object detectors are usually trained on large-scale datasets with high-quality 3D annotations.
-
27 Mar 2023 1 repository listedIt employs a "divide-and-conquer" strategy and separately exploits positives for the classification and localization task, which is more robust to the assignment ambiguity.
-
16 Mar 2023 1 repository listedDespite the remarkable progress made by modern detection models, this challenge is particularly evident in the semi-supervised case.
-
15 Mar 2023 1 repository listedIn this paper, we study teacher-student learning from the perspective of data initialization and propose a novel algorithm called Active Teacher(Source code are available at…
-
22 Feb 2023 1 repository listedIn addition to this challenge, we also reveal two key issues in one-stage SSOD, which are low-quality pseudo-labeling and multi-task optimization conflict, respectively.
-
19 Dec 2022 1 repository listedIn this work, we propose an object-level point augmentor (OPA) that performs local transformations for semi-supervised 3D object detection.
-
7 Dec 2022 1 repository listedIn this work, we introduce our method Adaptive Self-Training for Object Detection (ASTOD), which is a simple yet effective teacher-student method.
-
1 Oct 2022 1 repository listed
-
Consistent-Teacher: Towards Reducing Inconsistent Pseudo-targets in Semi-supervised Object Detection4 Sep 2022 1 repository listed
-
18 Jul 2022 1 repository listed
-
17 Jul 2022 1 repository listed
-
12 Jul 2022 1 repository listed
-
7 Jul 2022 1 repository listed
-
21 Jun 2022 1 repository listed
-
19 Jun 2022 1 repository listed
-
12 May 2022 1 repository listed
-
15 Apr 2022 1 repository listed
-
30 Mar 2022 1 repository listed
-
30 Mar 2022 1 repository listed
-
29 Mar 2022 1 repository listed Syntology official (archive's flag): 2 ran · 2 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; 0 where Syntology's instrument failed) · 0 unverified (of 2 harvested samples)
-
17 Mar 2022 1 repository listed Syntology official (archive's flag): 3 ran · 3 ran (of which 0 constructed an object rather than computing a result; 1 with no instrument failure: 1 honoured, 0 violated, 0 with no contract checked; 2 where Syntology's instrument failed) · 0 unverified (of 3 harvested samples)
-
26 Jan 2022 1 repository listed
-
1 Jan 2022 1 repository listed
-
22 Nov 2021 1 repository listed
-
8 Jun 2021 1 repository listed Syntology official (archive's flag): 5 ran · 5 ran (of which 0 constructed an object rather than computing a result; 2 with no instrument failure: 0 honoured, 1 violated, 1 with no contract checked; 3 where Syntology's instrument failed) · 2 unverified (of 7 harvested samples) · 1 pointer-only (licence)
-
15 Apr 2021 1 repository listed Syntology 0 ran · 2 unverified (of 2 harvested samples) · 2 pointer-only (licence)
-
21 Mar 2021 1 repository listed
-
13 Jul 2020 1 repository listed
-
Building Blocks for Robust and Effective Semi-Supervised Real-World Object Detection24 Mar 2025 0 repositories listed
-
ClipGrader: Leveraging Vision-Language Models for Robust Label Quality Assessment in Object Detection3 Mar 2025 0 repositories listed
-
Semi-Supervised Weed Detection in Vegetable Fields: In-domain and Cross-domain Experiments24 Feb 2025 0 repositories listed
-
Co-Learning: Towards Semi-Supervised Object Detection with Road-side Cameras28 Nov 2024 0 repositories listed
-
Collaborative Feature-Logits Contrastive Learning for Open-Set Semi-Supervised Object Detection20 Nov 2024 0 repositories listed
-
Applying the Lower-Biased Teacher Model in Semi-Supervised Object Detection29 Sep 2024 0 repositories listed
-
Semi-Supervised 3D Object Detection with Channel Augmentation using Transformation Equivariance10 Sep 2024 0 repositories listed
-
Class-balanced Open-set Semi-supervised Object Detection for Medical Images22 Aug 2024 0 repositories listed
-
Semi-Supervised Object Detection: A Survey on Progress from CNN to Transformer11 Jul 2024 0 repositories listed
-
Collaboration of Teachers for Semi-supervised Object Detection22 May 2024 0 repositories listed
-
IMWA: Iterative Model Weight Averaging Benefits Class-Imbalanced Learning Tasks25 Apr 2024 0 repositories listed
-
2 Apr 2024 0 repositories listed
-
Boosting Semi-Supervised Object Detection in Remote Sensing Images With Active Teaching29 Feb 2024 0 repositories listed
-
SeMoLi: What Moves Together Belongs Together29 Feb 2024 0 repositories listed
-
Detection of Thermal Events by Semi-Supervised Learning for Tokamak First Wall Safety19 Jan 2024 0 repositories listed
-
A-Teacher: Asymmetric Network for 3D Semi-Supervised Object Detection1 Jan 2024 0 repositories listed
-
Credible Teacher for Semi-Supervised Object Detection in Open Scene1 Jan 2024 0 repositories listed
-
Multiview Aerial Visual Recognition (MAVREC): Can Multi-view Improve Aerial Visual Perception?7 Dec 2023 0 repositories listed
-
Weakly-semi-supervised object detection in remotely sensed imagery29 Nov 2023 0 repositories listed
-
Rethinking Scale Imbalance in Semi-supervised Object Detection for Aerial Images23 Oct 2023 0 repositories listed
-
Generalized Open-World Semi-Supervised Object Detection28 Jul 2023 0 repositories listed
-
Aligned Unsupervised Pretraining of Object Detectors with Self-training28 Jul 2023 0 repositories listed
-
Training-based Model Refinement and Representation Disagreement for Semi-Supervised Object Detection25 Jul 2023 0 repositories listed
-
Low-Confidence Samples Mining for Semi-supervised Object Detection28 Jun 2023 0 repositories listed
-
Pseudo-Labeling Enhanced by Privileged Information and Its Application to In Situ Sequencing Images28 Jun 2023 0 repositories listed
-
Semi-supervised Object Detection: A Survey on Recent Research and Progress25 Jun 2023 0 repositories listed
-
A Semi-supervised Object Detection Algorithm for Underwater Imagery7 Jun 2023 0 repositories listed
-
4 Jun 2023 0 repositories listed
-
Online Open-set Semi-supervised Object Detection with Dual Competing Head23 May 2023 0 repositories listed
-
Semi-Supervised Object Detection for Sorghum Panicles in UAV Imagery16 May 2023 0 repositories listed
-
MOST: Multiple Object localization with Self-supervised Transformers for object discovery11 Apr 2023 0 repositories listed
-
Pseudo-label Correction and Learning For Semi-Supervised Object Detection6 Mar 2023 0 repositories listed
-
6 Dec 2022 0 repositories listed
-
Semi-supervised object detection based on single-stage detector for thighbone fracture localization20 Oct 2022 0 repositories listed
-
Dual-Curriculum Teacher for Domain-Inconsistent Object Detection in Autonomous Driving17 Oct 2022 0 repositories listed
-
Open-Set Semi-Supervised Object Detection29 Aug 2022 0 repositories listed
-
Cycle Self-Training for Semi-Supervised Object Detection with Distribution Consistency Reweighting12 Jul 2022 0 repositories listed
-
Point-Teaching: Weakly Semi-Supervised Object Detection with Point Annotations1 Jun 2022 0 repositories listed
-
Penalizing Proposals using Classifiers for Semi-Supervised Object Detection26 May 2022 0 repositories listed
-
Lesion Localization in OCT by Semi-Supervised Object Detection24 Apr 2022 0 repositories listed
-
S4OD: Semi-Supervised learning for Single-Stage Object Detection9 Apr 2022 0 repositories listed
-
Scale-Equivalent Distillation for Semi-Supervised Object Detection23 Mar 2022 0 repositories listed
-
PseudoProp: Robust Pseudo-Label Generation for Semi-Supervised Object Detection in Autonomous Driving Systems11 Mar 2022 0 repositories listed
-
SparseDet: Improving Sparsely Annotated Object Detection with Pseudo-positive Mining12 Jan 2022 0 repositories listed
-
Semi-Supervised Object Detection via Multi-Instance Alignment With Global Class Prototypes1 Jan 2022 0 repositories listed
-
Semi-supervised Object Detection via Virtual Category Learning25 Nov 2021 0 repositories listed
-
CrossMatch: Improving Semi-Supervised Object Detection via Multi-Scale Consistency29 Sep 2021 0 repositories listed
-
11 Jul 2021 0 repositories listed
-
21 Jun 2021 0 repositories listed
Syntology lines on 11 of the papers shown; no Syntology record for the others (a paper without an arXiv id cannot be joined to the graph, and absence from the graph layer is not a recorded non-run). “Ran” means the sample executed on a synthesized fixture, not that the paper's result was reproduced; each line links to that paper's sample list. Syntology's record for this page last changed ; when this build read Syntology's graph is in the build record. For agents: get_harvested_code_for_paper(arxiv_id) lists each paper's samples; how to connect.
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