Methods › Computer Vision › One-Stage Object Detection Models › YOLOX
YOLOX
archive 2025-07-28 Description, source and code snippet are the archive's method entry.
YOLOX is a single-stage object detector that makes several modifications to YOLOv3 with a DarkNet53 backbone. Specifically, YOLO’s head is replaced with a decoupled one. For each level of FPN feature, we first adopt a 1 × 1 conv layer to reduce the feature channel to 256 and then add two parallel branches with two 3 × 3 conv layers each for classification and regression tasks respectively.
Additional changes include adding Mosaic and MixUp into the augmentation strategies to boost YOLOX’s performance. The anchor mechanism is also removed so YOLOX is anchor-free. Lastly, SimOTA for label assignment -- where label assignment is formulated as an optimal transport problem via a top-k strategy.
In Syntology harvested code stored, below machine verification (unverified_code; harvested), served level V1; retrieve with get_harvested_code_for_paper(arxiv_id='2107.08430'). Repositories: 42 listed of 42 in the graph, strongest link: official. The lookup matched a paper by its title, arXiv:2107.08430, not a method entry. The archive credits no paper with an arXiv id for this method, so whether this answer (about arXiv:2107.08430) is about this method is not checked.
Origin paper of this answer, arXiv:2107.08430 (its page on this site · its page on Syntology): Syntology's run record for its harvested code, 16 ran (of which 0 constructed an object rather than computing a result; 14 with no instrument failure: 0 honoured, 0 violated, 14 with no contract checked; 2 where Syntology's instrument failed) · 7 unverified (of 23 harvested samples). The instrument figure counts failures of Syntology's instrument, not of the code. Ran means executed on a synthesized input, not that the code is correct.
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.
What each level means, quoted from Syntology's server card: V0 “imports”; V1 “executes against a synthesized fixture and returns a value of the recorded type”; V2 “two implementations GENERATED from the paper's signature and spec agree numerically (1e-6) on fixture inputs” “neither of the two ever read the authors' own code, so V2 measures how unambiguously the paper specifies the method, not fidelity to the authors' implementation (measured 2026-09-11, commit 75eaa77: cross_checked_by is a second LLM on 2,628 of 2,831 served samples)”; V3 “paper-derived property tests pass on both of those same two generations.” The card adds: “No rung on this ladder compares the served code against the authors' implementation, so treat every level as evidence about runnability and internal agreement, not about matching the paper's results.” A level quoted in two parts is one definition the card writes as two clauses joined by a double hyphen, each clause quoted on its own (how these levels are quoted).
Papers archive 2025-07-28
archive papers tagged: 33 · with a code link: 21 · where Syntology ran a sample: 5 (4 with a run with no instrument failure, 1 where every run was a failure of Syntology's instrument) Syntology
Show: all tagged papersonly where code ran (5 of 33 tagged: 4 with a run with no instrument failure, 1 where every run was a failure of Syntology's instrument)
Page 1 of 1: papers 1 to 33 of 33, 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.
-
WalnutData: A UAV Remote Sensing Dataset of Green Walnuts and Model Evaluation 27 Feb 2025 · 1 repository · arXiv:2502.20092
-
Enhancing Transparent Object Pose Estimation: A Fusion of GDR-Net and Edge Detection 17 Feb 2025 · 0 repositories · arXiv:2502.12027
-
Beyond Boxes: Mask-Guided Spatio-Temporal Feature Aggregation for Video Object Detection 6 Dec 2024 · 0 repositories · arXiv:2412.04915
-
MapVision: CVPR 2024 Autonomous Grand Challenge Mapless Driving Tech Report 14 Jun 2024 · 0 repositories · arXiv:2406.10125
-
Real-time object detection and tracking using flash LiDAR imagery 7 Jun 2024 · 0 repositories
-
Replication Study and Benchmarking of Real-Time Object Detection Models 11 May 2024 · 1 repository · arXiv:2405.06911
-
Efficient and Concise Explanations for Object Detection with Gaussian-Class Activation Mapping Explainer 20 Apr 2024 · 1 repository · arXiv:2404.13417
-
FlightScope: An Experimental Comparative Review of Aircraft Detection Algorithms in Satellite Imagery 3 Apr 2024 · 1 repository · arXiv:2404.02877
-
Knowledge Distillation in YOLOX-ViT for Side-Scan Sonar Object Detection 14 Mar 2024 · 1 repository · arXiv:2403.09313
-
FusionVision: A comprehensive approach of 3D object reconstruction and segmentation from RGB-D cameras using YOLO and fast segment anything 29 Feb 2024 · 1 repository · arXiv:2403.00175
-
Detection of Micromobility Vehicles in Urban Traffic Videos 28 Feb 2024 · 1 repository · arXiv:2402.18503
-
Beyond Kalman Filters: Deep Learning-Based Filters for Improved Object Tracking 15 Feb 2024 · 1 repository · arXiv:2402.09865
-
MuraNet: Multi-task Floor Plan Recognition with Relation Attention 1 Sep 2023 · 0 repositories · arXiv:2309.00348
-
Object Detection for Caries or Pit and Fissure Sealing Requirement in Children's First Permanent Molars 31 Aug 2023 · 0 repositories · arXiv:2308.16551
-
G-CAME: Gaussian-Class Activation Mapping Explainer for Object Detectors 6 Jun 2023 · 1 repository · arXiv:2306.03400
-
Towards Better Explanations for Object Detection 5 Jun 2023 · 1 repository · arXiv:2306.02744
-
Long Range Object-Level Monocular Depth Estimation for UAVs 17 Feb 2023 · 0 repositories · arXiv:2302.08943
-
Research on road object detection algorithm based on improved YOLOX 16 Feb 2023 · 0 repositories · arXiv:2302.08156
-
CholecTriplet2022: Show me a tool and tell me the triplet -- an endoscopic vision challenge for surgical action triplet detection 13 Feb 2023 · 2 repositories · arXiv:2302.06294
-
Towards Edge-Cloud Architectures for Personal Protective Equipment Detection 4 Jan 2023 · 0 repositories · arXiv:2301.01501
-
Comparison Of Deep Object Detectors On A New Vulnerable Pedestrian Dataset 12 Dec 2022 · 2 repositories · arXiv:2212.06218
-
Multiple Object Tracking Challenge Technical Report for Team MT_IoT 7 Dec 2022 · 1 repository · arXiv:2212.03586
-
The 1st-place Solution for ECCV 2022 Multiple People Tracking in Group Dance Challenge 27 Oct 2022 · 3 repositories · arXiv:2210.15281
-
PredNAS: A Universal and Sample Efficient Neural Architecture Search Framework 26 Oct 2022 · 0 repositories · arXiv:2210.14460
-
Centralized Feature Pyramid for Object Detection 5 Oct 2022 · 1 repository · arXiv:2210.02093Syntology 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) · 1 unverified (of 2 harvested samples)
-
FasterX: Real-Time Object Detection Based on Edge GPUs for UAV Applications 7 Sep 2022 · 0 repositories · arXiv:2209.03157
-
YOLOX-PAI: An Improved YOLOX, Stronger and Faster than YOLOv6 27 Aug 2022 · 3 repositories · arXiv:2208.13040
-
YOLOv7: Trainable bag-of-freebies sets new state-of-the-art for real-time object detectors 6 Jul 2022 · 21 repositories · arXiv:2207.02696Syntology community repositories only · 10 ran (of which 0 constructed an object rather than computing a result; 8 with no instrument failure: 2 honoured, 0 violated, 6 with no contract checked; 2 where Syntology's instrument failed) · 1 unverified (of 11 harvested samples) · 5 pointer-only (licence)
-
PP-YOLOE: An evolved version of YOLO 30 Mar 2022 · 8 repositories · arXiv:2203.16250Syntology official (archive's flag): 2 ran · 22 ran (of which 0 constructed an object rather than computing a result; 19 with no instrument failure: 2 honoured, 0 violated, 17 with no contract checked; 3 where Syntology's instrument failed) · 5 unverified (of 27 harvested samples) · 1 pointer-only (licence)
-
Evaluation of YOLO Models with Sliced Inference for Small Object Detection 9 Mar 2022 · 0 repositories · arXiv:2203.04799
-
Workshop on Autonomous Driving at CVPR 2021: Technical Report for Streaming Perception Challenge 27 Jul 2021 · 1 repository · arXiv:2108.04230Syntology official (archive's flag): 2 ran · 2 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; 1 where Syntology's instrument failed) · 2 unverified (of 4 harvested samples)
-
YOLOX: Exceeding YOLO Series in 2021 18 Jul 2021 · 42 repositories · arXiv:2107.08430Syntology community repositories only · 16 ran (of which 0 constructed an object rather than computing a result; 14 with no instrument failure: 0 honoured, 0 violated, 14 with no contract checked; 2 where Syntology's instrument failed) · 7 unverified (of 23 harvested samples)
-
USB: Universal-Scale Object Detection Benchmark 25 Mar 2021 · 1 repository · arXiv:2103.14027
Tasks archive 2025-07-28
20 shown of 52 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