Papers › YOLOv9: Learning What You Want to Learn Using Programmable Gradient Information
YOLOv9: Learning What You Want to Learn Using Programmable Gradient Information
Chien-Yao Wang, I-Hau Yeh, Hong-Yuan Mark Liao
Today's deep learning methods focus on how to design the most appropriate objective functions so that the prediction results of the model can be closest to the ground truth. Meanwhile, an appropriate architecture that can facilitate acquisition of enough information for prediction has to be designed. Existing methods ignore a fact that when input data undergoes layer-by-layer feature extraction and spatial transformation, large amount of information will be lost. This paper will delve into the important issues of data loss when data is transmitted through deep networks, namely information bottleneck and reversible functions. We proposed the concept of programmable gradient information (PGI) to cope with the various changes required by deep networks to achieve multiple objectives. PGI can provide complete input information for the target task to calculate objective function, so that reliable gradient information can be obtained to update network weights. In addition, a new lightweight network architecture -- Generalized Efficient Layer Aggregation Network (GELAN), based on gradient path planning is designed. GELAN's architecture confirms that PGI has gained superior results on lightweight models. We verified the proposed GELAN and PGI on MS COCO dataset based object detection. The results show that GELAN only uses conventional convolution operators to achieve better parameter utilization than the state-of-the-art methods developed based on depth-wise convolution. PGI can be used for variety of models from lightweight to large. It can be used to obtain complete information, so that train-from-scratch models can achieve better results than state-of-the-art models pre-trained using large datasets, the comparison results are shown in Figure 1. The source codes are at: https://github.com/WongKinYiu/yolov9.
In Syntology View this paper on Syntology, its page in Syntology's graph. That page adds which of its functions are also present in other papers' code Syntology holds, with dates, and its dated run record as JSON and a README badge. It also lists the repositories linked to the paper, the abstract and the calls for agents.
Open this paper in Syntology's Atlas, the map of the papers in Syntology's graph and their citations.
For agents, on Syntology's MCP service (how to connect):
get_harvested_code_for_paper(arxiv_id="2402.13616")get_code(code_sha256="…")with a sample'scode_sha256from the list belowget_citation_path(paper_1="2402.13616", paper_2="…")with another paper's arXiv id or titleget_concepts_for_paper(arxiv_id="2402.13616")
Code
Syntology 32 code samples harvested from 5 repositories linked to this paper: 25 ran (of which 9 constructed an object rather than computing a result; 21 with no instrument failure: 4 honoured, 2 violated, 15 with no contract checked; 4 where Syntology's instrument failed) · 7 unverified. Where Syntology's instrument failed: 3 where our contract draft was wrong; 1 where the contract check could not run; failures of Syntology's instrument, not of the code.
By repository: official repository: 9 samples from 1 repository, 7 ran (4 with no instrument failure; 3 where Syntology's instrument failed); named in the paper: 11 samples from 2 repositories, 8 ran (8 with no instrument failure; 0 where Syntology's instrument failed); community (archive-listed): 12 samples from 2 repositories, 10 ran (9 with no instrument failure; 1 where Syntology's instrument failed). The run record, sample by sample. “Ran” means executed on a synthesized input, not that the code is correct or reproduces the paper.
Levels written between 2026-09-22 and 2026-09-25 (UTC): the dates Syntology's graph wrote each sample's verification level, not when the code executed.
Repository list and official/mentioned flags are the archive's, frozen 2025-07-28. Reachability, where shown, is from one Syntology probe window (2026-09-16 to 2026-09-18); repositories not probed show nothing. GitHub stars are not tracked.
Code Syntology ran Syntology
32 samples harvested: 25 ran (of which 9 constructed an object rather than computing a result; 21 with no instrument failure: 4 honoured, 2 violated, 15 with no contract checked; 4 where Syntology's instrument failed) · 7 unverified. “Where Syntology's instrument failed” counts failures of Syntology's instrument, not of the code. Syntology's record for this page last changed ; when this build read Syntology's graph is in the build record. That date is not when the samples ran.
Licence: 11 of the 32 samples are pointer only, meaning Syntology does not serve that copy's text. This page shows no code text for any sample; each one links to its file in the repository.
Harvested from 5 repositories linked to this paper, official or community; the list below is grouped by repository, each group headed by its name and what it is to the paper. “Ran” means the sample executed on a synthesized input. It does not mean the output is correct, and nothing here reproduces the paper's results. A line beginning “fixture:” under a sample that ran gives the arguments Syntology's fixture called the sample with, each as name:type/rank/element kind (? where none was recorded), and the type of what the fixture's run returned, exactly as the harness recorded them; the arguments and the returned type were recorded by two separate runs of the same fixture. No output value is shown, and a returned type says nothing about whether the output was right. “Level recorded” gives the UTC date when Syntology's graph wrote the sample's verification level, not when the code executed; where the level was written before Syntology's graph kept that date, the row says “level recorded, date not recorded”. For 8 samples that ran, the graph records a signature this page does not show: for a class the fixture built without calling, the harness called the object with inputs it made up itself, so the recorded signature is the harness's probe, not the fixture's arguments. “Honoured” and “violated” refer to a contract Syntology drafted from the code itself. “Our draft was wrong” and “the contract check could not run” are failures of Syntology's instrument, not of the code: the sample ran on Syntology's synthesized input, and then the drafted contract did not describe it, or the check itself raised an error (RAISES), lacked a dependency (DEP_MISSING) or ran out of time (TIMEOUT); hover the label for which. A metamorphic tier, where shown, is evidence of the output's shape, not that the sample implements the method.
Each sample ends with its code_sha256. A sample's code_sha256 is Syntology's identity for that exact code. It is printed in full (16 hexadecimal characters for every sample in this build), and get_code(code_sha256="…") takes it exactly as printed. An agent calls it on Syntology's MCP service (how to connect); click an identity to copy that call.
Repository labels, per sample. official repository: The archive marks this repository official for the paper. named in the paper: The archive records that the paper mentions this repository; it is not marked official. community (archive-listed): In the archive's code links for this paper, not marked official and not recorded as mentioned in the paper. found in paper text by Syntology: Syntology found this repository in the paper's own text; whether it is the authors' implementation is not asserted. community: Not in the archive's code links for this paper; a community repository Syntology harvested. Samples are grouped by repository: a repository marked official first, then by how directly the repository is tied to the paper, then in the archive's order; never by how many ran. Licence labels name the repository's licence as recorded at harvest. “Pointer only” means Syntology does not serve that copy's text, for one of six reasons: no licence file was found; the licence was not identified; the licence is recorded as permissive but that copy's record is not marked cleared; the licence is outside the permissive list Syntology serves text under (MIT, Apache-2.0, BSD and similar); this paper's copy was not located, so its licence is not recorded; or this paper's copy is cleared, but the stored copy of the same code that Syntology serves is not. Some licences outside that list permit redistribution, such as WTFPL, and GPL-3.0 under its conditions; they are simply not on the list. Hover a licence label for the reason. File links open the file on GitHub at the default branch, which may have changed since the harvest.
A function or class name links to its page when the name occurs in the harvested code of at least 5 papers; the name is a string, not an identity. A census tag appears when Syntology's census ran implementations with that name on one shared input per bucket: it gives how many were compared, from how many papers, and how many distinct outputs they produced, and names this sample's bucket when this sample was one of them.
acb86aa8696bb043 · report
fixture: signature kernel_size:tuple/1/int, dilation:tuple/1/int · returned tuple · level recorded 2026-09-24 c9cb18bff87ea33b · report
fixture: signature bbox1:Tensor/2/float, bbox2:Tensor/2/float, metrics:str/0/str · returned Tensor · level recorded 2026-09-24 8e61071af5c8f65a · report
fixture: signature image_size:list/1/int, strides:list/1/int · returned tuple · level recorded 2026-09-24 census: 4 implementations from 6 papers, 1 distinct output on one shared input yolo/utils/model_utils.py ran MIT (permissive) ·
38e55f346fdfc802 · report
fixture: signature start:float/0/float, end:float/0/float, step:float/0/float, total:int/0/int · returned float · level recorded 2026-09-24 b332cb7d65ce68f1 · report
fixture: signature data:dict/0/?, id_to_idx:dict/0/? · returned dict · level recorded 2026-09-24 8e1ad17d8526e395 · report
fixture: signature x:int/0/int, div:int/0/int · returned int · level recorded 2026-09-24 f718ace509af682f · report
fixture: signature bbox:Tensor/2/float, indicator:str/0/str · returned Tensor · level recorded 2026-09-24 5eb213554929874f · report
86db6b7ab1646a7c · report
fixture: signature k:int/0/int, p:NoneType/0/?, d:int/0/int · returned int · level recorded 2026-09-22 386a04c4b6c96c88 · report
fixture: signature eps:float/0/float · returned tuple · level recorded 2026-09-25 6fab24a4d78a99ac · report
7707093cd2ca2b68 · report
fixture: returned Bottleneck · level recorded 2026-09-22 955083ecf0b31e55 · report
fixture: returned C3 · level recorded 2026-09-22 census: 8 implementations from 8 papers, 8 distinct outputs across 2 buckets, one shared input per bucket ultralytics/nn/modules/block.py ran · metamorphic tier: deterministic fingerprinted AGPL-3.0 (copyleft) · pointer only ·
af6c4f0d1c425989 · report
fixture: returned Conv · level recorded 2026-09-22 7385e2e3d2a2af23 · report
fixture: returned RepBottleneck · level recorded 2026-09-22 a36954bb2b2d92af · report
fixture: returned RepConv · level recorded 2026-09-22 11ea59c9308130b2 · report
fixture: signature k:int/0/int, p:NoneType/0/?, d:int/0/int · returned int · level recorded 2026-09-22 66c4746608dc55b1 · report
c8d57d5b7650e553 · report
dea6d7ba4c8c882f · report
fixture: returned Bottleneck · level recorded 2026-09-22 census: 8 implementations from 8 papers, 8 distinct outputs across 2 buckets, one shared input per bucket yolo/model/module.py ran fingerprinted MIT (permissive) ·
f12c179ff392638b · report
fixture: returned Conv · level recorded 2026-09-22 859cd8d4d3b28b71 · report
fixture: returned DConv · level recorded 2026-09-22 5ddf9e8137680cff · report
fixture: returned RepConv · level recorded 2026-09-22 7115585ff5427d1d · report
fixture: signature x:Tensor/4/float · returned Tensor · level recorded 2026-09-24 00279341e44c9e1a · report
fixture: signature kernel_size:tuple/1/int, dilation:tuple/1/int · returned tuple · level recorded 2026-09-22 d0374cf3dbdab1f6 · report
fixture: signature activation:str/0/str · returned ReLU · level recorded 2026-09-22 b8d4eb0708db9812 · report
fixture: signature image:ndarray/3/int, box:ndarray/1/float, color:tuple/1/int, thickness:int/0/int · returned ndarray · level recorded 2026-09-24 c9dab4a605d6462a · report
fixture: signature image:ndarray/3/int, boxes:ndarray/2/float, scores:ndarray/1/float, class_ids:ndarray/1/int, mask_alpha:float/0/float · returned ndarray · level recorded 2026-09-24 8bd590382607dfcb · report
fixture: signature image:ndarray/3/int, text:str/0/str, box:ndarray/1/float, color:tuple/1/int, font_size:float/0/float, text_thickness:int/0/int · returned ndarray · level recorded 2026-09-25 Method as code Syntology
What Syntology's graph records as this paper's claimed method, lifted into code: each assembly names its bricks (functions and classes), each with its own role and its own verification level. An assembly is not a check that the code implements the method correctly or reproduces the paper's results. Levels are each brick's own verification level in Syntology's graph (level 0: no recorded run), listed brick by brick and never combined into one level; “ran” means the brick executed on a synthesized input, not that its output is correct, and the instrument figure counts failures of Syntology's instrument, not of the code. Where a model read the code against the paper's claim, each assembly's label verdict is one model's judgement, kept in this page's JSON twin; it is not calibrated, so no card prints it. Siblings are assemblies lifted from this paper in the same batch for the same method: alternative readings kept side by side; none replaces or supersedes another.
2 assemblies on this paper: 2 harvested, 0 generated, listed in 1 groups (siblings lifted in one batch form one group).
2 sibling assemblies for Generalized Efficient Layer Aggregation Network (GELAN) (harvested), lifted in the same batch on 2026-09-09: alternative readings kept side by side; none replaces or supersedes another.
harvested Assembly for Generalized Efficient Layer Aggregation Network (GELAN) (graph method: Generalized Efficient Layer Aggregation Network (GELAN)). 8 bricks; individually on a fixture: 6 ran (of which 5 constructed an object rather than computing a result; 6 with no instrument failure: 1 honoured, 0 violated, 5 with no contract checked; 0 where Syntology's instrument failed) · 2 unverified. The assembly has not been run end-to-end.
one of 2 siblings
- RepNCSPELAN4 entry · level 0 · unverified ·
c8d57d5b7650e553 - Conv model · level 1 · ran ·
af6c4f0d1c425989 - RepCSP helper · level 0 · unverified ·
66c4746608dc55b1 - autopad helper · level 1 · ran · honoured contract ·
11ea59c9308130b2 - C3 helper · level 1 · ran ·
955083ecf0b31e55 - RepBottleneck helper · level 1 · ran ·
7385e2e3d2a2af23 - Bottleneck helper · level 1 · ran ·
7707093cd2ca2b68 - RepConv model · level 1 · ran ·
a36954bb2b2d92af
harvested Assembly for Generalized Efficient Layer Aggregation Network (GELAN) (graph method: Generalized Efficient Layer Aggregation Network (GELAN)). 9 bricks; individually on a fixture: 7 ran (of which 4 constructed an object rather than computing a result; 6 with no instrument failure: 0 honoured, 1 violated, 5 with no contract checked; 1 where Syntology's instrument failed) · 2 unverified. The assembly has not been run end-to-end.
one of 2 siblings
- RepNCSPELAND entry · level 0 · unverified ·
5f145be1974d90b9 - DConv model · level 1 · ran ·
859cd8d4d3b28b71 - RepNCSPELAN helper · level 0 · unverified ·
2ae37bf73015412d - Conv helper · level 1 · ran ·
f12c179ff392638b - RepNCSP model · level 1 · ran ·
7115585ff5427d1d - auto_pad helper · level 1 · ran · violated contract ·
00279341e44c9e1a - create_activation_function helper · level 1 · ran · our draft was wrong ·
d0374cf3dbdab1f6 - Bottleneck helper · level 1 · ran ·
dea6d7ba4c8c882f - RepConv helper · level 1 · ran ·
5ddf9e8137680cff
Each brick ends with its code_sha256, Syntology's identity for that exact code; click one to copy the get_code call that returns it. For agents, on Syntology's MCP service: assembly(arxiv_id="2402.13616") returns these assemblies with each brick's role and wiring (how to connect).
Tasks
Results from the paper archive 2025-07-28
Ranks are positions in the archive's leaderboards as they stood at the 2025-07-28 snapshot. Results published since then are not among these rows, so a rank here is not a current standing.
Methods
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