Papers › Cross-Domain Weakly-Supervised Object Detection through Progressive Domain Adaptation

Cross-Domain Weakly-Supervised Object Detection through Progressive Domain Adaptation

30 Mar 2018CVPR 2018 6arXiv:1803.11365archive 2025-07-28

Naoto Inoue, Ryosuke Furuta, Toshihiko Yamasaki, Kiyoharu Aizawa

Can we detect common objects in a variety of image domains without instance-level annotations? In this paper, we present a framework for a novel task, cross-domain weakly supervised object detection, which addresses this question. For this paper, we have access to images with instance-level annotations in a source domain (e.g., natural image) and images with image-level annotations in a target domain (e.g., watercolor). In addition, the classes to be detected in the target domain are all or a subset of those in the source domain. Starting from a fully supervised object detector, which is pre-trained on the source domain, we propose a two-step progressive domain adaptation technique by fine-tuning the detector on two types of artificially and automatically generated samples. We test our methods on our newly collected datasets containing three image domains, and achieve an improvement of approximately 5 to 20 percentage points in terms of mean average precision (mAP) compared to the best-performing baselines.

PaperPDFConference PDFCodeCode Syntology ran

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):

Code

The archive's official repository (naoto0804/cross-domain-detection) was not harvested; the 11 samples below come from 2 community repositories.

Syntology 11 code samples harvested from 2 repositories linked to this paper: 8 ran (of which 0 constructed an object rather than computing a result; 6 with no instrument failure: 0 honoured, 0 violated, 6 with no contract checked; 2 where Syntology's instrument failed) · 3 unverified. Where Syntology's instrument failed: 2 where our contract draft was wrong; failures of Syntology's instrument, not of the code.

By repository: community (archive-listed): 11 samples from 2 repositories, 8 ran (6 with no instrument failure; 2 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 2026-09-26 (UTC): the dates Syntology's graph wrote each sample's verification level, not when the code executed.

naoto0804/cross-domain-detection officialSyntology: not harvested report
barisbatuhan/dass_det_inference mentioned on GitHubpytorchApache-2.0Syntology: 9 samples, 6 ran (2 instrument-failed) · 3 unverified report
barisbatuhan/dass_detector mentioned on GitHubpytorchApache-2.0Syntology: 2 samples, 2 ran (0 instrument-failed) · 0 unverified report

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

11 samples harvested: 8 ran (of which 0 constructed an object rather than computing a result; 6 with no instrument failure: 0 honoured, 0 violated, 6 with no contract checked; 2 where Syntology's instrument failed) · 3 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.

2ran · our draft was wrong
6ran
3unverified

Licence: 1 of the 11 samples is pointer only, meaning Syntology does not serve that copy's text. For that sample, this paper's copy is under a permissive licence and cleared, but the stored copy of the same code that Syntology serves is not; the licence label's tooltip gives Syntology's recorded reason. This page shows no code text for any sample; each one links to its file in the repository.

Harvested from 2 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”. “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.

barisbatuhan/dass_det_inference community (archive-listed) 9 samples, 6 ran (2 instrument-failed) · 3 unverified
check_center_boxa_in_boxb dass_det/utils/boxes.py ran Apache-2.0 (permissive) · fa151da186910445 · report fixture: signature box_a:Tensor/2/float, box_b:Tensor/2/float, cxcy_format:bool/0/bool · returned Tensor · level recorded 2026-09-26
filter_box dass_det/utils/boxes.py ran Apache-2.0 (permissive) · 4a3604aadeec303e · report fixture: signature output:Tensor/2/float, scale_range:tuple/1/float · returned Tensor · level recorded 2026-09-26
fuse_conv_and_bn in 6 papers dass_det/utils/model_utils.py ran Apache-2.0 (permissive) · d3111a0ae5602114 · report fixture: signature conv:callable/0/?, bn:callable/0/? · returned Conv2d · level recorded 2026-09-24
get_activation in 218 papers dass_det/models/network_blocks.py ran · our draft was wrong Apache-2.0 (permissive) · 6e3d5f4c3ce305d7 · report fixture: signature name:str/0/str, inplace:bool/0/bool · returned SiLU · level recorded 2026-09-26
intersect in 33 papers dass_det/utils/boxes.py ran · our draft was wrong fingerprinted Apache-2.0 (permissive) here; the stored copy is pointer only · f01c5f73515770a5 · report fixture: signature box_a:Tensor/2/float, box_b:Tensor/2/float · returned Tensor · level recorded 2026-09-22
load_ckpt in 31 papers dass_det/utils/checkpoint.py ran Apache-2.0 (permissive) · 8851ffb179a522ed · report fixture: signature model:callable/0/?, ckpt:dict/0/? · returned SimpleModel · level recorded 2026-09-26
fuse_model dass_det/utils/model_utils.py unverified Apache-2.0 (permissive) · bce7fbf2f1717430 · report
get_total_and_free_memory_in_Mb dass_det/utils/metric.py unverified Apache-2.0 (permissive) · 8211e0d6dc4df44f · report
is_parallel in 15 papers dass_det/utils/ema.py unverified Apache-2.0 (permissive) · bbbb5d6a28074b9d · report
barisbatuhan/dass_detector community (archive-listed) 2 samples, 2 ran (0 instrument-failed) · 0 unverified
get_faces_and_bodies_in_frame datasets/dcm_panels_creator.py ran Apache-2.0 (permissive) · 4ee3fb89cd920516 · report fixture: signature frame:tuple/1/int, faces:list/1/list, bodies:list/1/list, margin:float/0/float · returned tuple · level recorded 2026-09-26
load_annotations in 11 papers datasets/dcm_panels_creator.py ran Apache-2.0 (permissive) · 7b6ebc447d32adc5 · report fixture: signature dcm_path:str/0/str, group:list/1/str · returned dict · level recorded 2026-09-26

Tasks

Domain AdaptationObject DetectionWeakly Supervised Object Detectionobject-detection

Datasets

Introduced by this paper, per the archive.

Clipart1kComic2kWatercolor2k

Results from the paper archive 2025-07-28

TaskDatasetModelMetricValueRank at snapshotLeaderboardReport
Weakly Supervised Object Detection Clipart1k DT+PL MAP 46.0 #5 of 7 Archive leaderboard report
Weakly Supervised Object Detection Comic2k DT+PL (+extra) MAP 42.2 #5 of 8 Archive leaderboard report
Weakly Supervised Object Detection Comic2k DT+PL MAP 37.2 #6 of 8 Archive leaderboard report
Weakly Supervised Object Detection Watercolor2k DT+PL (+extra) MAP 59.1 #5 of 12 Archive leaderboard report
Weakly Supervised Object Detection Watercolor2k DT+PL MAP 54.3 #9 of 12 Archive leaderboard report

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.

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