Papers › Towards Open World Object Detection

Towards Open World Object Detection

3 Mar 2021CVPR 2021 1arXiv:2103.02603archive 2025-07-28

K J Joseph, Salman Khan, Fahad Shahbaz Khan, Vineeth N Balasubramanian

Humans have a natural instinct to identify unknown object instances in their environments. The intrinsic curiosity about these unknown instances aids in learning about them, when the corresponding knowledge is eventually available. This motivates us to propose a novel computer vision problem called: `Open World Object Detection', where a model is tasked to: 1) identify objects that have not been introduced to it as `unknown', without explicit supervision to do so, and 2) incrementally learn these identified unknown categories without forgetting previously learned classes, when the corresponding labels are progressively received. We formulate the problem, introduce a strong evaluation protocol and provide a novel solution, which we call ORE: Open World Object Detector, based on contrastive clustering and energy based unknown identification. Our experimental evaluation and ablation studies analyze the efficacy of ORE in achieving Open World objectives. As an interesting by-product, we find that identifying and characterizing unknown instances helps to reduce confusion in an incremental object detection setting, where we achieve state-of-the-art performance, with no extra methodological effort. We hope that our work will attract further research into this newly identified, yet crucial research direction.

PaperPDFConference PDFCodeCode Syntology ranMethod as code

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 (JosephKJ/OWOD) was not harvested; the 2 samples below come from 1 community repository.

Syntology 2 code samples harvested from 1 repository linked to this paper: 0 ran · 2 unverified.

By repository: community (archive-listed): 2 samples from 1 repository, 0 ran (0 with no instrument failure; 0 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.

JosephKJ/OWOD officialmentioned in papermentioned on GitHubpytorchSyntology: not harvested report
josephkj/eli mentioned on GitHubpytorchSyntology: 2 samples, 0 ran · 2 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

2 samples harvested: 0 ran · 2 unverified. Syntology's record for this page has not changed since , the first build that kept a record date for it; when this build read Syntology's graph is in the build record. That date is not when the samples ran.

2unverified

Licence: 0 of the 2 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 josephkj/eli. “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. “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.

josephkj/eli community (archive-listed) 2 samples, 0 ran · 2 unverified
EBMAligner detection/detectron2/modeling/ebm_aligner.py unverified MIT (permissive) · 0a2d0fce109fe7fa · report
FeatureDataset detection/detectron2/modeling/ebm_aligner.py unverified MIT (permissive) · ea41a66b69d6075b · report

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.

1 assembly on this paper: 1 harvested, 0 generated.

harvested Assembly for ORE: Open World Object Detector (graph method: ORE: Open World Object Detector). 3 bricks; individually on a fixture: 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) · 2 unverified. The assembly has not been run end-to-end.

  1. EBMAligner entry · level 0 · unverified · 0a2d0fce109fe7fa
  2. EBM model · level 1 · ran · 1cb1eede30824641
  3. FeatureDataset helper · level 0 · unverified · ea41a66b69d6075b

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="2103.02603") returns these assemblies with each brick's role and wiring (how to connect).

Tasks

ClusteringObjectOpen World Object Detectionobject-detection

Results from the paper archive 2025-07-28

TaskDatasetModelMetricValueRank at snapshotLeaderboardReport
Open World Object Detection COCO 2017 (Electronic, Indoor, Kitchen, Furniture) ORE MAP 26.66 #2 of 2 Archive leaderboard report
Open World Object Detection COCO 2017 (Outdoor, Accessories, Appliance, Truck) ORE A-OSE 7772 #2 of 2 Archive leaderboard report
Open World Object Detection COCO 2017 (Outdoor, Accessories, Appliance, Truck) ORE MAP 38.98 #2 of 2 Archive leaderboard report
Open World Object Detection COCO 2017 (Outdoor, Accessories, Appliance, Truck) ORE Unknown Recall 11.32 #2 of 2 Archive leaderboard report
Open World Object Detection COCO 2017 (Outdoor, Accessories, Appliance, Truck) ORE WI 0.0154 #2 of 2 Archive leaderboard report
Open World Object Detection COCO 2017 (Sports, Food) ORE A-OSE 6634 #2 of 2 Archive leaderboard report
Open World Object Detection COCO 2017 (Sports, Food) ORE MAP 29.32 #2 of 2 Archive leaderboard report
Open World Object Detection COCO 2017 (Sports, Food) ORE Unknown Recall 14.79 #2 of 2 Archive leaderboard report
Open World Object Detection COCO 2017 (Sports, Food) ORE WI 0.0081 #2 of 2 Archive leaderboard report
Open World Object Detection PASCAL VOC 2007 ORE A-OSE 8234 #2 of 2 Archive leaderboard report
Open World Object Detection PASCAL VOC 2007 ORE MAP 56.34 #2 of 2 Archive leaderboard report
Open World Object Detection PASCAL VOC 2007 ORE Unknown Recall 14.40 #2 of 2 Archive leaderboard report
Open World Object Detection PASCAL VOC 2007 ORE WI 0.02193 #2 of 2 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