Browse State-of-the-Art › Open World Object Detection
Open World Object Detection
30 papers with code · 7 benchmarks · 6 datasets archive 2025-07-28
Open World Object Detection is a computer vision problem 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.
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.
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
6 datasets 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: 50 · with a code link: 30 · where Syntology ran a sample: 8 (8 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 (8 of 50 tagged: 8 with a run with no instrument failure, 0 where every run was a failure of Syntology's instrument)
Page 1 of 1: papers 1 to 50 of 50, 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.
-
15 Aug 2021 6 repositories listed Syntology community repositories only · 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) · 2 unverified (of 4 harvested samples)In this paper, we identify that the problem is that the binary classifiers in existing proposal methods tend to overfit to the training categories.
-
25 Jun 2023 2 repositories listedWe argue that this contextual information should already be embedded within the known classes.
-
2 Dec 2021 2 repositories listedIn the case of incremental object detection, OW-DETR outperforms the state-of-the-art for all settings on PASCAL VOC.
-
3 Mar 2021 2 repositories listed Syntology official: not harvested · 0 ran · 2 unverified (of 2 harvested samples)Humans have a natural instinct to identify unknown object instances in their environments.
-
1 Jan 2025 1 repository listedTo achieve this, we start with a standard OVD detector and adapt it for OWOD tasks.
-
30 Dec 2024 1 repository listedIn this work, we introduce Universal Open-World Object Detection (Uni-OWD), a new paradigm that unifies open-vocabulary and open-world object detection tasks.
-
27 Nov 2024 1 repository listedTo address theses limitations, we propose a framework that enables OVD models to operate in open world settings, by identifying and incrementally learning novel objects.
-
26 Nov 2024 1 repository listedMoreover, we propose a vision-centric 3D open-world object detection baseline and further introduce an ensemble method by fusing general and specialized models to address the issue of lower precision in existing…
-
21 Nov 2024 1 repository listedDINO-X employs the same Transformer-based encoder-decoder architecture as Grounding DINO 1.
-
15 Oct 2024 1 repository listedExploring new knowledge is a fundamental human ability that can be mirrored in the development of deep neural networks, especially in the field of object detection.
-
8 Oct 2024 1 repository listedTo mitigate the inaccurate region classification in OVD, we propose a new Shape-Invariant Adapter named SIA-OVD to bridge the image-region gap in the OVD task.
-
8 Apr 2024 1 repository listedObject detection is critical in autonomous driving, and it is more practical yet challenging to localize objects of unknown categories: an endeavour known as Class-Agnostic Object Detection (CAOD).
-
19 Mar 2024 1 repository listedThis paper explores the potential of Large Language Models(LLMs) in zero-shot anomaly detection for safe visual navigation.
-
25 Feb 2024 1 repository listed Syntology official (archive's flag): 2 ran · 2 ran (of which 1 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) · 4 pointer-only (licence)We demonstrate the effectiveness of our SS-OWOD problem setting and approach for remote sensing object detection, proposing carefully curated splits and baseline performance evaluations.
-
1 Jan 2024 1 repository listedTo address this problem we exploit three levels of orthogonality in the detection process: First the objectness and classification heads are disentangled by operating on separate sets of features that are orthogonal to…
-
14 Dec 2023 1 repository listedAblation experiments demonstrate that both of them are effective in mitigating the impact of open-world knowledge distillation on the learning of known objects.
-
4 Nov 2023 1 repository listedThis is because the predictor is inevitably biased to the known categories, and fails under the shift in the appearance of the unseen categories.
-
2 Nov 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) · 6 unverified (of 11 harvested samples) · 11 pointer-only (licence)Building on the success of powerful image-level vision-language (ViL) foundation models like CLIP, recent efforts have sought to harness their capabilities by either training a contrastive model from scratch with an…
-
31 Aug 2023 1 repository listed Syntology official (archive's flag): 3 ran · 3 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; 1 where Syntology's instrument failed) · 0 unverified (of 3 harvested samples) · 3 pointer-only (licence)Open-World Object Detection (OWOD) extends object detection problem to a realistic and dynamic scenario, where a detection model is required to be capable of detecting both known and unknown objects and incrementally…
-
17 Jul 2023 1 repository listed Syntology official (archive's flag): 13 ran · 13 ran (of which 0 constructed an object rather than computing a result; 7 with no instrument failure: 4 honoured, 2 violated, 1 with no contract checked; 6 where Syntology's instrument failed) · 3 unverified (of 16 harvested samples) · 16 pointer-only (licence)First, as the randomization is independent of the distribution of the limited known objects, the random proposals become the instrumental variable that prevents the training from being confounded by the known objects.
-
24 Mar 2023 1 repository listed Syntology official (archive's flag): 4 ran · 4 ran (of which 0 constructed an object rather than computing a result; 2 with no instrument failure: 1 honoured, 0 violated, 1 with no contract checked; 2 where Syntology's instrument failed) · 0 unverified (of 4 harvested samples)The recently proposed open-world object and open-set detection have achieved a breakthrough in finding never-seen-before objects and distinguishing them from known ones.
-
21 Mar 2023 1 repository listed Syntology 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) · 1 unverified (of 3 harvested samples) · 1 pointer-only (licence)In this paper, we formally address universal object detection, which aims to detect every scene and predict every category.
-
21 Mar 2023 1 repository listedWe propose leveraging the VL as the ``Brain'' of the open-world detector by simply generating unknown labels.
-
1 Jan 2023 1 repository listedTo the best of our knowledge, this is the first OWOD work without manual unknown selection.
-
22 Dec 2022 1 repository listedWe address the task of open-world class-agnostic object detection, i. e., detecting every object in an image by learning from a limited number of base object classes.
-
2 Dec 2022 1 repository listedThe resulting Probabilistic Objectness transformer-based open-world detector, PROB, integrates our framework into traditional object detection models, adapting them for the open-world setting.
-
23 Jul 2022 1 repository listedIn this work, we propose a novel OWOD problem called Unknown-Classified Open World Object Detection (UC-OWOD).
-
12 May 2022 1 repository listedIn this work, we propose an open-vocabulary object detection method that, based on image-caption pairs, learns to detect novel object classes along with a given set of known classes.
-
3 Jan 2022 1 repository listed Syntology official (archive's flag): 4 ran · 4 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; 2 where Syntology's instrument failed) · 0 unverified (of 4 harvested samples)Open World Object Detection (OWOD), simulating the real dynamic world where knowledge grows continuously, attempts to detect both known and unknown classes and incrementally learn the identified unknown ones.
-
22 Nov 2021 1 repository listedThis has been a long-standing question in computer vision.
-
Decoupled PROB: Decoupled Query Initialization Tasks and Objectness-Class Learning for Open World Object Detection17 Jul 2025 0 repositories listed
-
SAM2Auto: Auto Annotation Using FLASH9 Jun 2025 0 repositories listed
-
VL-SAM-V2: Open-World Object Detection with General and Specific Query Fusion25 May 2025 0 repositories listed
-
Detecting Open World Objects via Partial Attribute Assignment1 Jan 2025 0 repositories listed
-
Open-World Objectness Modeling Unifies Novel Object Detection1 Jan 2025 0 repositories listed
-
UADet: A Remarkably Simple Yet Effective Uncertainty-Aware Open-Set Object Detection Framework12 Dec 2024 0 repositories listed
-
OW-Rep: Open World Object Detection with Instance Representation Learning24 Sep 2024 0 repositories listed
-
Finding Dino: A plug-and-play framework for unsupervised detection of out-of-distribution objects using prototypes11 Apr 2024 0 repositories listed
-
YOLOOC: YOLO-based Open-Class Incremental Object Detection with Novel Class Discovery30 Mar 2024 0 repositories listed
-
BSDP: Brain-inspired Streaming Dual-level Perturbations for Online Open World Object Detection5 Mar 2024 0 repositories listed
-
Open World Object Detection in the Era of Foundation Models10 Dec 2023 0 repositories listed
-
USD: Unknown Sensitive Detector Empowered by Decoupled Objectness and Segment Anything Model4 Jun 2023 0 repositories listed
-
Addressing the Challenges of Open-World Object Detection27 Mar 2023 0 repositories listed
-
Open-World Object Detection via Discriminative Class Prototype Learning23 Feb 2023 0 repositories listed
-
CAT: LoCalization and IdentificAtion Cascade Detection Transformer for Open-World Object Detection5 Jan 2023 0 repositories listed
-
Open World DETR: Transformer based Open World Object Detection6 Dec 2022 0 repositories listed
-
DetCLIP: Dictionary-Enriched Visual-Concept Paralleled Pre-training for Open-world Detection20 Sep 2022 0 repositories listed
-
Rectifying Open-set Object Detection: A Taxonomy, Practical Applications, and Proper Evaluation20 Jul 2022 0 repositories listed
-
Contrastive Object Detection Using Knowledge Graph Embeddings21 Dec 2021 0 repositories listed
-
Objects in Semantic Topology6 Oct 2021 0 repositories listed
Syntology lines on 9 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