Browse State-of-the-Art › Novel Object Detection
Novel Object Detection
24 papers with code · 1 benchmark · 1 dataset archive 2025-07-28
Novel Object Detection is a challenging task introduced by Fomenko et.al. in their paper "Learning to Discover and Detect Objects". The goal in this task is to measure mAP performance on known as well as novel classes, where the known classes correspond to the 80 COCO classes, and the novel classes are the remaining 1123 classes from LVIS dataset. Thus, during training the model can only be trained with annotations from COCO dataset, but during evaluation/inference it is expected to BOTH classify and detect objects belonging to ALL the classes in the LVIS dataset.
Description from the archive archive 2025-07-28.
Benchmarks archive 2025-07-28
1 leaderboard table shown for this task, 1 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.
| Dataset | Best model (first row in archive order) | Paper | Code | Syntology | Compare |
|---|---|---|---|---|---|
| LVIS v1.0 val (5 rows) | Cooperative Foundational Models | Enhancing Novel Object Detection via Cooperative Foundational Models | code | — | Compare |
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
1 dataset 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: 53 · with a code link: 24 · where Syntology ran a sample: 4 (4 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 (4 of 53 tagged: 4 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 53 of 53, 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.
-
9 Jun 2024 2 repositories listedOur contributions are as follows: 1) We propose that the ODMamba backbone introduce a State Space Model (SSM) with linear complexity to address the quadratic complexity of self-attention.
-
12 Jun 2020 2 repositories listedDeploying deep learning models on embedded systems has been challenging due to limited computing resources.
-
29 Nov 2018 2 repositories listed Syntology 3 ran (of which 0 constructed an object rather than computing a result; 3 with no instrument failure: 0 honoured, 0 violated, 3 with no contract checked; 0 where Syntology's instrument failed) · 0 unverified (of 3 harvested samples)This paper proposes a novel object detection framework named Grid R-CNN, which adopts a grid guided localization mechanism for accurate object detection.
-
5 Jul 2024 1 repository listedMeanwhile, the Advanced Assisted Fusion (AAF) module deeply embedded within the neck conveys a more diverse range of gradient information to the output layer.
-
14 Mar 2024 1 repository listedIn this paper we present YOLOX-ViT, a novel object detection model, and investigate the efficacy of knowledge distillation for model size reduction without sacrificing performance.
-
15 Jan 2024 1 repository listedHowever, the class-level prototypes are difficult to precisely generate, and they also lack detailed information, leading to instability in performance.
-
19 Nov 2023 1 repository listedWe present a novel approach to transform existing closed-set detectors into open-set detectors.
-
3 Oct 2023 1 repository listedMFAD excels in both simple and complex anomaly detection scenarios.
-
2 Oct 2023 1 repository listedWe refer to this approach as the self-training strategy, which enhances recall and accuracy for novel classes without requiring extra annotations, datasets, and re-training.
-
17 Sep 2023 1 repository listedThe ability to detect objects in all lighting (i. e., normal-, over-, and under-exposed) conditions is crucial for real-world applications, such as self-driving.
-
24 Jun 2023 1 repository listed Syntology 4 ran (of which 0 constructed an object rather than computing a result; 3 with no instrument failure: 0 honoured, 0 violated, 3 with no contract checked; 1 where Syntology's instrument failed) · 0 unverified (of 4 harvested samples) · 4 pointer-only (licence)In fact, our experiments show that GLIP, the state-of-the-art vision-language model for object detection, often disregards contextual information in the language descriptions and instead relies heavily on detecting…
-
19 Oct 2022 1 repository listed Syntology official: harvested, nothing ran · 0 ran · 1 unverified (of 1 harvested sample)We then train our network to learn to classify each RoI, either as one of the known classes, seen in the source dataset, or one of the novel classes, with a long-tail distribution constraint on the class assignments…
-
11 Jul 2022 1 repository listedA critical object detection task is finetuning an existing model to detect novel objects, but the standard workflow requires bounding box annotations which are time-consuming and expensive to collect.
-
24 Oct 2021 1 repository listedDue to the success of Bidirectional Encoder Representations from Transformers (BERT) in natural language process (NLP), the multi-head attention transformer has been more and more prevalent in computer-vision researches…
-
19 Aug 2021 1 repository listed Syntology 4 ran (of which 4 constructed an object rather than computing a result; 4 with no instrument failure: 0 honoured, 0 violated, 4 with no contract checked; 0 where Syntology's instrument failed) · 0 unverified; every one of the 4 samples that ran constructed an object rather than computing a result (of 4 harvested samples)In this paper, we study the problem of Novel Class Discovery (NCD).
-
26 Jul 2021 1 repository listedAccess to high resolution satellite imagery has dramatically increased in recent years as several new constellations have entered service.
-
15 May 2021 1 repository listedThe model achieves a (COCO-style) average precision of 0.
-
1 Mar 2021 1 repository listedThus, we develop a new framework of few-shot object detection with universal prototypes (FSOD^{up}) that owns the merit of feature generalization towards novel objects.
-
6 Feb 2021 1 repository listedHere, we introduce a novel open-world semi-supervised learning setting that formalizes the notion that novel classes may appear in the unlabeled test data.
-
4 Mar 2020 1 repository listedWe have taken an incremental approach in reaching our final proposed method through detailed evaluation and comparison with baselines using our constructed SVSO (Street View Signboard Objects) signboard dataset…
-
27 May 2019 1 repository listedIn this work, we propose to exploit the natural correlation in narrations and the visual presence of objects in video, to learn an object detector and retrieval without any manual labeling involved.
-
3 Mar 2019 1 repository listedThis paper presents a novel object detection network (CAD-Net) that exploits attention-modulated features as well as global and local contexts to address the new challenges in detecting objects from remote sensing…
-
14 Mar 2017 1 repository listedWe present a novel object detection pipeline for localization and recognition in three dimensional environments.
-
9 Apr 2016 1 repository listed Syntology official (archive's flag): 1 ran · 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) · 0 unverified (of 1 harvested sample)Temporal and contextual information of videos are not fully investigated and utilized.
-
MambaNeXt-YOLO: A Hybrid State Space Model for Real-time Object Detection4 Jun 2025 0 repositories listedReal-time object detection is a fundamental but challenging task in computer vision, particularly when computational resources are limited.
-
Language-guided Learning for Object Detection Tackling Multiple Variations in Aerial Images29 May 2025 0 repositories listedDespite recent advancements in computer vision research, object detection in aerial images still suffers from several challenges.
-
MASF-YOLO: An Improved YOLOv11 Network for Small Object Detection on Drone View25 Apr 2025 0 repositories listedWith the rapid advancement of Unmanned Aerial Vehicle (UAV) and computer vision technologies, object detection from UAV perspectives has emerged as a prominent research area.
-
An object detection approach for lane change and overtake detection from motion profiles6 Feb 2025 0 repositories listedIn the application domain of fleet management and driver monitoring, it is very challenging to obtain relevant driving events and activities from dashcam footage while minimizing the amount of information stored and…
-
Open-World Objectness Modeling Unifies Novel Object Detection1 Jan 2025 0 repositories listedThe challenge in open-world object detection, similarly to few- and zero-shot learning, is to generalize beyond the class distribution of the training data.
-
WoodYOLO: A Novel Object Detector for Wood Species Detection in Microscopic Images18 Nov 2024 0 repositories listedWood species identification plays a crucial role in various industries, from ensuring the legality of timber products to advancing ecological conservation efforts.
-
FA-YOLO: Research On Efficient Feature Selection YOLO Improved Algorithm Based On FMDS and AGMF Modules29 Aug 2024 0 repositories listed
-
EMDFNet: Efficient Multi-scale and Diverse Feature Network for Traffic Sign Detection26 Aug 2024 0 repositories listed
-
Meta-tuning Loss Functions and Data Augmentation for Few-shot Object Detection24 Apr 2023 0 repositories listed
-
PlantDet: A benchmark for Plant Detection in the Three-Rivers-Source Region11 Apr 2023 0 repositories listed
-
PV-RCNN++: Semantical Point-Voxel Feature Interaction for 3D Object Detection29 Aug 2022 0 repositories listed
-
LiDAR Cluster First and Camera Inference Later: A New Perspective Towards Autonomous Driving18 Nov 2021 0 repositories listed
-
Visual Understanding of Complex Table Structures from Document Images13 Nov 2021 0 repositories listed
-
Partially-Supervised Novel Object Captioning Leveraging Context from Paired Data10 Sep 2021 0 repositories listed
-
Oriented Bounding Boxes for Small and Freely Rotated Objects24 Apr 2021 0 repositories listed
-
Unsupervised Discovery of the Long-Tail in Instance Segmentation Using Hierarchical Self-Supervision2 Apr 2021 0 repositories listed
-
2 Mar 2021 0 repositories listed
-
Knowledge Guided Learning: Towards Open Domain Egocentric Action Recognition with Zero Supervision16 Sep 2020 0 repositories listed
-
Any-Shot Object Detection16 Mar 2020 0 repositories listed
-
Multi-Task Self-Supervised Object Detection via Recycling of Bounding Box Annotations1 Jun 2019 0 repositories listed
-
ORSIm Detector: A Novel Object Detection Framework in Optical Remote Sensing Imagery Using Spatial-Frequency Channel Features23 Jan 2019 0 repositories listed
-
Deep Regionlets: Blended Representation and Deep Learning for Generic Object Detection28 Nov 2018 0 repositories listed
-
Object Detection based Deep Unsupervised Hashing24 Nov 2018 0 repositories listed
-
Deep Watershed Detector for Music Object Recognition26 May 2018 0 repositories listed
-
Deep Regionlets for Object Detection6 Dec 2017 0 repositories listed
-
CAD Priors for Accurate and Flexible Instance Reconstruction8 May 2017 0 repositories listed
-
Dictionary Pair Classifier Driven Convolutional Neural Networks for Object Detection1 Jun 2016 0 repositories listed
-
Small Instance Detection by Integer Programming on Object Density Maps1 Jun 2015 0 repositories listed
-
Accurate Object Detection with Joint Classification-Regression Random Forests1 Jun 2014 0 repositories listed
Syntology lines on 5 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