Browse State-of-the-Art › Object Proposal Generation
Object Proposal Generation
21 papers with code · 2 benchmarks · 3 datasets archive 2025-07-28
Object proposal generation is a preprocessing technique that has been widely used in current object detection pipelines to guide the search of objects and avoid exhaustive sliding window search across images.
( Image credit: Multiscale Combinatorial Grouping for Image Segmentation and Object Proposal Generation )
Description from the archive archive 2025-07-28.
Benchmarks archive 2025-07-28
2 leaderboard tables shown for this task, 2 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 |
|---|---|---|---|---|---|
| PASCAL VOC 2012, 60 proposals per image (3 rows) | MDef-DETR | Class-agnostic Object Detection with Multi-modal Transformer | code | — | Compare |
| COCO (Common Objects in Context) (1 row) | MDef-DETR (Off-the-shelf evaluation) | Class-agnostic Object Detection with Multi-modal Transformer | 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
3 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: 54 · with a code link: 21 · where Syntology ran a sample: 4 (3 with a run with no instrument failure, 1 where every run was a failure of Syntology's instrument) Syntology
Show: all tagged papersonly where code ran (4 of 54 tagged: 3 with a run with no instrument failure, 1 where every run was a failure of Syntology's instrument)
Page 1 of 1: papers 1 to 54 of 54, 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.
-
11 Dec 2018 13 repositories listed Syntology official (archive's flag): 2 ran · 7 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; 5 where Syntology's instrument failed) · 2 unverified (of 9 harvested samples) · 4 pointer-only (licence)In this paper, we propose PointRCNN for 3D object detection from raw point cloud.
-
27 May 2017 11 repositories listed Syntology 3 ran (of which 0 constructed an object rather than computing a result; 1 with no instrument failure: 0 honoured, 1 violated, 0 with no contract checked; 2 where Syntology's instrument failed) · 4 unverified (of 7 harvested samples) · 4 pointer-only (licence)To this end, we propose a novel end-to-end deep semantic edge learning architecture based on ResNet and a new skip-layer architecture where category-wise edge activations at the top convolution layer share and are fused…
-
23 Nov 2016 3 repositories listed Syntology 0 ran · 3 unverified (of 3 harvested samples) · 3 pointer-only (licence)We encode the sparse 3D point cloud with a compact multi-view representation.
-
22 Dec 2017 2 repositories listedWe introduce a differentiable, end-to-end trainable framework for solving pixel-level grouping problems such as instance segmentation consisting of two novel components.
-
28 May 2024 1 repository listed Syntology official (archive's flag): 7 ran · 7 ran (of which 0 constructed an object rather than computing a result; 5 with no instrument failure: 2 honoured, 0 violated, 3 with no contract checked; 2 where Syntology's instrument failed) · 0 unverified (of 7 harvested samples)Furthermore, the weight adapter optimizes weights to enhance the distinctiveness of instance embeddings during similarity computation.
-
1 Sep 2023 1 repository listedObject proposal generation serves as a standard pre-processing step in Vision-Language (VL) tasks (image captioning, visual question answering, etc.).
-
21 Jun 2023 1 repository listedIn this paper, we propose a speed-up alternative method for this fundamental task with comparable performance.
-
11 May 2023 1 repository listedOn the other hand, unknown objects, which have not been seen in training sample set, are one of the reasons that hinder autonomous vehicles from driving beyond the operational domain.
-
29 Sep 2022 1 repository listed Syntology official (archive's flag): 2 ran · 2 ran (of which 0 constructed an object rather than computing a result; 0 with no instrument failure: 0 honoured, 0 violated, 0 with no contract checked; 2 where Syntology's instrument failed) · 1 unverified (of 3 harvested samples) · 3 pointer-only (licence)Our voting-based tracklet generation method followed by geometric feature-based aggregation generates significantly improved panoptic LiDAR segmentation quality when compared to modeling the entire 4D volume using…
-
22 Nov 2021 1 repository listedThis has been a long-standing question in computer vision.
-
12 Jan 2021 1 repository listedPrecise segmentation of objects is an important problem in tasks like class-agnostic object proposal generation or instance segmentation.
-
21 Dec 2020 1 repository listedIn this paper, we propose Pointformer, a Transformer backbone designed for 3D point clouds to learn features effectively.
-
1 Dec 2020 1 repository listedIn this paper, we propose a unified WSOD framework, termed UWSOD, to develop a high-capacity general detection model with only image-level labels, which is self-contained and does not require external modules or…
-
21 Nov 2018 1 repository listedWe propose a novel approach for class-agnostic object proposal generation, which is efficient and especially well-suited to detect small objects.
-
9 Apr 2018 1 repository listedSemantic edge detection (SED), which aims at jointly extracting edges as well as their category information, has far-reaching applications in domains such as semantic segmentation, object proposal generation, and object…
-
12 Apr 2017 1 repository listedIn application domains such as robotics, it is useful to represent the uncertainty related to the robot's belief about the state of its environment.
-
30 Mar 2017 1 repository listedWe propose a new method for semantic instance segmentation, by first computing how likely two pixels are to belong to the same object, and then by grouping similar pixels together.
-
18 Apr 2016 1 repository listedMoreover, on general image retrieval datasets, SCDA achieves comparable retrieval results with state-of-the-art general image retrieval approaches.
-
Video object detection is challenging because objects that are easily detected in one frame may be difficult to detect in another frame within the same clip.
-
28 Apr 2015 1 repository listedWith the combination of CNN features and boosting forest, CCF benefits from the richer capacity in feature representation compared with channel features, as well as lower cost in computation and storage compared with…
-
3 Mar 2015 1 repository listedWe propose a unified approach for bottom-up hierarchical image segmentation and object proposal generation for recognition, called Multiscale Combinatorial Grouping (MCG).
-
Small, but important: Traffic light proposals for detecting small traffic lights and beyond27 Jul 2023 0 repositories listedTraffic light detection is a challenging problem in the context of self-driving cars and driver assistance systems.
-
Segmenting Medical Instruments in Minimally Invasive Surgeries using AttentionMask21 Mar 2022 0 repositories listedPrecisely locating and segmenting medical instruments in images of minimally invasive surgeries, medical instrument segmentation, is an essential first step for several tasks in medical image processing.
-
Localizing Small Apples in Complex Apple Orchard Environments23 Feb 2022 0 repositories listedThe localization of fruits is an essential first step in automated agricultural pipelines for yield estimation or fruit picking.
-
ProposalCLIP: Unsupervised Open-Category Object Proposal Generation via Exploiting CLIP Cues18 Jan 2022 0 repositories listedObject proposal generation is an important and fundamental task in computer vision.
-
DeepFH Segmentations for Superpixel-based Object Proposal Refinement7 Aug 2021 0 repositories listedClass-agnostic object proposal generation is an important first step in many object detection pipelines.
-
3DVG-Transformer: Relation Modeling for Visual Grounding on Point Clouds1 Jan 2021 0 repositories listedVisual grounding on 3D point clouds is an emerging vision and language task that benefits various applications in understanding the 3D visual world.
-
You Don't Only Look Once: Constructing Spatial-Temporal Memory for Integrated 3D Object Detection and Tracking1 Jan 2021 0 repositories listedHumans are able to continuously detect and track surrounding objects by constructing a spatial-temporal memory of the objects when looking around.
-
Improving Point Cloud Semantic Segmentation by Learning 3D Object Detection22 Sep 2020 0 repositories listedPoint cloud semantic segmentation plays an essential role in autonomous driving, providing vital information about drivable surfaces and nearby objects that can aid higher level tasks such as path planning and collision…
-
What leads to generalization of object proposals?13 Aug 2020 0 repositories listedObject proposal generation is often the first step in many detection models.
-
Real-time 3D object proposal generation and classification under limited processing resources24 Mar 2020 0 repositories listed
-
Relation Graph Network for 3D Object Detection in Point Clouds30 Nov 2019 0 repositories listed
-
Deep Learning for Generic Object Detection: A Survey6 Sep 2018 0 repositories listed
-
A New Target-specific Object Proposal Generation Method for Visual Tracking27 Mar 2018 0 repositories listed
-
Object cosegmentation using deep Siamese network7 Mar 2018 0 repositories listed
-
Deep Crisp Boundaries: From Boundaries to Higher-level Tasks8 Jan 2018 0 repositories listed
-
SalProp: Salient object proposals via aggregated edge cues14 Jun 2017 0 repositories listed
-
Object Discovery via Cohesion Measurement28 Apr 2017 0 repositories listed
-
ScaleNet: Guiding Object Proposal Generation in Supermarkets and Beyond22 Apr 2017 0 repositories listed
-
Boundary-aware Instance Segmentation9 Dec 2016 0 repositories listed
-
4 Dec 2016 0 repositories listed
-
Multi-stage Object Detection with Group Recursive Learning18 Aug 2016 0 repositories listed
-
1 Jun 2016 0 repositories listed
-
Multi-Scale Patch Aggregation (MPA) for Simultaneous Detection and Segmentation1 Jun 2016 0 repositories listed
-
Generating Discriminative Object Proposals via Submodular Ranking11 Feb 2016 0 repositories listed
-
Learning to Combine Mid-Level Cues for Object Proposal Generation1 Dec 2015 0 repositories listed
-
SubmodBoxes: Near-Optimal Search for a Set of Diverse Object Proposals1 Dec 2015 0 repositories listed
-
Sequential Optimization for Efficient High-Quality Object Proposal Generation14 Nov 2015 0 repositories listed
-
Manipulated Object Proposal: A Discriminative Object Extraction and Feature Fusion Framework for First-Person Daily Activity Recognition2 Sep 2015 0 repositories listed
-
Object Detection by Labeling Superpixels1 Jun 2015 0 repositories listed
-
Traditional Saliency Reloaded: A Good Old Model in New Shape1 Jun 2015 0 repositories listed
-
High-for-Low and Low-for-High: Efficient Boundary Detection from Deep Object Features and its Applications to High-Level Vision23 Apr 2015 0 repositories listed
-
Salient Object Detection: A Survey18 Nov 2014 0 repositories listed
-
Object Proposal Generation using Two-Stage Cascade SVMs20 Jul 2014 0 repositories listed
Syntology lines on 6 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