No article text was recorded for this version.
class-agnostic region proposal
Version 2 of 2469 papers650 conceptsfrozen 2026-10-04
Papers in this version
- Blog: Detecting Everything in the Open World: Towards Universal Object Detection
- Blog: Unknown Sniffer for Object Detection: Don't Turn a Blind Eye to Unknown Objects
- Blog: Scalable Object Detection Using Deep Neural Networks
- Blog: UN-DETR: Promoting Objectness Learning via Joint Supervision for Unknown Object Detection
- Blog: OpenInst: A Simple Query-Based Method for Open-World Instance Segmentation
- Blog: Rethinking the Route Towards Weakly Supervised Object Localization
- Blog: MASON: A Model AgnoStic ObjectNess Framework
- Blog: Learning to Track Any Object
- Blog: Exemplar-Based Open-Set Panoptic Segmentation Network
- Blog: Fine-Grained Entity Segmentation
- Blog: Improving Open-World Object Localization by Discovering Background
- Blog: 1st Place Solutions for the UVO Challenge 2022
- Blog: Open-World Instance Segmentation: Exploiting Pseudo Ground Truth From Learned Pairwise Affinity
- Blog: Dual Decision Improves Open-Set Panoptic Segmentation
- Blog: Exploring Orthogonality in Open World Object Detection
- Blog: Unknown Sniffer for Object Detection: Don't Turn a Blind Eye to Unknown Objects
- Blog: Addressing the Challenges of Open-World Object Detection
- Blog: S4Net: Single stage salient-instance segmentation
- Blog: Deep learning for class-generic object detection
- Blog: Debiased Novel Category Discovering and Localization
- Blog: Commonality-Parsing Network Across Shape and Appearance for Partially Supervised Instance Segmentation
- Blog: Unidentified Video Objects: A Benchmark for Dense, Open-World Segmentation
- Blog: R-FCN-3000 at 30fps: Decoupling Detection and Classification
- Blog: Open-World Objectness Modeling Unifies Novel Object Detection
- Blog: Cubify Anything: Scaling Indoor 3D Object Detection
- Blog: 4D Generic Video Object Proposals
- Blog: CAT: LoCalization and IdentificAtion Cascade Detection Transformer for Open-World Object Detection
- Blog: PromptDet: Towards Open-Vocabulary Detection Using Uncurated Images
- Blog: Object-level Semantic and Spatial Distillation for Open Vocabulary Detection
- Blog: A Simple Baseline for Open-Vocabulary Semantic Segmentation with Pre-trained Vision-Language Model
- Blog: Parts4Feature: Learning 3D Global Features from Generally Semantic Parts in Multiple Views
- Blog: One-Shot Instance Segmentation
- Blog: CoinSeg: Contrast Inter- and Intra- Class Representations for Incremental Segmentation
- Blog: Interactively Picking Real-World Objects with Unconstrained Spoken Language Instructions
- Blog: ContrastMask: Contrastive Learning to Segment Every Thing
- Blog: CSL: Class-Agnostic Structure-Constrained Learning for Segmentation Including the Unseen
- Blog: Exploiting VLM Localizability and Semantics for Open Vocabulary Action Detection
- Blog: Segmenting Unknown 3D Objects from Real Depth Images using Mask R-CNN Trained on Synthetic Point Clouds
- Blog: Exploring Transformers for Open-world Instance Segmentation
- Blog: SFUOD: Source-Free Unknown Object Detection
- Blog: Unsupervised Recognition of Unknown Objects for Open-World Object Detection
- Blog: Efficient Pipeline for Automating Species ID in new Camera Trap Projects
- Blog: Open-world Instance Segmentation: Top-down Learning with Bottom-up Supervision
- Blog: Region-Aware Pretraining for Open-Vocabulary Object Detection with Vision Transformers
- Blog: Exploiting VLM Localizability and Semantics for Open Vocabulary Action Detection
- Blog: Latent SVM for Object Localization in Weakly Labeled Videos
- Blog: End-to-end Tracking with a Multi-query Transformer
- Blog: Incremental Few-Shot Instance Segmentation
- Blog: Prototypical Kernel Learning and Open-set Foreground Perception for Generalized Few-shot Semantic Segmentation
- Blog: Towards Open-World Segmentation of Parts
- Blog: Open-world Weakly-Supervised Object Localization
- Blog: Lowis3D: Language-Driven Open-World Instance-Level 3D Scene Understanding
- Blog: Unsupervised Object Localization in the Era of Self-Supervised ViTs: A Survey
- Blog: Towards Open-Vocabulary Multimodal 3D Object Detection with Attributes
- Blog: OCTrack: Benchmarking the Open-Corpus Multi-Object Tracking
- Blog: Two-stage Decision Improves Open-Set Panoptic Segmentation
- Blog: Learning to Discover and Detect Objects
- Blog: Instance-aware Remote Sensing Image Captioning with Cross-hierarchy Attention
- Blog: PoserNet: Refining Relative Camera Poses Exploiting Object Detections
- Blog: The surprising impact of mask-head architecture on novel class segmentation
Showing 60 of 469 papers.
History & citation
Current · Permanent link
- cross-category objectness generalization split from this direction (83% overlap)
- closed-world assumption (open-world object detection) split from this direction (50% overlap)
Cite this direction
Latest version (a living page):
@misc{lacuna_class_agnostic_region_proposal_985dbb0d,
title = {class-agnostic region proposal},
author = {{Lacuna}},
howpublished = {Lacuna research direction},
year = {2026},
url = {https://lacuna.tiptreesystems.com/direction/class-agnostic-region-proposal/rdr_985dbb0de0634977930637a4a0315215},
note = {Latest version of a living research direction; cite a version for a fixed text. Accessed 2026-11-21},
}This exact version (version 2, frozen text):
@misc{lacuna_class_agnostic_region_proposal_985dbb0d_v2,
title = {class-agnostic region proposal},
author = {{Lacuna}},
howpublished = {Lacuna research direction},
year = {2026},
url = {https://lacuna.tiptreesystems.com/direction/class-agnostic-region-proposal/rdr_985dbb0de0634977930637a4a0315215/v/2},
note = {Version 2, frozen 2026-10-04. Accessed 2026-11-21},
}