Region Proposal
136 papers with code • 1 benchmarks • 5 datasets
Benchmarks
These leaderboards are used to track progress in Region Proposal
| Trend | Dataset | Best Model | Paper | Code | Compare |
|---|---|---|---|---|---|
|
Libraries
Use these libraries to find Region Proposal models and implementations
MS COCO
RefCOCO
ABC Dataset
MobilityAids
ISBDA
Latest papers
Training-free Boost for Open-Vocabulary Object Detection with Confidence Aggregation
Specifically, in the region-proposal stage, proposals that contain novel instances showcase lower objectness scores, since they are treated as background proposals during the training phase.
Generative Region-Language Pretraining for Open-Ended Object Detection
foundationvision/generateu
•
•
To address it, we formulate object detection as a generative problem and propose a simple framework named GenerateU, which can detect dense objects and generate their names in a free-form way.
PETDet: Proposal Enhancement for Two-Stage Fine-Grained Object Detection
canoe-z/petdet
•
•
Fine-grained object detection (FGOD) extends object detection with the capability of fine-grained recognition.
Boosting Segment Anything Model Towards Open-Vocabulary Learning
The recent Segment Anything Model (SAM) has emerged as a new paradigmatic vision foundation model, showcasing potent zero-shot generalization and flexible prompting.
OVIR-3D: Open-Vocabulary 3D Instance Retrieval Without Training on 3D Data
This work presents OVIR-3D, a straightforward yet effective method for open-vocabulary 3D object instance retrieval without using any 3D data for training.
How To Effectively Train An Ensemble Of Faster R-CNN Object Detectors To Quantify Uncertainty
akola-mbey-denis/efficientensemble
•
•
This paper presents a new approach for training two-stage object detection ensemble models, more specifically, Faster R-CNN models to estimate uncertainty.
DST-Det: Simple Dynamic Self-Training for Open-Vocabulary Object Detection
We 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.
Few-shot Object Detection in Remote Sensing: Lifting the Curse of Incompletely Annotated Novel Objects
zhu-xlab/st-fsod
•
•
In this context, few-shot object detection (FSOD) has emerged as a promising direction, which aims at enabling the model to detect novel objects with only few of them annotated.
Unsupervised Recognition of Unknown Objects for Open-World Object Detection
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 learning newly introduced knowledge.
An extensible point-based method for data chart value detection
bnlnlp/ppn_model
•
•
We present an extensible method for identifying semantic points to reverse engineer (i. e. extract the values of) data charts, particularly those in scientific articles.
