Region Proposal
136 papers with code • 1 benchmarks • 5 datasets
Libraries
Use these libraries to find Region Proposal models and implementationsLatest 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
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
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
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
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
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.