Open World Object Detection
22 papers with code • 7 benchmarks • 5 datasets
Open World Object Detection is a computer vision problem where a model is tasked to: 1) identify objects that have not been introduced to it as `unknown', without explicit supervision to do so, and 2) incrementally learn these identified unknown categories without forgetting previously learned classes, when the corresponding labels are progressively received.
Benchmarks
These leaderboards are used to track progress in Open World Object Detection
| Trend | Dataset | Best Model | Paper | Code | Compare |
|---|---|---|---|---|---|
|
|||||
|
|||||
|
|||||
|
|||||
|
|||||
|
|||||
|
MS COCO
PASCAL VOC 2007
UVO
COCO-OOD
COCO-Mix
Most implemented papers
Learning Open-World Object Proposals without Learning to Classify
mcahny/object_localization_network
•
•
In this paper, we identify that the problem is that the binary classifiers in existing proposal methods tend to overfit to the training categories.
Towards Open World Object Detection
Humans have a natural instinct to identify unknown object instances in their environments.
OW-DETR: Open-world Detection Transformer
akshitac8/ow-detr
•
•
CVPR 2022
In the case of incremental object detection, OW-DETR outperforms the state-of-the-art for all settings on PASCAL VOC.
Hyp-OW: Exploiting Hierarchical Structure Learning with Hyperbolic Distance Enhances Open World Object Detection
We argue that this contextual information should already be embedded within the known classes.
Detecting Every Object from Events
hatins/deoe
•
•
Object detection is critical in autonomous driving, and it is more practical yet challenging to localize objects of unknown categories: an endeavour known as Class-Agnostic Object Detection (CAOD).
Class-agnostic Object Detection with Multi-modal Transformer
mmaaz60/mvits_for_class_agnostic_od
•
•
This has been a long-standing question in computer vision.
Revisiting Open World Object Detection
re-owod/re-owod
•
•
Open World Object Detection (OWOD), simulating the real dynamic world where knowledge grows continuously, attempts to detect both known and unknown classes and incrementally learn the identified unknown ones.
Localized Vision-Language Matching for Open-vocabulary Object Detection
In this work, we propose an open-vocabulary object detection method that, based on image-caption pairs, learns to detect novel object classes along with a given set of known classes.
UC-OWOD: Unknown-Classified Open World Object Detection
In this work, we propose a novel OWOD problem called Unknown-Classified Open World Object Detection (UC-OWOD).
PROB: Probabilistic Objectness for Open World Object Detection
The resulting Probabilistic Objectness transformer-based open-world detector, PROB, integrates our framework into traditional object detection models, adapting them for the open-world setting.
