Addressing the Challenges of Open-World Object Detection
- URL: http://arxiv.org/abs/2303.14930v1
- Date: Mon, 27 Mar 2023 06:11:28 GMT
- Title: Addressing the Challenges of Open-World Object Detection
- Authors: David Pershouse, Feras Dayoub, Dimity Miller, Niko S\"underhauf
- Abstract summary: OW-RCNN is an open world object detector that addresses the three main challenges of open world object detection (OWOD)
OW-RCNN establishes a new state of the art using the open-world evaluation protocol on MS-COCO.
- Score: 12.053132866404972
- License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
- Abstract: We address the challenging problem of open world object detection (OWOD),
where object detectors must identify objects from known classes while also
identifying and continually learning to detect novel objects. Prior work has
resulted in detectors that have a relatively low ability to detect novel
objects, and a high likelihood of classifying a novel object as one of the
known classes. We approach the problem by identifying the three main challenges
that OWOD presents and introduce OW-RCNN, an open world object detector that
addresses each of these three challenges. OW-RCNN establishes a new state of
the art using the open-world evaluation protocol on MS-COCO, showing a
drastically increased ability to detect novel objects (16-21% absolute increase
in U-Recall), to avoid their misclassification as one of the known classes (up
to 52% reduction in A-OSE), and to incrementally learn to detect them while
maintaining performance on previously known classes (1-6% absolute increase in
mAP).
Related papers
- V3Det Challenge 2024 on Vast Vocabulary and Open Vocabulary Object Detection: Methods and Results [142.5704093410454]
The V3Det Challenge 2024 aims to push the boundaries of object detection research.
The challenge consists of two tracks: Vast Vocabulary Object Detection and Open Vocabulary Object Detection.
We aim to inspire future research directions in vast vocabulary and open-vocabulary object detection.
arXiv Detail & Related papers (2024-06-17T16:58:51Z) - Enhancing Novel Object Detection via Cooperative Foundational Models [75.30243629533277]
We present a novel approach to transform existing closed-set detectors into open-set detectors.
We surpass the current state-of-the-art by a margin of 7.2 $ textAP_50 $ for novel classes.
arXiv Detail & Related papers (2023-11-19T17:28:28Z) - Towards Open World Active Learning for 3D Object Detection [43.242426340854905]
We introduce Open World Active Learning for 3D Object Detection (OWAL-3D)
OWAL-3D aims at selecting a small number of 3D boxes to annotate while maximizing detection performance on both known and unknown classes.
We unify both relational constraints into a simple and effective AL strategy namely OpenCRB, which guides to acquisition of informative point clouds.
arXiv Detail & Related papers (2023-10-16T13:32:53Z) - Unsupervised Recognition of Unknown Objects for Open-World Object
Detection [28.787586991713535]
Open-World Object Detection (OWOD) extends object detection problem to a realistic and dynamic scenario.
Current OWOD models, such as ORE and OW-DETR, focus on pseudo-labeling regions with high objectness scores as unknowns.
This paper proposes a novel approach that learns an unsupervised discriminative model to recognize true unknown objects.
arXiv Detail & Related papers (2023-08-31T08:17:29Z) - Open World DETR: Transformer based Open World Object Detection [60.64535309016623]
We propose a two-stage training approach named Open World DETR for open world object detection based on Deformable DETR.
We fine-tune the class-specific components of the model with a multi-view self-labeling strategy and a consistency constraint.
Our proposed method outperforms other state-of-the-art open world object detection methods by a large margin.
arXiv Detail & Related papers (2022-12-06T13:39:30Z) - Incremental-DETR: Incremental Few-Shot Object Detection via
Self-Supervised Learning [60.64535309016623]
We propose the Incremental-DETR that does incremental few-shot object detection via fine-tuning and self-supervised learning on the DETR object detector.
To alleviate severe over-fitting with few novel class data, we first fine-tune the class-specific components of DETR with self-supervision.
We further introduce a incremental few-shot fine-tuning strategy with knowledge distillation on the class-specific components of DETR to encourage the network in detecting novel classes without catastrophic forgetting.
arXiv Detail & Related papers (2022-05-09T05:08:08Z) - Towards Open-Set Object Detection and Discovery [38.81806249664884]
We present a new task, namely Open-Set Object Detection and Discovery (OSODD)
We propose a two-stage method that first uses an open-set object detector to predict both known and unknown objects.
Then, we study the representation of predicted objects in an unsupervised manner and discover new categories from the set of unknown objects.
arXiv Detail & Related papers (2022-04-12T08:07:01Z) - OW-DETR: Open-world Detection Transformer [90.56239673123804]
We introduce a novel end-to-end transformer-based framework, OW-DETR, for open-world object detection.
OW-DETR comprises three dedicated components namely, attention-driven pseudo-labeling, novelty classification and objectness scoring.
Our model outperforms the recently introduced OWOD approach, ORE, with absolute gains ranging from 1.8% to 3.3% in terms of unknown recall.
arXiv Detail & Related papers (2021-12-02T18:58:30Z) - Towards Open World Object Detection [68.79678648726416]
ORE: Open World Object Detector is based on contrastive clustering and energy based unknown identification.
We find that identifying and characterizing unknown instances helps to reduce confusion in an incremental object detection setting.
arXiv Detail & Related papers (2021-03-03T18:58:18Z)
This list is automatically generated from the titles and abstracts of the papers in this site.
This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.