Towards Open-Set Object Detection and Discovery
- URL: http://arxiv.org/abs/2204.05604v1
- Date: Tue, 12 Apr 2022 08:07:01 GMT
- Title: Towards Open-Set Object Detection and Discovery
- Authors: Jiyang Zheng, Weihao Li, Jie Hong, Lars Petersson, Nick Barnes
- Abstract summary: 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.
- Score: 38.81806249664884
- License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
- Abstract: With the human pursuit of knowledge, open-set object detection (OSOD) has
been designed to identify unknown objects in a dynamic world. However, an issue
with the current setting is that all the predicted unknown objects share the
same category as "unknown", which require incremental learning via a
human-in-the-loop approach to label novel classes. In order to address this
problem, we present a new task, namely Open-Set Object Detection and Discovery
(OSODD). This new task aims to extend the ability of open-set object detectors
to further discover the categories of unknown objects based on their visual
appearance without human effort. 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. With this method, a
detector is able to detect objects belonging to known classes and define novel
categories for objects of unknown classes with minimal supervision. We show the
performance of our model on the MS-COCO dataset under a thorough evaluation
protocol. We hope that our work will promote further research towards a more
robust real-world detection system.
Related papers
- 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) - Detecting the unknown in Object Detection [20.84221126313118]
We propose a novel training strategy, called UNKAD, able to predict unknown objects without requiring any annotation.
UNKAD first identifies and pseudo-labels unknown objects and then uses the pseudo-annotations to train an additional unknown class.
While UNKAD can directly detect unknown objects, we further combine it with previous unknown detection techniques, showing that it improves their performance at no costs.
arXiv Detail & Related papers (2022-08-24T16:27:38Z) - More Practical Scenario of Open-set Object Detection: Open at Category
Level and Closed at Super-category Level [23.98839374194848]
Open-set object detection (OSOD) has recently attracted considerable attention.
We first point out that the scenario of OSOD considered in recent studies, which considers an unlimited variety of unknown objects, has a fundamental issue.
This issue leads to difficulty with the evaluation of methods' performance on unknown object detection.
arXiv Detail & Related papers (2022-07-20T09:28:51Z) - Learning Open-World Object Proposals without Learning to Classify [110.30191531975804]
We propose a classification-free Object Localization Network (OLN) which estimates the objectness of each region purely by how well the location and shape of a region overlaps with any ground-truth object.
This simple strategy learns generalizable objectness and outperforms existing proposals on cross-category generalization.
arXiv Detail & Related papers (2021-08-15T14:36:02Z) - The Pursuit of Knowledge: Discovering and Localizing Novel Categories
using Dual Memory [85.01439251151203]
We tackle object category discovery, which is the problem of discovering and localizing novel objects in a large unlabeled dataset.
We propose a method to use prior knowledge about certain object categories to discover new categories by leveraging two memory modules.
We show the performance of our detector on the COCO minival dataset to demonstrate its in-the-wild capabilities.
arXiv Detail & Related papers (2021-05-04T17:55:59Z) - 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) - Class-agnostic Object Detection [16.97782147401037]
We propose class-agnostic object detection as a new problem that focuses on detecting objects irrespective of their object-classes.
Specifically, the goal is to predict bounding boxes for all objects in an image but not their object-classes.
We propose training and evaluation protocols for benchmarking class-agnostic detectors to advance future research in this domain.
arXiv Detail & Related papers (2020-11-28T19:22:38Z) - Slender Object Detection: Diagnoses and Improvements [74.40792217534]
In this paper, we are concerned with the detection of a particular type of objects with extreme aspect ratios, namely textbfslender objects.
For a classical object detection method, a drastic drop of $18.9%$ mAP on COCO is observed, if solely evaluated on slender objects.
arXiv Detail & Related papers (2020-11-17T09:39:42Z)
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.