PROB: Probabilistic Objectness for Open World Object Detection

12/02/2022
by   Orr Zohar, et al.
0

Open World Object Detection (OWOD) is a new and challenging computer vision task that bridges the gap between classic object detection (OD) benchmarks and object detection in the real world. In addition to detecting and classifying seen/labeled objects, OWOD algorithms are expected to detect novel/unknown objects - which can be classified and incrementally learned. In standard OD, object proposals not overlapping with a labeled object are automatically classified as background. Therefore, simply applying OD methods to OWOD fails as unknown objects would be predicted as background. The challenge of detecting unknown objects stems from the lack of supervision in distinguishing unknown objects and background object proposals. Previous OWOD methods have attempted to overcome this issue by generating supervision using pseudo-labeling - however, unknown object detection has remained low. Probabilistic/generative models may provide a solution for this challenge. Herein, we introduce a novel probabilistic framework for objectness estimation, where we alternate between probability distribution estimation and objectness likelihood maximization of known objects in the embedded feature space - ultimately allowing us to estimate the objectness probability of different proposals. 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. Comprehensive experiments on OWOD benchmarks show that PROB outperforms all existing OWOD methods in both unknown object detection (∼ 2× unknown recall) and known object detection (∼ 10% mAP). Our code will be made available upon publication at https://github.com/orrzohar/PROB.

READ FULL TEXT

page 1

page 4

page 7

page 8

page 13

page 14

research
03/21/2023

Detecting the open-world objects with the help of the Brain

Open World Object Detection (OWOD) is a novel computer vision task with ...
research
12/02/2021

OW-DETR: Open-world Detection Transformer

Open-world object detection (OWOD) is a challenging computer vision prob...
research
03/24/2023

Unknown Sniffer for Object Detection: Don't Turn a Blind Eye to Unknown Objects

The recently proposed open-world object and open-set detection achieve a...
research
06/04/2023

USD: Unknown Sensitive Detector Empowered by Decoupled Objectness and Segment Anything Model

Open World Object Detection (OWOD) is a novel and challenging computer v...
research
03/08/2022

Unknown-Aware Object Detection: Learning What You Don't Know from Videos in the Wild

Building reliable object detectors that can detect out-of-distribution (...
research
07/17/2023

Random Boxes Are Open-world Object Detectors

We show that classifiers trained with random region proposals achieve st...
research
01/03/2022

Revisiting Open World Object Detection

Open World Object Detection (OWOD), simulating the real dynamic world wh...

Please sign up or login with your details

Forgot password? Click here to reset