Enhancing Novel Object Detection via Cooperative Foundational Models

Fuente: arXiv
Saved in:
Bibliographic Details
Main Authors: Bharadwaj, Rohit, Naseer, Muzammal, Khan, Salman, Khan, Fahad Shahbaz
Format: Preprint
Published: 2023
Subjects:
Online Access:
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866929677041401856
author Bharadwaj, Rohit
Naseer, Muzammal
Khan, Salman
Khan, Fahad Shahbaz
author_facet Bharadwaj, Rohit
Naseer, Muzammal
Khan, Salman
Khan, Fahad Shahbaz
contents In this work, we address the challenging and emergent problem of novel object detection (NOD), focusing on the accurate detection of both known and novel object categories during inference. Traditional object detection algorithms are inherently closed-set, limiting their capability to handle NOD. We present a novel approach to transform existing closed-set detectors into open-set detectors. This transformation is achieved by leveraging the complementary strengths of pre-trained foundational models, specifically CLIP and SAM, through our cooperative mechanism. Furthermore, by integrating this mechanism with state-of-the-art open-set detectors such as GDINO, we establish new benchmarks in object detection performance. Our method achieves 17.42 mAP in novel object detection and 42.08 mAP for known objects on the challenging LVIS dataset. Adapting our approach to the COCO OVD split, we surpass the current state-of-the-art by a margin of 7.2 $ \text{AP}_{50} $ for novel classes. Our code is available at https://rohit901.github.io/coop-foundation-models/ .
format Preprint
id arxiv_https___arxiv_org_abs_2311_12068
institution arXiv
publishDate 2023
record_format arxiv
spellingShingle Enhancing Novel Object Detection via Cooperative Foundational Models
Bharadwaj, Rohit
Naseer, Muzammal
Khan, Salman
Khan, Fahad Shahbaz
Computer Vision and Pattern Recognition
Artificial Intelligence
Machine Learning
In this work, we address the challenging and emergent problem of novel object detection (NOD), focusing on the accurate detection of both known and novel object categories during inference. Traditional object detection algorithms are inherently closed-set, limiting their capability to handle NOD. We present a novel approach to transform existing closed-set detectors into open-set detectors. This transformation is achieved by leveraging the complementary strengths of pre-trained foundational models, specifically CLIP and SAM, through our cooperative mechanism. Furthermore, by integrating this mechanism with state-of-the-art open-set detectors such as GDINO, we establish new benchmarks in object detection performance. Our method achieves 17.42 mAP in novel object detection and 42.08 mAP for known objects on the challenging LVIS dataset. Adapting our approach to the COCO OVD split, we surpass the current state-of-the-art by a margin of 7.2 $ \text{AP}_{50} $ for novel classes. Our code is available at https://rohit901.github.io/coop-foundation-models/ .
title Enhancing Novel Object Detection via Cooperative Foundational Models
topic Computer Vision and Pattern Recognition
Artificial Intelligence
Machine Learning
url https://arxiv.org/abs/2311.12068