Concealed Object Detection
- PMID: 34061739
- DOI: 10.1109/TPAMI.2021.3085766
Concealed Object Detection
Abstract
We present the first systematic study on concealed object detection (COD), which aims to identify objects that are visually embedded in their background. The high intrinsic similarities between the concealed objects and their background make COD far more challenging than traditional object detection/segmentation. To better understand this task, we collect a large-scale dataset, called COD10K, which consists of 10,000 images covering concealed objects in diverse real-world scenarios from 78 object categories. Further, we provide rich annotations including object categories, object boundaries, challenging attributes, object-level labels, and instance-level annotations. Our COD10K is the largest COD dataset to date, with the richest annotations, which enables comprehensive concealed object understanding and can even be used to help progress several other vision tasks, such as detection, segmentation, classification etc. Motivated by how animals hunt in the wild, we also design a simple but strong baseline for COD, termed the Search Identification Network (SINet). Without any bells and whistles, SINet outperforms twelve cutting-edge baselines on all datasets tested, making them robust, general architectures that could serve as catalysts for future research in COD. Finally, we provide some interesting findings, and highlight several potential applications and future directions. To spark research in this new field, our code, dataset, and online demo are available at our project page: http://mmcheng.net/cod.
Similar articles
-
Collaborative Camouflaged Object Detection: A Large-Scale Dataset and Benchmark.IEEE Trans Neural Netw Learn Syst. 2023 Oct 27;PP. doi: 10.1109/TNNLS.2023.3317091. Online ahead of print. IEEE Trans Neural Netw Learn Syst. 2023. PMID: 37889825
-
Zero-Shot Camouflaged Object Detection.IEEE Trans Image Process. 2023;32:5126-5137. doi: 10.1109/TIP.2023.3308295. Epub 2023 Sep 12. IEEE Trans Image Process. 2023. PMID: 37643103
-
Survey and Performance Analysis of Deep Learning Based Object Detection in Challenging Environments.Sensors (Basel). 2021 Jul 28;21(15):5116. doi: 10.3390/s21155116. Sensors (Basel). 2021. PMID: 34372351 Free PMC article. Review.
-
Re-Thinking Co-Salient Object Detection.IEEE Trans Pattern Anal Mach Intell. 2022 Aug;44(8):4339-4354. doi: 10.1109/TPAMI.2021.3060412. Epub 2022 Jul 1. IEEE Trans Pattern Anal Mach Intell. 2022. PMID: 33600309
-
Performance of a Computational Model of the Mammalian Olfactory System.In: Persaud KC, Marco S, Gutiérrez-Gálvez A, editors. Neuromorphic Olfaction. Boca Raton (FL): CRC Press/Taylor & Francis; 2013. Chapter 6. In: Persaud KC, Marco S, Gutiérrez-Gálvez A, editors. Neuromorphic Olfaction. Boca Raton (FL): CRC Press/Taylor & Francis; 2013. Chapter 6. PMID: 26042330 Free Books & Documents. Review.
Cited by
-
Time-Series Field Phenotyping of Soybean Growth Analysis by Combining Multimodal Deep Learning and Dynamic Modeling.Plant Phenomics. 2024 Mar 20;6:0158. doi: 10.34133/plantphenomics.0158. eCollection 2024. Plant Phenomics. 2024. PMID: 38524738 Free PMC article.
-
Edge-Guided Camouflaged Object Detection via Multi-Level Feature Integration.Sensors (Basel). 2023 Jun 21;23(13):5789. doi: 10.3390/s23135789. Sensors (Basel). 2023. PMID: 37447638 Free PMC article.
-
MAGNet: A Camouflaged Object Detection Network Simulating the Observation Effect of a Magnifier.Entropy (Basel). 2022 Dec 9;24(12):1804. doi: 10.3390/e24121804. Entropy (Basel). 2022. PMID: 36554209 Free PMC article.
Publication types
MeSH terms
LinkOut - more resources
Full Text Sources
Other Literature Sources