Concealed Object Detection

Abstract

We present the first systematic study on concealed object detection (COD), which aims to identify objects that are "perfectly" 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 12 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 on our project page: http://mmcheng.net/cod.

17 pages, 27 figures, Code: https://github.com/GewelsJI/SINet-V2

References in corpus (6)

• Review of Artificial Intelligence Techniques in Imaging Data Acquisition, Segmentation and Diagnosis for COVID-19
• Segmentation-Based Deep-Learning Approach for Surface-Defect Detection
• Anabranch Network for Camouflaged Object Segmentation
• Boundary-Aware Segmentation Network for Mobile and Web Applications
• Camouflaged Object Detection and Tracking: A Survey
• Simultaneously Localize, Segment and Rank the Camouflaged Objects

Cited by in corpus (32)

• Polyp-PVT: Polyp Segmentation with Pyramid Vision Transformers
• Boundary-Guided Camouflaged Object Detection
• Deep Gradient Learning for Efficient Camouflaged Object Detection
• Feature Aggregation and Propagation Network for Camouflaged Object Detection
• Fast Camouflaged Object Detection via Edge-based Reversible Re-calibration Network
• CAVER: Cross-Modal View-Mixed Transformer for Bi-Modal Salient Object Detection
• Segment Anything Is Not Always Perfect: An Investigation of SAM on Different Real-world Applications
• Video Polyp Segmentation: A Deep Learning Perspective
• Progressively Normalized Self-Attention Network for Video Polyp Segmentation
• Advances in Deep Concealed Scene Understanding
• ZoomNeXt: A Unified Collaborative Pyramid Network for Camouflaged Object Detection
• SAM Struggles in Concealed Scenes -- Empirical Study on Segment Anything
• Bilateral Reference for High-Resolution Dichotomous Image Segmentation
• A Survey on Deep Learning for Polyp Segmentation: Techniques, Challenges and Future Trends
• Salient Objects in Clutter
• GCoNet+: A Stronger Group Collaborative Co-Salient Object Detector
• Patch is Enough: Naturalistic Adversarial Patch against Vision-Language Pre-training Models
• Effectiveness Assessment of Recent Large Vision-Language Models
• Depth Awakens: A Depth-perceptual Attention Fusion Network for RGB-D Camouflaged Object Detection
• Context in object detection: a systematic literature review
• Context-aware Cross-level Fusion Network for Camouflaged Object Detection
• Rethinking Object Saliency Ranking: A Novel Whole-flow Processing Paradigm
• Improving Camouflaged Object Detection with the Uncertainty of Pseudo-edge Labels
• How Good is Google Bard's Visual Understanding? An Empirical Study on Open Challenges
• View-aware Salient Object Detection for 360° Omnidirectional Image
• Towards Real Zero-Shot Camouflaged Object Segmentation without Camouflaged Annotations
• Acquiring Weak Annotations for Tumor Localization in Temporal and Volumetric Data
• Weakly Supervised Camouflaged Object Detection Based on the SAM Model and Mask Guidance
• Utilizing Grounded SAM for self-supervised frugal camouflaged human detection
• Synthetic-to-Real Camouflaged Object Detection
• Fine-grained spatial-temporal perception for gas leak segmentation
• CamoNAS: Neural Architecture Search for Enhanced Camouflaged Object Detection