☆ 4.6 Article

Edge-Guided Camouflaged Object Detection via Multi-Level Feature Integration

SENSORS (2023)

Related references

Note: Only part of the references are listed.

Article Automation & Control Systems

D2C-Net: A Dual-Branch, Dual-Guidance and Cross-Refine Network for Camouflaged Object Detection

Kang Wang et al.

Summary: This article proposes a novel framework for camouflaged object detection (COD), named (DC)-C-2-Net, which includes two new modules: Dual-branch features extraction (DFE) and gradually refined cross fusion (GRCF). The framework outperforms 13 state-of-the-art deep learning-based methods on three public datasets and shows successful applications in surface defect detection and medical image segmentation.

IEEE TRANSACTIONS ON INDUSTRIAL ELECTRONICS (2022)

Add to Collection

Article Computer Science, Artificial Intelligence

Fast Camouflaged Object Detection via Edge-based Reversible Re-calibration Network

Ge-Peng Ji et al.

Summary: Camouflaged Object Detection (COD) is a growing research area. This paper proposes a novel edge-based reversible re-calibration network called ERRNet, which models visual perception behavior using selective edge aggregation and reversible re-calibration units. Experimental results show that ERRNet outperforms existing models on multiple datasets.

PATTERN RECOGNITION (2022)

Add to Collection

Article Engineering, Electrical & Electronic

Camouflaged Object Detection via Context-Aware Cross-Level Fusion

Geng Chen et al.

Summary: Camouflaged object detection aims to identify hidden objects in natural scenes. To address challenges such as low boundary contrast and variation in object appearances, a novel Context-aware Cross-level Fusion Network is proposed, which accurately identifies camouflaged objects by fusing context-aware cross-level features.

IEEE TRANSACTIONS ON CIRCUITS AND SYSTEMS FOR VIDEO TECHNOLOGY (2022)

Add to Collection

Proceedings Paper Computer Science, Artificial Intelligence

Zoom In and Out: A Mixed-scale Triplet Network for Camouflaged Object Detection

Youwei Pang et al.

Summary: The article proposes a mixed-scale triplet network, ZoomNet, that mimics human behavior of zooming in and out to address the challenges in camouflaged object detection. The network learns discriminative mixed-scale semantics through a zoom strategy and introduces an uncertainty-aware loss to improve prediction accuracy.

2022 IEEE/CVF CONFERENCE ON COMPUTER VISION AND PATTERN RECOGNITION (CVPR 2022) (2022)

Add to Collection

Article Computer Science, Artificial Intelligence

Concealed Object Detection

Deng-Ping Fan et al.

Summary: This study presents the first systematic research on concealed object detection (COD) and introduces the COD10K dataset, along with rich annotations. The Search Identification Network (SINet) is proposed as a strong baseline model, outperforming 12 cutting-edge baselines in various datasets. The study also highlights potential applications and future directions in the field.

IEEE TRANSACTIONS ON PATTERN ANALYSIS AND MACHINE INTELLIGENCE (2022)

Add to Collection

Article Computer Science, Artificial Intelligence

EDN: Salient Object Detection via Extremely-Downsampled Network

Yu-Huan Wu et al.

Summary: Recent progress in salient object detection focuses on multi-scale learning, with a collaboration between high-level and low-level features. However, most efforts have been on enhancing low-level feature learning, neglecting the importance of high-level features in SOD. This paper introduces an Extremely-Downsampled Network (EDN) and Scale-Correlated Pyramid Convolution (SCPC) to enhance high-level feature learning for accurate salient object localization.

IEEE TRANSACTIONS ON IMAGE PROCESSING (2022)

Add to Collection

Article Computer Science, Artificial Intelligence

Res2Net: A New Multi-Scale Backbone Architecture

Shang-Hua Gao et al.

Summary: This paper introduces a novel building block for CNNs, Res2Net, which represents multiscale features within one single residual block by constructing hierarchical residual-like connections. The Res2Net enhances the representation of multiscale features in various vision tasks and consistently outperforms baseline models in performance gains.

IEEE TRANSACTIONS ON PATTERN ANALYSIS AND MACHINE INTELLIGENCE (2021)

Add to Collection

Proceedings Paper Computer Science, Artificial Intelligence

Uncertainty-Guided Transformer Reasoning for Camouflaged Object Detection

Fan Yang et al.

Summary: The study introduces a novel approach using a probabilistic representational model and transformers for camouflaged object detection, allowing explicit reasoning under uncertainties and achieving higher accuracy.

2021 IEEE/CVF INTERNATIONAL CONFERENCE ON COMPUTER VISION (ICCV 2021) (2021)

Add to Collection

Proceedings Paper Computer Science, Artificial Intelligence

Camouflaged Object Segmentation with Distraction Mining

Haiyang Mei et al.

Summary: The paper introduces a bio-inspired camouflage object segmentation framework PFNet, consisting of positioning module and focus module, which can effectively and efficiently identify objects perfectly assimilated into their surroundings.

2021 IEEE/CVF CONFERENCE ON COMPUTER VISION AND PATTERN RECOGNITION, CVPR 2021 (2021)

Add to Collection

Proceedings Paper Computer Science, Artificial Intelligence

Mutual Graph Learning for Camouflaged Object Detection

Qiang Zhai et al.

Summary: Detecting/segmenting objects that blend in with their surroundings is difficult for current models due to intrinsic similarities between foreground objects and background surroundings. The Mutual Graph Learning (MGL) model designed in this study is able to decouple an image into task-specific feature maps, effectively incorporating valuable clues from the scene for improved representation. Experiments demonstrate the superior performance of MGL compared to existing state-of-the-art methods on challenging datasets.

2021 IEEE/CVF CONFERENCE ON COMPUTER VISION AND PATTERN RECOGNITION, CVPR 2021 (2021)

Add to Collection

Proceedings Paper Computer Science, Artificial Intelligence

Uncertainty-aware Joint Salient Object and Camouflaged Object Detection

Aixuan Li et al.

Summary: This paper proposes a method to enhance the detection ability of visual salient object detection and camouflaged object detection by leveraging contradictory information. By using easy positive samples in the COD dataset to improve SOD model robustness, introducing a similarity measure module, and employing an adversarial learning network to handle labeling uncertainty, the proposed solution achieves state-of-the-art performance for both tasks.

2021 IEEE/CVF CONFERENCE ON COMPUTER VISION AND PATTERN RECOGNITION, CVPR 2021 (2021)

Add to Collection

Proceedings Paper Computer Science, Artificial Intelligence

Simultaneously Localize, Segment and Rank the Camouflaged Objects

Yunqiu Lv et al.

Summary: Camouflage is a crucial defense mechanism for survival across species. The Camouflaged object detection (COD) aims to segment camouflaged objects hiding in their surroundings. This paper presents the first ranking based COD network, which can simultaneously localize, segment and rank camouflaged objects and has achieved new state-of-the-art results.

2021 IEEE/CVF CONFERENCE ON COMPUTER VISION AND PATTERN RECOGNITION, CVPR 2021 (2021)

Add to Collection

Article Computer Science, Information Systems

MirrorNet: Bio-Inspired Camouflaged Object Segmentation

Jinnan Yan et al.

Summary: This paper introduces a novel bio-inspired network, MirrorNet, which combines instance segmentation and bio-inspired attack stream for camouflaged object segmentation. Experimental results show that this network achieves an accuracy of 89%, outperforming existing techniques.

IEEE ACCESS (2021)

Add to Collection

Article Computer Science, Artificial Intelligence

JCS: An Explainable COVID-19 Diagnosis System by Joint Classification and Segmentation

Yu-Huan Wu et al.

Summary: This paper proposes a novel JCS system for real-time and explainable COVID-19 chest CT diagnosis, trained on a large COVID-CS dataset. The system achieves efficient classification and segmentation results with high sensitivity and specificity for COVID-19 patients.

IEEE TRANSACTIONS ON IMAGE PROCESSING (2021)

Add to Collection

Proceedings Paper Computer Science, Artificial Intelligence

Camouflaged Object Detection

Deng-Ping Fan et al.

2020 IEEE/CVF CONFERENCE ON COMPUTER VISION AND PATTERN RECOGNITION (CVPR) (2020)

Add to Collection

Article Computer Science, Artificial Intelligence

Anabranch network for camouflaged object segmentation

Trung-Nghia Le et al.

COMPUTER VISION AND IMAGE UNDERSTANDING (2019)

Add to Collection

Proceedings Paper Computer Science, Artificial Intelligence

A Mutual Learning Method for Salient Object Detection with intertwined Multi-Supervision

Runmin Wu et al.

2019 IEEE/CVF CONFERENCE ON COMPUTER VISION AND PATTERN RECOGNITION (CVPR 2019) (2019)

Add to Collection

Proceedings Paper Computer Science, Artificial Intelligence

Cascaded Partial Decoder for Fast and Accurate Salient Object Detection

Zhe Wu et al.

2019 IEEE/CVF CONFERENCE ON COMPUTER VISION AND PATTERN RECOGNITION (CVPR 2019) (2019)

Add to Collection

Article Computer Science, Information Systems

A High-Efficiency Fully Convolutional Networks for Pixel-Wise Surface Defect Detection

Lingteng Qiu et al.

IEEE ACCESS (2019)

Add to Collection

Proceedings Paper Computer Science, Artificial Intelligence

Detect Globally, Refine Locally: A Novel Approach to Saliency Detection

Tiantian Wang et al.

2018 IEEE/CVF CONFERENCE ON COMPUTER VISION AND PATTERN RECOGNITION (CVPR) (2018)

Add to Collection

Proceedings Paper Computer Science, Artificial Intelligence

Progressive Attention Guided Recurrent Network for Salient Object Detection

Xiaoning Zhang et al.

2018 IEEE/CVF CONFERENCE ON COMPUTER VISION AND PATTERN RECOGNITION (CVPR) (2018)

Add to Collection

Article Chemistry, Analytical

A Robust Deep-Learning-Based Detector for Real-Time Tomato Plant Diseases and Pests Recognition

Alvaro Fuentes et al.

SENSORS (2017)

Add to Collection

Proceedings Paper Computer Science, Artificial Intelligence

Non-Local Deep Features for Salient Object Detection

Zhiming Luo et al.

30TH IEEE CONFERENCE ON COMPUTER VISION AND PATTERN RECOGNITION (CVPR 2017) (2017)

Add to Collection

Proceedings Paper Computer Science, Artificial Intelligence

Amulet: Aggregating Multi-level Convolutional Features for Salient Object Detectionn

Pingping Zhang et al.

2017 IEEE INTERNATIONAL CONFERENCE ON COMPUTER VISION (ICCV) (2017)

Add to Collection

Proceedings Paper Computer Science, Artificial Intelligence

Deeply Supervised Salient Object Detection with Short Connections

Qibin Hou et al.

30TH IEEE CONFERENCE ON COMPUTER VISION AND PATTERN RECOGNITION (CVPR 2017) (2017)

Add to Collection

Proceedings Paper Computer Science, Artificial Intelligence

Structure-measure: A New Way to Evaluate Foreground Maps

Deng-Ping Fan et al.

2017 IEEE INTERNATIONAL CONFERENCE ON COMPUTER VISION (ICCV) (2017)

Add to Collection

Article Engineering, Civil

Automatic Road Crack Detection Using Random Structured Forests

Yong Shi et al.

IEEE TRANSACTIONS ON INTELLIGENT TRANSPORTATION SYSTEMS (2016)

Add to Collection

Article Engineering, Biomedical

WM-DOVA maps for accurate polyp highlighting in colonoscopy: Validation vs. saliency maps from physicians

Jorge Bernal et al.

COMPUTERIZED MEDICAL IMAGING AND GRAPHICS (2015)

Add to Collection

Article Robotics

Investigation of Vision-based Underwater Object Detection with Multiple Datasets

Dario Lodi Rizzini et al.

INTERNATIONAL JOURNAL OF ADVANCED ROBOTIC SYSTEMS (2015)

Add to Collection

Proceedings Paper Computer Science, Artificial Intelligence

How to Evaluate Foreground Maps?

Ran Margolin et al.

2014 IEEE CONFERENCE ON COMPUTER VISION AND PATTERN RECOGNITION (CVPR) (2014)

Add to Collection

© Peeref 2019-2024. All rights reserved.