Corpus ID: 220793720

MirrorNet: Bio-Inspired Adversarial Attack for Camouflaged Object Segmentation

  title={MirrorNet: Bio-Inspired Adversarial Attack for Camouflaged Object Segmentation},
  author={Jinnan Yan and Trung-Nghia Le and Khanh-Duy Nguyen and Minh-Triet Tran and Thanh-Toan Do and Tam V. Nguyen},
Camouflaged objects are generally difficult to be detected in their natural environment even for human beings. In this paper, we propose a novel bio-inspired network, named the MirrorNet, that leverages both instance segmentation and adversarial attack for the camouflaged object segmentation. Differently from existing networks for segmentation, our proposed network possesses two segmentation streams: the main stream and the adversarial stream corresponding with the original image and its… Expand
Context-aware Cross-level Fusion Network for Camouflaged Object Detection
A novel Context-aware Crosslevel Fusion Network (CF-Net) to address the challenging COD task and proposes an Attention-induced Cross-level Fusion Module (ACFM) to integrate the multi-level features with informative attention coefficients. Expand
Depth-Guided Camouflaged Object Detection
This work presents a depth-guided camouflaged object detection network with pre-computed depth maps from existing monocular depth estimation methods, and introduces a depth quality assessment module to evaluate the quality of depth based on the model prediction from both RGB COD branch and RGB-D C OD branch. Expand
Mutual Graph Learning for Camouflaged Object Detection
A novel Mutual Graph Learning (MGL) model is designed, which generalizes the idea of conventional mutual learning from regular grids to the graph domain and fully exploits the mutual benefits by recurrently reasoning their high-order relations through graphs. Expand
Confidence-Aware Learning for Camouflaged Object Detection
This work presents a confidence-aware camouflaged object detection framework using dynamic supervision to produce both accurate camouflage map and meaningful “confidence” representing model awareness about the current prediction. Expand
Uncertainty-Guided Transformer Reasoning for Camouflaged Object Detection
  • Fan Yang, Qiang Zhai, +4 authors Deng-Ping Fan
  • 2021
Spotting objects that are visually adapted to their surroundings is challenging for both humans and AI. Conventional generic / salient object detection techniques are suboptimal for this task becauseExpand
Boundary-Aware Segmentation Network for Mobile and Web Applications
This paper proposes a simple yet powerful Boundary-Aware Segmentation Network (BASNet), which comprises a predict-refine architecture and a hybrid loss, for highly accurate image segmentation, and further developed two (close to) commercial applications. Expand
Camouflage design, assessment and breaking techniques: a survey
This article discusses various camouflage design, assessment, and breaking techniques in the literature and addresses several issues of interest as well as future research direction in this area. Expand
Camouflaged Object Segmentation with Distraction Mining
A bio-inspired framework, termed Positioning and Focus Network (PFNet), which mimics the process of predation in nature and significantly outperforms 18 cutting-edge models on three challenging datasets under four standard metrics. Expand
Multi-Interactive Dual-Decoder for RGB-Thermal Salient Object Detection
A novel dual-decoder to conduct the interactions of multi-level features, two modalities and global contexts, which works well in diversely challenging scenarios even in the presence of invalid modality. Expand
Simultaneously Localize, Segment and Rank the Camouflaged Objects
It is argued that explicitly modeling the conspicuousness of camouflaged objects against their particular backgrounds can not only lead to a better understanding about camouflage and evolution of animals, but also provide guidance to design more sophisticated camouflage techniques. Expand


Adversarial Examples for Semantic Segmentation and Object Detection
This paper proposes a novel algorithm named Dense Adversary Generation (DAG), which applies to the state-of-the-art networks for segmentation and detection, and finds that the adversarial perturbations can be transferred across networks with different training data, based on different architectures, and even for different recognition tasks. Expand
On the Robustness of Semantic Segmentation Models to Adversarial Attacks
This paper presents what to their knowledge is the first rigorous evaluation of adversarial attacks on modern semantic segmentation models, using two large-scale datasets and shows how mean-field inference in deep structured models and multiscale processing naturally implement recently proposed adversarial defenses. Expand
Anabranch network for camouflaged object segmentation
This paper proposes a general end-to-end network, called the Anabranch Network, that leverages both classification and segmentation tasks and possesses the second branch for classification to predict the probability of containing camouflaged object(s) in an image. Expand
Strike (With) a Pose: Neural Networks Are Easily Fooled by Strange Poses of Familiar Objects
This paper presents a framework for discovering DNN failures that harnesses 3D renderers and 3D models, and investigates the vulnerability of DNNs to OoD poses of well-known objects in ImageNet. Expand
Detection of People With Camouflage Pattern Via Dense Deconvolution Network
Experimental results demonstrate that the proposed method outperforms the classical camouflaged object detection method and typical CNN-based detection methods. Expand
Camouflaged Object Detection
A simple but effective framework for COD, termed Search Identification Network (SINet), which outperforms various state-of-the-art object detection baselines on all datasets tested, making it a robust, general framework that can help facilitate future research in COD. Expand
BASNet: Boundary-Aware Salient Object Detection
Experimental results on six public datasets show that the proposed predict-refine architecture, BASNet, outperforms the state-of-the-art methods both in terms of regional and boundary evaluation measures. Expand
Mask R-CNN
This work presents a conceptually simple, flexible, and general framework for object instance segmentation that outperforms all existing, single-model entries on every task, including the COCO 2016 challenge winners. Expand
DHSNet: Deep Hierarchical Saliency Network for Salient Object Detection
  • Nian Liu, Junwei Han
  • Computer Science
  • 2016 IEEE Conference on Computer Vision and Pattern Recognition (CVPR)
  • 2016
Evaluations on four benchmark datasets and comparisons with other 11 state-of-the-art algorithms demonstrate that DHSNet not only shows its significant superiority in terms of performance, but also achieves a real-time speed of 23 FPS on modern GPUs. Expand
Performance of Decamouflaging Through Exploratory Image Analysis
This paper has proposed a system to identify the camouflaged object and to extract that from the background efficiently, which is needed for the authors' country to save soldiers in defense area. Expand