Published on Wed May 26 2021

Context-aware Cross-level Fusion Network for Camouflaged Object Detection

Yujia Sun, Geng Chen, Tao Zhou, Yi Zhang, Nian Liu

Camouflaged object detection (COD) is a challenging task due to the low boundary contrast between the object and its surroundings. In this paper, we propose a novel Context-aware Cross-level Fusion Network (C2F-Net) to address the task.

0
0
0
Abstract

Camouflaged object detection (COD) is a challenging task due to the low boundary contrast between the object and its surroundings. In addition, the appearance of camouflaged objects varies significantly, e.g., object size and shape, aggravating the difficulties of accurate COD. In this paper, we propose a novel Context-aware Cross-level Fusion Network (C2F-Net) to address the challenging COD task. Specifically, we propose an Attention-induced Cross-level Fusion Module (ACFM) to integrate the multi-level features with informative attention coefficients. The fused features are then fed to the proposed Dual-branch Global Context Module (DGCM), which yields multi-scale feature representations for exploiting rich global context information. In C2F-Net, the two modules are conducted on high-level features using a cascaded manner. Extensive experiments on three widely used benchmark datasets demonstrate that our C2F-Net is an effective COD model and outperforms state-of-the-art models remarkably. Our code is publicly available at: https://github.com/thograce/C2FNet.

Thu Jan 14 2021
Computer Vision
Accurate Camouflaged Object Detection via Mixture Convolution and Interactive Fusion
Camouflaged object detection (COD) aims to identify the objects that conceal themselves into the surroundings. We propose a novel deep learning based COD approach, which integrates the large receptive field and effective feature fusion into a unified framework. Our method detects camouflaged objects with an effective fusion strategy, which aggregates the rich context
0
0
0
Tue Feb 04 2020
Computer Vision
Selective Convolutional Network: An Efficient Object Detector with Ignoring Background
Selective Convolutional Network (SCN) selectivelyculates only on the locations that contain meaningful and conducive information. The basic idea is to exclude the insignificant background areas, which effectively reduces the computational cost especially during the feature extraction.
0
0
0
Thu May 20 2021
Computer Vision
AGSFCOS: Based on attention mechanism and Scale-Equalizing pyramid network of object detection
The anchor-free object detection model has shown great potential for accuracy and speed to exceed anchor-based object detection. Our optimal model can get 39.5% COCO AP under the background of ResNet50. The attention mechanism module can capture contextual information well.
0
0
0
Mon Jul 12 2021
Computer Vision
Locally Enhanced Self-Attention: Rethinking Self-Attention as Local and Context Terms
Locally Enhanced Self-Attention (LESA) is based on Conditional Random Fields (CRFs) LESA incorporates the unary term by incorporating it with convolutions, and utilizes a fusion module to dynamically couple unary and binary operations.
1
11
41
Fri Dec 04 2020
Computer Vision
Global Context Aware RCNN for Object Detection
RoIPool/RoIAlign is an indispensable process for the typical two-stage object detection algorithm. We propose a novel end-to-end trainable framework, called Global Context Aware (GCA) RCNN. The core component of the framework is a context aware mechanism.
0
0
0
Sat Apr 03 2021
Computer Vision
Mutual Graph Learning for Camouflaged Object Detection
0
0
0
Tue Apr 21 2020
Machine Learning
AdaX: Adaptive Gradient Descent with Exponential Long Term Memory
AdaX exponentially accumulates the long-term gradient information in the past during training. Extensive experiments show that AdaX outperforms Adam in various tasks.
0
0
0
Tue Sep 29 2020
Computer Vision
Attentional Feature Fusion
Feature fusion is an omnipresent part of modern network architectures. To better fuse features of inconsistent semantics and scales, we propose a multi-scale channel attention module. Our models outperform state-of-the-art networks on both CIFAR-100 and ImageNet datasets.
0
0
0
Sat Jul 25 2020
Computer Vision
MirrorNet: Bio-Inspired Camouflaged Object Segmentation
The MirrorNet is a network that leverages both instance segmentation and mirror stream for the camouflaged object segmentation. The output from the mirror stream is then fused into the main stream's result for the final camouflage map to boost up the segmentation accuracy.
0
0
0
Sat Mar 06 2021
Computer Vision
Simultaneously Localize, Segment and Rank the Camouflaged Objects
0
0
0
Fri Mar 01 2019
Computer Vision
Pyramid Feature Attention Network for Saliency detection
Saliency detection is one of the basic challenges in computer vision. Not all features are useful for saliency detection and some even cause interferences. We propose Pyramid Feature Attention network to focus on effective high-level context features.
0
0
0
Sun Dec 04 2016
Computer Vision
Pyramid Scene Parsing Network
The proposed approach achieves state-of-the-art performance on various datasets. A single PSPNet yields new record of mIoU accuracy 85.4% on PASCAL VOC 2012 and 80.2% on Cityscapes.
0
0
0