Paper Reading AI Learner

A bioinspired three-stage model for camouflaged object detection

2023-05-22 02:01:48
Tianyou Chen, Jin Xiao, Xiaoguang Hu, Guofeng Zhang, Shaojie Wang

Abstract

Camouflaged objects are typically assimilated into their backgrounds and exhibit fuzzy boundaries. The complex environmental conditions and the high intrinsic similarity between camouflaged targets and their surroundings pose significant challenges in accurately locating and segmenting these objects in their entirety. While existing methods have demonstrated remarkable performance in various real-world scenarios, they still face limitations when confronted with difficult cases, such as small targets, thin structures, and indistinct boundaries. Drawing inspiration from human visual perception when observing images containing camouflaged objects, we propose a three-stage model that enables coarse-to-fine segmentation in a single iteration. Specifically, our model employs three decoders to sequentially process subsampled features, cropped features, and high-resolution original features. This proposed approach not only reduces computational overhead but also mitigates interference caused by background noise. Furthermore, considering the significance of multi-scale information, we have designed a multi-scale feature enhancement module that enlarges the receptive field while preserving detailed structural cues. Additionally, a boundary enhancement module has been developed to enhance performance by leveraging boundary information. Subsequently, a mask-guided fusion module is proposed to generate fine-grained results by integrating coarse prediction maps with high-resolution feature maps. Our network surpasses state-of-the-art CNN-based counterparts without unnecessary complexities. Upon acceptance of the paper, the source code will be made publicly available at this https URL.

Abstract (translated)

伪装的物体通常会将其背景融入其中,表现出模糊的边界。复杂的环境条件和伪装目标与其周围环境的高内在相似性在准确定位和分割这些物体整个方面提出了巨大的挑战。虽然现有的方法在各种不同的现实世界场景中表现出卓越的性能,但在面对困难的情况,如小型目标、薄结构以及模糊的边界时仍面临限制。从观察包含伪装物体的图像时的人类视觉感知中汲取灵感,我们提出了一个三阶段模型,可以在一次迭代中实现粗到精的分割。具体而言,我们的模型使用三个解码器依次处理缩小的特征、裁剪的特征和高分辨率原始特征。这个 proposed 的方法不仅减少了计算开销,而且还抵消了背景噪声引起的干扰。此外,考虑到多尺度信息的重要性,我们设计了多尺度特征增强模块,扩大接收域并保留详细的结构线索。此外,我们还开发了边界增强模块,通过利用边界信息来提高性能。随后,我们提出了一个用 mask 引导的 fusion 模块通过集成粗预测映射和高分辨率特征映射生成精细结果的方法。我们的网络在没有不必要的复杂度的情况下超越了最先进的卷积神经网络相关器。一旦论文接受,源代码将在此 https URL 上公开发布。

URL

https://arxiv.org/abs/2305.12635

PDF

https://arxiv.org/pdf/2305.12635.pdf


Tags
3D Action Action_Localization Action_Recognition Activity Adversarial Agent Attention Autonomous Bert Boundary_Detection Caption Chat Classification CNN Compressive_Sensing Contour Contrastive_Learning Deep_Learning Denoising Detection Dialog Diffusion Drone Dynamic_Memory_Network Edge_Detection Embedding Embodied Emotion Enhancement Face Face_Detection Face_Recognition Facial_Landmark Few-Shot Gait_Recognition GAN Gaze_Estimation Gesture Gradient_Descent Handwriting Human_Parsing Image_Caption Image_Classification Image_Compression Image_Enhancement Image_Generation Image_Matting Image_Retrieval Inference Inpainting Intelligent_Chip Knowledge Knowledge_Graph Language_Model Matching Medical Memory_Networks Multi_Modal Multi_Task NAS NMT Object_Detection Object_Tracking OCR Ontology Optical_Character Optical_Flow Optimization Person_Re-identification Point_Cloud Portrait_Generation Pose Pose_Estimation Prediction QA Quantitative Quantitative_Finance Quantization Re-identification Recognition Recommendation Reconstruction Regularization Reinforcement_Learning Relation Relation_Extraction Represenation Represenation_Learning Restoration Review RNN Salient Scene_Classification Scene_Generation Scene_Parsing Scene_Text Segmentation Self-Supervised Semantic_Instance_Segmentation Semantic_Segmentation Semi_Global Semi_Supervised Sence_graph Sentiment Sentiment_Classification Sketch SLAM Sparse Speech Speech_Recognition Style_Transfer Summarization Super_Resolution Surveillance Survey Text_Classification Text_Generation Tracking Transfer_Learning Transformer Unsupervised Video_Caption Video_Classification Video_Indexing Video_Prediction Video_Retrieval Visual_Relation VQA Weakly_Supervised Zero-Shot