Label Decoupling Framework for Salient Object Detection
Key Lab of Intell. Info. Process., Inst. of Comput. Tech., CAS(中国科学院计算技术研究所智能信息处理重点实验室);University of Chinese Academy of Sciences(中国科学院大学);Peng Cheng Laboratory(鹏城实验室);Kingsoft Cloud(金山云);Noah’s Ark Lab, Huawei Technologies(华为技术有限公司诺亚方舟实验室)
Jun Wei, Shuhui Wang, Zhe Wu, Chi Su, Qingming Huang, Qi Tian
To get more accurate saliency maps, recent methods mainly focus on aggregating multi-level features from fully convolutional network (FCN) and introducing edge information as auxiliary supervision. Though remarkable progress has been achieved, we observe that the closer the pixel is to the edge, the more difficult it is to be predicted, because edge pixels have a very imbalance distribution. To address this problem, we propose a label decoupling framework (LDF) which consists of a label decoupling (LD) procedure and a feature interaction network (FIN). LD explicitly decomposes the original saliency map into body map and detail map, where body map concentrates on center areas of objects and detail map focuses on regions around edges. Detail map works better because it involves much more pixels than traditional edge supervision. Different from saliency map, body map discards edge pixels and only pays attention to center areas. This successfully avoids the distraction from edge pixels during training. Therefore, we employ two branches in FIN to deal with body map and detail map respectively. Feature interaction (FI) is designed to fuse the two complementary branches to predict the saliency map, which is then used to refine the two branches again. This iterative refinement is helpful for learning better representations and more precise saliency maps. Comprehensive experiments on six benchmark datasets demonstrate that LDF outperforms state-of-the-art approaches on different evaluation metrics.
Non-Salient Region Object Mining for Weakly Supervised Semantic Segmentation
Nanjing University of Science and Technology(南京理工大学);Mohamed bin Zayed University of AI(穆罕默德·本·扎耶德人工智能大学);University of Electronic Science and Technology of China(电子科技大学);University of Adelaide(阿德莱德大学);University of Technology Sydney(悉尼科技大学)
Semi-Supervised Video Salient Object Detection Using Pseudo-Labels
Sun Yat-sen University(中山大学);DarkMatter AI Research(暗物质人工智能研究院);Shenzhen Research Institute of Big Data, the Chinese University of Hong Kong (Shenzhen)(香港中文大学(深圳)深圳大数据研究院);Megvii Technology(旷视科技)
A Weakly Supervised Learning Framework for Salient Object Detection via Hybrid Labels
Beijing Jiaotong University(北京交通大学);City University of Hong Kong(香港城市大学);Ningbo University(宁波大学);City University of Hong Kong Shenzhen Research Institute(香港城市大学深圳研究院)
全监督显著性目标检测(SOD)方法已经取得了很大的进展,但这类方法往往依赖于大量的像素级标注,耗时耗力。在本文中,我们专注于一个新的弱监督SOD任务下的混合标签,其中的监督标签包括大量的粗标签由传统的无监督方法和少量的真正的标签。为了解决这个任务中的标签噪声和数量不平衡问题,我们设计了一个新的管道框架,其中包含三个复杂的训练策略。在模型框架上,将任务解耦为标签细化子任务和显著目标检测子任务,这两个子任务相互协作,交替进行训练。具体来说,R-Net被设计为一个双流编码器-解码器模型,配备了Blender with Guidance and Aggregation Mechanisms(BGA),旨在纠正粗糙标签以获得更可靠的伪标签,而S-Net是一个由当前R-Net生成的伪标签监督的可替换SOD网络。请注意,我们只需要使用训练好的S-Net进行测试。此外,为了保证网络训练的有效性和效率,设计了交替迭代机制、分组增量机制和可信性验证机制三种训练策略。在五个SOD基准上的实验表明,我们的方法在定性和定量上都比弱监督/无监督方法具有竞争力的性能。
Northwestern Polytechnical University(西北工业大学);Australian National University(澳大利亚国立大学);CSIRO Australia(澳大利亚联邦科学与工业研究组织);Inception Institute of Artificial Intelligence(起源人工智能研究院)
Weakly-Supervised Salient Object Detection via Scribble Annotations
Australian National University(澳大利亚国立大学);ACRV(澳大利亚机器人视觉中心);Data61(数据61);University of Technology Sydney(悉尼科技大学);Northwestern Polytechnical University(西北工业大学)
MFNet: Multi-filter Directive Network for Weakly Supervised Salient Object Detection
Dalian University of Technology(大连理工大学);Pengcheng Lab(鹏城实验室);Key Lab for Ubiquitous Network and Service Software of Liaoning Province(辽宁省泛在网络与服务软件重点实验室)
Scribble-based Boundary-aware Network for Weakly Supervised Salient Object Detection in Remote Sensing Images
University of Electronic Science and Technology of China(电子科技大学);Inception Institute of Artificial Intelligence (IIAI)(人工智能初始研究所);Mohamed bin Zayed University of Artificial Intelligence(穆罕默德·本·扎耶德人工智能大学)
Texture-guided Saliency Distilling for Unsupervised Salient Object Detection
Sun Yat-sen University(中山大学);Guangdong Province Key Laboratory of Information Security Technology(广东省信息安全技术重点实验室);Key Laboratory of Machine Intelligence and Advanced Computing, Ministry of Education(教育部机器智能与先进计算重点实验室)
Guidance and Teaching Network for Video Salient Object Detection
Wuhan University(武汉大学);Jiangxi University of Finance and Economics(江西财经大学)
现有的视频显著目标检测(VSOD)方法由于难以挖掘时空线索,在理解复杂和噪声场景时受到限制,往往无法推断出显著目标。为了减轻这些缺点,我们提出了一个简单而有效的架构,称为指导和教学网络(GTNet),独立地隐藏有效的空间和时间线索与隐式指导和明确的教学功能和决策水平,分别。具体来说,我们(a)引入一个时间调制器来隐式地将来自运动的特征桥接到外观分支中,这能够协同地融合跨模态特征,以及(b)利用运动引导的掩码来在特征聚合期间传播显式提示。这种新的学习策略通过解耦复杂的时空线索和映射信息线索在不同的方式取得了令人满意的结果。在三个具有挑战性的基准测试上进行的大量实验表明,该方法可以在单个TITAN Xp GPU上以约28 fps的速度运行,并与14个尖端基线相比具有竞争力。
Cascaded Interaction with Eroded Deep Supervision for Salient Object Detection
Institute of Space Science and Applied Technology, Harbin Institute of Technology, Shenzhen(哈尔滨工业大学(深圳)空间科学与应用技术研究院);School of Mechanical Engineering and Automation, Harbin Institute of Technology, Shenzhen(哈尔滨工业大学(深圳)机电工程与自动化学院)
Pseudo-Label Quality Decoupling and Correction for Semi-Supervised Instance Segmentation
Key Laboratory of Multimedia Trusted Perception and Efficient Computing, Ministry of Education of China, Xiamen University, China(中国教育部多媒体可信感知与高效计算重点实验室,厦门大学);Tencent Youtu Lab(腾讯云视频实验室)
Synthetic Data Supervised Salient Object Detection
Beihang University(北京航空航天大学);Harbin Institute of Technology(哈尔滨工业大学);China University of Petroleum (East China)(中国石油大学(华东));Peng Cheng Laboratory(鹏城实验室);Western University(韦仕敦大学)
Evaluating Salient Object Detection in Natural Images with Multiple Objects having Multi-level Saliency
Zalando Research(Zalando研究院);Indian Institute of Technology, Kharagpur(印度理工学院卡拉格普尔分校);National University of Singapore(新加坡国立大学);École Polytechnique Fédérale de Lausanne(洛桑联邦理工学院)
Pixel is All You Need: Adversarial Trajectory-Ensemble Active Learning for Salient Object Detection
State Key Laboratory of Virtual Reality Technology and Systems, Beihang University(北京航空航天大学虚拟现实技术与系统国家重点实验室);School of Transportation Science and Engineering, Beihang University(北京航空航天大学交通科学与工程学院);Harbin Institute of Technology (Shenzhen)(哈尔滨工业大学(深圳));SenseTime Research(商汤科技研究院);China University of Petroleum (East China)(中国石油大学(华东));Peng Cheng Laboratory(鹏城实验室);Case Western Reserve University(凯斯西储大学)
Rethinking Detecting Salient and Camouflaged Objects in Unconstrained Scenes
School of Software Engineering, Huazhong University of Science and Technology(华中科技大学软件工程学院);School of Computer Science and Engineering, The Chinese University of Hong Kong(香港中文大学计算机科学与工程学院);School of Computer Science and Technology, Hainan University(海南大学计算机科学与技术学院)
Distribution-Specific Learning for Joint Salient and Camouflaged Object Detection
School of Computing and Information Technology, Great Bay University(计算与信息学院,大湾大学);Computer Vision and Pattern Recognition Laboratory, School of Engineering Science, Lappeenranta-Lahti University of Technology LUT(计算机视觉与模式识别实验室,工程科学学院,拉佩兰塔-拉赫蒂技术大学);School of Computer Science and Software Engineering, Shenzhen University(计算机科学与软件工程学院,深圳大学);School of Software Engineering, Xi’an Jiaotong University(软件工程学院,西安交通大学);School of Electrical and Information Engineering, Tianjin University(电气与信息工程学院,天津大学)