TasksSotADatasetsPapersMethodsSubmitAbout
Papers With Code 2

A community resource for machine learning research: papers, code, benchmarks, and state-of-the-art results.

Explore

Notable BenchmarksAll SotADatasetsPapersMethods

Community

Submit ResultsAbout

Data sourced from the PWC Archive (CC-BY-SA 4.0). Built by the community, for the community.

Papers/Towards High-Resolution Salient Object Detection

Towards High-Resolution Salient Object Detection

Yi Zeng, Pingping Zhang, Jianming Zhang, Zhe Lin, Huchuan Lu

2019-08-20ICCV 2019 10Vocal Bursts Intensity PredictionSalient Object Detectionobject-detectionObject DetectionRGB Salient Object DetectionSaliency Detection
PaperPDFCode(official)

Abstract

Deep neural network based methods have made a significant breakthrough in salient object detection. However, they are typically limited to input images with low resolutions ($400\times400$ pixels or less). Little effort has been made to train deep neural networks to directly handle salient object detection in very high-resolution images. This paper pushes forward high-resolution saliency detection, and contributes a new dataset, named High-Resolution Salient Object Detection (HRSOD). To our best knowledge, HRSOD is the first high-resolution saliency detection dataset to date. As another contribution, we also propose a novel approach, which incorporates both global semantic information and local high-resolution details, to address this challenging task. More specifically, our approach consists of a Global Semantic Network (GSN), a Local Refinement Network (LRN) and a Global-Local Fusion Network (GLFN). GSN extracts the global semantic information based on down-sampled entire image. Guided by the results of GSN, LRN focuses on some local regions and progressively produces high-resolution predictions. GLFN is further proposed to enforce spatial consistency and boost performance. Experiments illustrate that our method outperforms existing state-of-the-art methods on high-resolution saliency datasets by a large margin, and achieves comparable or even better performance than them on widely-used saliency benchmarks. The HRSOD dataset is available at https://github.com/yi94code/HRSOD.

Results

TaskDatasetMetricValueModel
Object DetectionDAVIS-SF-measure0.889Zeng et al. (HRSOD)
Object DetectionDAVIS-SMAE0.026Zeng et al. (HRSOD)
Object DetectionDAVIS-SS-measure0.876Zeng et al. (HRSOD)
Object DetectionDAVIS-SmBA0.618Zeng et al. (HRSOD)
Object DetectionHRSODMAE0.03Zeng et al.
Object DetectionHRSODS-Measure0.892Zeng et al.
Object DetectionHRSODmBA0.693Zeng et al.
Object DetectionHRSODmax F-Measure0.892Zeng et al.
3DDAVIS-SF-measure0.889Zeng et al. (HRSOD)
3DDAVIS-SMAE0.026Zeng et al. (HRSOD)
3DDAVIS-SS-measure0.876Zeng et al. (HRSOD)
3DDAVIS-SmBA0.618Zeng et al. (HRSOD)
3DHRSODMAE0.03Zeng et al.
3DHRSODS-Measure0.892Zeng et al.
3DHRSODmBA0.693Zeng et al.
3DHRSODmax F-Measure0.892Zeng et al.
RGB Salient Object DetectionDAVIS-SF-measure0.889Zeng et al. (HRSOD)
RGB Salient Object DetectionDAVIS-SMAE0.026Zeng et al. (HRSOD)
RGB Salient Object DetectionDAVIS-SS-measure0.876Zeng et al. (HRSOD)
RGB Salient Object DetectionDAVIS-SmBA0.618Zeng et al. (HRSOD)
RGB Salient Object DetectionHRSODMAE0.03Zeng et al.
RGB Salient Object DetectionHRSODS-Measure0.892Zeng et al.
RGB Salient Object DetectionHRSODmBA0.693Zeng et al.
RGB Salient Object DetectionHRSODmax F-Measure0.892Zeng et al.
2D ClassificationDAVIS-SF-measure0.889Zeng et al. (HRSOD)
2D ClassificationDAVIS-SMAE0.026Zeng et al. (HRSOD)
2D ClassificationDAVIS-SS-measure0.876Zeng et al. (HRSOD)
2D ClassificationDAVIS-SmBA0.618Zeng et al. (HRSOD)
2D ClassificationHRSODMAE0.03Zeng et al.
2D ClassificationHRSODS-Measure0.892Zeng et al.
2D ClassificationHRSODmBA0.693Zeng et al.
2D ClassificationHRSODmax F-Measure0.892Zeng et al.
2D Object DetectionDAVIS-SF-measure0.889Zeng et al. (HRSOD)
2D Object DetectionDAVIS-SMAE0.026Zeng et al. (HRSOD)
2D Object DetectionDAVIS-SS-measure0.876Zeng et al. (HRSOD)
2D Object DetectionDAVIS-SmBA0.618Zeng et al. (HRSOD)
2D Object DetectionHRSODMAE0.03Zeng et al.
2D Object DetectionHRSODS-Measure0.892Zeng et al.
2D Object DetectionHRSODmBA0.693Zeng et al.
2D Object DetectionHRSODmax F-Measure0.892Zeng et al.
16kDAVIS-SF-measure0.889Zeng et al. (HRSOD)
16kDAVIS-SMAE0.026Zeng et al. (HRSOD)
16kDAVIS-SS-measure0.876Zeng et al. (HRSOD)
16kDAVIS-SmBA0.618Zeng et al. (HRSOD)
16kHRSODMAE0.03Zeng et al.
16kHRSODS-Measure0.892Zeng et al.
16kHRSODmBA0.693Zeng et al.
16kHRSODmax F-Measure0.892Zeng et al.

Related Papers

A Real-Time System for Egocentric Hand-Object Interaction Detection in Industrial Domains2025-07-17RS-TinyNet: Stage-wise Feature Fusion Network for Detecting Tiny Objects in Remote Sensing Images2025-07-17Decoupled PROB: Decoupled Query Initialization Tasks and Objectness-Class Learning for Open World Object Detection2025-07-17Dual LiDAR-Based Traffic Movement Count Estimation at a Signalized Intersection: Deployment, Data Collection, and Preliminary Analysis2025-07-17Vision-based Perception for Autonomous Vehicles in Obstacle Avoidance Scenarios2025-07-16Tomato Multi-Angle Multi-Pose Dataset for Fine-Grained Phenotyping2025-07-15ECORE: Energy-Conscious Optimized Routing for Deep Learning Models at the Edge2025-07-08Beyond One Shot, Beyond One Perspective: Cross-View and Long-Horizon Distillation for Better LiDAR Representations2025-07-07