Non-local Deep Features for Salient Object Detection

By Zhiming Luo, Akshaya Kumar Mishra, Andrew Achkar, Justin A. Eichel, Shaozi Li, Pierre-Marc Jodoin. Computer Vision and Pattern Recognition, 2017

557 citations recorded by the source corpus.

Subfields: Computer Vision and Pattern Recognition

View Paper: https://www.semanticscholar.org/paper/d7eccc1cd55e70802b017a2cadb9a778e47c7879

How researchers see this paper

The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.

In Computer Vision and Pattern Recognition

Citations in the corpus

Salient Object Detection With Pyramid Attention and Salient Edges (2019, methodology): “We compare the proposed PAGE-Net against 19 recent deep learning based alternatives: MDF [21], LEGS [34], DS [24], DCL [22], ELD [20], MC [57], RFCN [36], DHS [26], HEDS [14], KSR [38], NLDF [29], DLS [15], AMU [54], UCF [55], SRM [37], FSN [8], PAGR [56], RAS [7] and C2S [23].”
Uncertainty-aware Joint Salient Object and Camouflaged Object Detection (2021, unknown): “where ω is the edge-aware weight, which is defined as ω = 1+ 5 ∗ |(avg pool(Y )− Y )|, Lce is the cross-entropy loss, Liou is the boundary-IOU loss [33], which is defined as: Liou = 1− ω ∗ inter + 1 ω ∗ union− ω ∗ inter + 1 , (8)”
Reverse Attention for Salient Object Detection (2018, methodology): “Data augmentation is also implemented the same with [10,11] to reduce the over-fitting risk, which increased by 2 times through horizontal flipping.”
Salient Objects in Clutter: Bringing Salient Object Detection to the Foreground (2018, methodology): “To further improve the performance, UCF [50], DSS [17], NLDF [31], and AMU [49] utilize the FCN to improve the performance of SOD ( S sal in Table 4).”
Visual Saliency Transformer (2021, methodology): “Global contexts [21, 83, 56, 44, 37] and global contrast [75, 2, 8] have been proved crucial for saliency detection for a long time.”
Weakly-Supervised Salient Object Detection via Scribble Annotations (2020, methodology): “Models Metric DGRL UCF PiCANet R3Net NLDF MSNet CPD AFNet PFAN PAGRN BASNet SBF WSI WSS MNL MSW Ours [35] [53] [21] [5] [23] [40] [41] [8] [56] [54] [26] [48] [16] [34] [52] [47]”
A Simple Pooling-Based Design for Real-Time Salient Object Detection (2019, methodology): “When the edge branch is not incorporated, training only takes less than 6 hours on a training set of 5,000 images, which is quite faster than most of the previous methods [24, 43, 28, 44, 45, 9].”
Pyramid Dilated Deeper ConvLSTM for Video Salient Object Detection (2018, methodology): “We compared our model with 18 famous saliency methods, including 11 image salient object detection models: Amulet [51], SRM [36], UCF [52], DSS [16], MSR [23], NLDF [29], DCL [25], DHS [26], ELD [22], RFCN [35], KSR [37]; and”
Cascaded Partial Decoder for Fast and Accurate Salient Object Detection (2019, methodology): “In addition, we re-train three salient object detection models for shadow detection: NLDF [25], DSS [9], BMPM [41].”
BASNet: Boundary-Aware Salient Object Detection (2019, methodology): “Rather than using explicit boundary losses (NLDF+ [41], C2S [36]), we implicitly inject the goal of accurate boundary prediction in the hybrid loss, contemplating that it may help reduce spurious error from cross propagating the information learned on the boundary and the other regions on the image.”
Salient Object Detection in the Deep Learning Era: An In-Depth Survey (2019, background): “• NLDF [76] generates a local saliency map by fusing multi-level features and contrast features in a top-down manner, then integrates the local map with a global one yielded by the top layer to produce the ﬁnal prediction.”
Interactive Two-Stream Decoder for Accurate and Fast Saliency Detection (2020, methodology): “We compare our model with 16 existing saliency detection models, including 10 nearly real-time models, such as RFCN [32], Amulet [45], UCF [46], NLDF [24], CKT [18], BMP [44], PCA [22], PAGE [35], DSS [12], EGNet [48] and 6 real-time models, such as RA [3], AFNet [8], BASNet [26], CPD [37], PoolNet ”
Global Context-Aware Progressive Aggregation Network for Salient Object Detection (2020, background): “As pointed out in previous works (Luo et al. 2017; Zhang et al. 2017), due to the pyramid-like CNNs structure, low-level features usually have larger spatial size and more fine-grained details, while high-level features tend to gain more semantic knowledge and discard some meaningless or irrelevant ”
Multi-Scale Interactive Network for Salient Object Detection (2020, methodology): “…methods, including the SRM [32], PiCANet [20], DGRL [34], R3Net [6], CapSal [50], BAS-Net [27], BANet [30], ICNet [36], CPD [41], Amulet [51], NLDF [23], MSRNet [15], UCF [52], DSS [13], PAGR[53], RAS [4], C2SNet [17], HRS [46], PAGE [37], MLM-SNet [40], AFNet [9], SCRN [42], and EGNet [56].”
Pyramid Feature Attention Network for Saliency Detection (2019, methodology): “Luo et al. [24] combine the local and global information through a multi-resolution grid structure.”