Highly Efficient Salient Object Detection with 100K Parameters

Gao, Shanghua; Tan, Yongqiang; Cheng, Ming–Ming; Lu, Chin-Pi; Chen, Yunpeng; Yan, Shuicheng

doi:10.1007/978-3-030-58539-6_42

Cited by 156 publications

(66 citation statements)

References 67 publications

Supporting

Mentioning

Contrasting

Unclassified

Order By: Relevance

“…To verify the feasibility and advantages of our method, we compared CODCEF with 10 previous methods, including FPN [ 34 ], BASNet [ 26 ], PFANet [ 22 ], CPD [ 25 ], ANet [ 18 ], CSNet [ 51 ], SINet [ 20 ], RankNet [ 19 ], and R-MGL [ 50 ]. Among those, MGL, SINet, and RankNet are the state-of-the-art methods for COD.…”

Section: Discussionmentioning

confidence: 99%

Cascade and Fusion: A Deep Learning Approach for Camouflaged Object Sensing

Huang

Zhang

et al. 2021

Sensors

View full text Add to dashboard Cite

The demand for the sensor-based detection of camouflage objects widely exists in biological research, remote sensing, and military applications. However, the performance of traditional object detection algorithms is limited, as they are incapable of extracting informative parts from low signal-to-noise ratio features. To address this problem, we propose Camouflaged Object Detection with Cascade and Feedback Fusion (CODCEF), a deep learning framework based on an RGB optical sensor that leverages a cascaded structure with Feedback Partial Decoders (FPD) instead of a traditional encoder–decoder structure. Through a selective fusion strategy and feedback loop, FPD reduces the loss of information and the interference of noises in the process of feature interweaving. Furthermore, we introduce Pixel Perception Fusion (PPF) loss, which aims to pay more attention to local pixels that might become the edges of an object. Experimental results on an edge device show that CODCEF achieved competitive results compared with 10 state-of-the-art methods.

show abstract

Section: Discussionmentioning

confidence: 99%

Cascade and Fusion: A Deep Learning Approach for Camouflaged Object Sensing

Huang

Zhang

et al. 2021

Sensors

View full text Add to dashboard Cite

show abstract

“…We compare our detection model with recent 15 state-of-the-art methods, including AFNet, 25 CPD, 42 PAGE, 15 BANet, 26 PoolNet, 43 BASNet, 29 SCRN, 14 EGNet, 13 F3Net, 23 GCPA, 24 MINet, 22 T A B L E 2 Ablation analysis of the proposed network on five data sets ITSD, 12 CSF, 44 GateNet, 45 and LDF. 27 The saliency maps of compared methods are provided by the corresponding authors.…”

Section: Comparison With State-of-the-artsmentioning

confidence: 99%

Dual‐branch mutual assistance network for salient object detection

Yao

Wang

2021

Int J Intell Syst

View full text Add to dashboard Cite

To maintain the boundaries of salient objects in the detection results, some methods start to apply additional edge labels to train their networks to learn detailed information. These methods have made gratifying progress. However, since the quality of the saliency maps will be affected by boundary features, it is still worth exploring how to extract effective boundary features and fuse them with semantic features. In this

show abstract

“…Komatsu et al [54] used octave convolution to predict depth maps. Gao et al [55] proposed a novel multi-scale octave convolution to achieve high-speed saliency maps generation. The above researches pay more attention to the advantages of the fast speed and the low resource occupancy of octave convolution, and pay more attention to its multi-scale characteristics, ignoring the research on its noise-resilient performance.…”

Section: A Octave Convolutionmentioning

confidence: 99%

Object Detection Based on Global-Local Saliency Constraint in Aerial Images

Luo

Hong

et al. 2020

Remote Sensing

View full text Add to dashboard Cite

Different from object detection in natural image, optical remote sensing object detection is a challenging task, due to the diverse meteorological conditions, complex background, varied orientations, scale variations, etc. In this paper, to address this issue, we propose a novel object detection network (the global-local saliency constraint network, GLS-Net) that can make full use of the global semantic information and achieve more accurate oriented bounding boxes. More precisely, to improve the quality of the region proposals and bounding boxes, we first propose a saliency pyramid which combines a saliency algorithm with a feature pyramid network, to reduce the impact of complex background. Based on the saliency pyramid, we then propose a global attention module branch to enhance the semantic connection between the target and the global scenario. A fast feature fusion strategy is also used to combine the local object information based on the saliency pyramid with the global semantic information optimized by the attention mechanism. Finally, we use an angle-sensitive intersection over union (IoU) method to obtain a more accurate five-parameter representation of the oriented bounding boxes. Experiments with a publicly available object detection dataset for aerial images demonstrate that the proposed GLS-Net achieves a state-of-the-art detection performance.

show abstract

Highly Efficient Salient Object Detection with 100K Parameters

Cited by 156 publications

References 67 publications

Cascade and Fusion: A Deep Learning Approach for Camouflaged Object Sensing

Cascade and Fusion: A Deep Learning Approach for Camouflaged Object Sensing

Dual‐branch mutual assistance network for salient object detection

Object Detection Based on Global-Local Saliency Constraint in Aerial Images

Contact Info

Product

Resources

About