Saliency detection by multi-context deep learning

By Rui Zhao, Wanli Ouyang, Hongsheng Li, Xiaogang Wang. 2015

950 citations recorded by the source corpus.

Subfields: Computer Vision and Pattern Recognition

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

Recent advances in convolutional neural networks (2015, background): “Similar to [167], [168], the CNN model used in”
Res2Net: A New Multi-Scale Backbone Architecture (2019, background): “Later, multi-context deep learning [53] and multi-level convolutional features [49] are proposed for improving salient object detection.”
Learning to Compose Dynamic Tree Structures for Visual Contexts (2018, background): “For example, state-of-the-art CNN architectures capture the context by convolutions of various receptive fields and encode it into multi-scale feature map pyramid [8, 27, 60].”
AGIL: Learning Attention from Human for Visuomotor Tasks (2018, background): “In recent years, this approach has made tremendous progress due to large benchmark datasets and deep neural networks [19, 5, 25, 22, 42, 21].”
Dense and Low-Rank Gaussian CRFs Using Deep Embeddings (2017, methodology): “Our baselines for the saliency estimation task include (a) the Local Estimation and Global Search (LEGS) framework [36], (b) the multi-context network [39], (c) the multiscale deep features network [21], (d) the deep contrast learning networks [22] which proposes a network structure that better expl”
Structure-Measure: A New Way to Evaluate Foreground Maps (2017, neutral): “, 2016), MDF (Li &Yu, 2015), andMC (Zhao et al., 2015).”
Explainable AI: A Review of Machine Learning Interpretability Methods (2020, methodology): “Furthermore, in [26], a task-specific pre-training scheme was designed in order to make the multi-context modeling suited for saliency detection.”
Puzzle Mix: Exploiting Saliency and Local Statistics for Optimal Mixup (2020, methodology): “Subsequently, other methods were introduced to obtain more precise saliency (Zhao et al., 2015; Wang et al., 2015).”
Amulet: Aggregating Multi-level Convolutional Features for Salient Object Detection (2017, methodology): “We compare our algorithm with other 11 state-of-the-art ones including 7 deep learning based algorithms (DCL [22], DHS [27], DS [24], ELD [20], LEGS [41], MDF [50], RFCN [44]) and 4 conventional algorithms (BL[39], BSCA [32], DRFI [19], DSR [23]).”
Learning to Detect Salient Objects with Image-Level Supervision (2017, methodology): “Early works [46, 57, 26, 4] use DNNs in a patch-by-patch scanning manner, leading to numerous redundant computations.”
Extraction of skin lesions from non-dermoscopic images for surgical excision of melanoma (2016, background): “In some applications, combination of local texture and global context (local view and a broader look at the same spot) could significantly improve performance of segmentation, as it is used in [25] and [27].”
Deep Visual Attention Prediction (2017, background): “2) Multi-stream Network: Examples of this form of network include [45], [47], [31], [1].”
CNNs-Based RGB-D Saliency Detection via Cross-View Transfer and Multiview Fusion (2018, methodology): “Recently, CNNs have also shown their effectiveness in saliency detection [30]–[36].”
Global Context-Aware Progressive Aggregation Network for Salient Object Detection (2020, methodology): “Inspired by image semantic segmentation, Zhao et al. (Zhao et al. 2015) proposed a fully connected CNN to integrate local and global features to predict the saliency map.”
RGBD Salient Object Detection via Deep Fusion (2016, methodology): “Finally, a Laplacian propagation is performed on the resulted probabilities to extract the ﬁnal spatially consistent saliency map. some other works to extract hierarchical feature representations for detecting salient regions [33], [34], [35], [36], [37], [38].”
Visual Tracking with Fully Convolutional Networks (2015, background): “, image classification [16, 27], object detection [8, 23, 22], and saliency detection [33, 39].”
DeepSaliency: Multi-Task Deep Neural Network Model for Salient Object Detection (2015, background): “Recent data-driven saliency models [33], [34], [16], [35] aim to directly capture the semantic properties of salient objects in terms of supervised learning from a collection of training data with saliency annotations.”