Saliency detection using a deep conditional random field network

Qiu, Wenliang; Gao, Xinbo; Han, Bing

doi:10.1016/j.patcog.2020.107266

Cited by 10 publications

(2 citation statements)

References 12 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…In addition, Zheng et al [25] extended the fully connected CRF as a recurrent neural network (RNN) for object segmentation. Qiu et al [26] also integrated the CRF into a CNN to segment saliency objects. Although these methods allow us to jointly train the CNN and the CRF model end-to-end, the CRF still acts as postprocessing in the pipeline.…”

Section: Conditional Random Fieldmentioning

confidence: 99%

Continuous Conditional Random Field Convolution for Point Cloud Segmentation

Yang,

Davoine,

Wang

et al. 2021

Preprint

View full text Add to dashboard Cite

Point cloud segmentation is the foundation of 3D environmental perception for modern intelligent systems. To solve this problem and image segmentation, conditional random fields (CRFs) are usually formulated as discrete models in label space to encourage label consistency, which is actually a kind of postprocessing. In this paper, we reconsider the CRF in feature space for point cloud segmentation because it can capture the structure of features well to improve the representation ability of features rather than simply smoothing. Therefore, we first model the point cloud features with a continuous quadratic energy model and formulate its solution process as a message-passing graph convolution, by which it can be easily integrated into a deep network. We theoretically demonstrate that the message passing in the graph convolution is equivalent to the mean-field approximation of a continuous CRF model. Furthermore, we build an encoder-decoder network based on the proposed continuous CRF graph convolution (CRFConv), in which the CRFConv embedded in the decoding layers can restore the details of high-level features that were lost in the encoding stage to enhance the location ability of the network, thereby benefiting segmentation. Analogous to the CRFConv, we show that the classical discrete CRF can also work collaboratively with the proposed network via another graph convolution to further improve the segmentation results. Experiments on various point cloud benchmarks demonstrate the effectiveness and robustness of the proposed method. Compared with the state-of-the-art methods, the proposed method can also achieve competitive segmentation performance.

show abstract

Section: Conditional Random Fieldmentioning

confidence: 99%

Continuous Conditional Random Field Convolution for Point Cloud Segmentation

Yang,

Davoine,

Wang

et al. 2021

Preprint

View full text Add to dashboard Cite

show abstract

“…The proposed model requires less computation budgets while obtaining better wholeness and uniformity of the segmented salient object. The proposal of the Deep Conditional Random Field network (DCRF) [34] takes into account both the depth features and the neighbor information. DCRF is a good combination of low-level internal context and high-level semantic information, keeping object boundaries clear and suppressing background noise.…”

Section: Feature Engineering and Target Detectionmentioning

confidence: 99%

Foldover Features for Dynamic Object Behaviour Description in Microscopic Videos

Kulwa

et al. 2020

IEEE Access

View full text Add to dashboard Cite

A behavior description helps analyze tiny objects, similar objects, objects with weak visual information, and objects with similar visual information. It plays a fundamental role in the identification and classification of dynamic objects in microscopic videos. To this end, we propose foldover features to describe the behavior of dynamic objects. Foldover is defined as: Each frame of an object's motion is superimposed on the same spatial plane in the spacetime order of the motion, the result of the superposition is the foldover of the object's motion. Foldover of an object contains temporal information, spatial information, behavior features and static features. Therefore, the features extracted based on the foldover of the object are the foldover features. In this work, we first generate foldover for each object in microscopic videos in X, Y and Z directions, respectively. Then, we extract foldover features from the X, Y and Z directions with statistical methods, respectively. The core content of this paper is to construct the foldovers and extract the foldover features. Through these two steps, the temporal information, spatial information, behavior features and static features of the object are enhanced and included in the foldover features. Furthermore, the description of the behavior of dynamic objects by the foldover features is strengthened. Finally, we use four different classifiers to test the effectiveness of the proposed foldover features. In the experiment, we use a microscopic sperm video dataset to evaluate the proposed foldover features, including three types of 1374 sperms, and obtain the highest classification accuracy of 96.5%.

show abstract

Depth scale balance saliency detection with connective feature pyramid and edge guidance

Tan

2021

Appl Intell

View full text Add to dashboard Cite

Saliency detection using a deep conditional random field network

Cited by 10 publications

References 12 publications

Continuous Conditional Random Field Convolution for Point Cloud Segmentation

Continuous Conditional Random Field Convolution for Point Cloud Segmentation

Foldover Features for Dynamic Object Behaviour Description in Microscopic Videos

Depth scale balance saliency detection with connective feature pyramid and edge guidance

Contact Info

Product

Resources

About