LCNN: Low-level Feature Embedded CNN for Salient Object Detection
This work addresses the problem of accurately detecting salient objects in images for computer vision applications, representing an incremental improvement by combining low-level features with CNN-based high-level features.
The authors tackled salient object detection in complex images by proposing LCNN, a deep neural network framework that embeds low-level features to capture contrast and spatial information, achieving superior performance over most low-level oriented state-of-the-art methods on benchmarks like MSRA-5000, PASCAL-S, and ECCSD in terms of P-R curves, F-measure, and mean absolute errors.
In this paper, we propose a novel deep neural network framework embedded with low-level features (LCNN) for salient object detection in complex images. We utilise the advantage of convolutional neural networks to automatically learn the high-level features that capture the structured information and semantic context in the image. In order to better adapt a CNN model into the saliency task, we redesign the network architecture based on the small-scale datasets. Several low-level features are extracted, which can effectively capture contrast and spatial information in the salient regions, and incorporated to compensate with the learned high-level features at the output of the last fully connected layer. The concatenated feature vector is further fed into a hinge-loss SVM detector in a joint discriminative learning manner and the final saliency score of each region within the bounding box is obtained by the linear combination of the detector's weights. Experiments on three challenging benchmark (MSRA-5000, PASCAL-S, ECCSD) demonstrate our algorithm to be effective and superior than most low-level oriented state-of-the-arts in terms of P-R curves, F-measure and mean absolute errors.