A Deep Learning Based Fast Image Saliency Detection Algorithm
This work addresses the need for efficient saliency detection in computer vision, offering a faster alternative to existing deep learning methods, though it is incremental in nature.
The authors tackled the problem of fast object saliency detection in images by proposing a deep learning method that uses gradient descent and superpixel refinement, achieving results comparable to slower deep learning methods on benchmarks like Pascal VOC 2012 and MSRA10k.
In this paper, we propose a fast deep learning method for object saliency detection using convolutional neural networks. In our approach, we use a gradient descent method to iteratively modify the input images based on the pixel-wise gradients to reduce a pre-defined cost function, which is defined to measure the class-specific objectness and clamp the class-irrelevant outputs to maintain image background. The pixel-wise gradients can be efficiently computed using the back-propagation algorithm. We further apply SLIC superpixels and LAB color based low level saliency features to smooth and refine the gradients. Our methods are quite computationally efficient, much faster than other deep learning based saliency methods. Experimental results on two benchmark tasks, namely Pascal VOC 2012 and MSRA10k, have shown that our proposed methods can generate high-quality salience maps, at least comparable with many slow and complicated deep learning methods. Comparing with the pure low-level methods, our approach excels in handling many difficult images, which contain complex background, highly-variable salient objects, multiple objects, and/or very small salient objects.