Saliency Enhancement using Superpixel Similarity

• URL: http://arxiv.org/abs/2112.00665v1
• Date: Wed, 1 Dec 2021 17:22:54 GMT
• Title: Saliency Enhancement using Superpixel Similarity
• Authors: Leonardo de Melo Joao, Alexandre Xavier Falcao
• Abstract summary: Saliency Object Detection (SOD) has several applications in image analysis. Deep-learning-based SOD methods are among the most effective, but they may miss foreground parts with similar colors. We introduce a post-processing method, named textitSaliency Enhancement over Superpixel Similarity (SESS) We demonstrate that SESS can consistently and considerably improve the results of three deep-learning-based SOD methods on five image datasets.
• Score: 77.34726150561087
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: Saliency Object Detection (SOD) has several applications in image analysis. Deep-learning-based SOD methods are among the most effective, but they may miss foreground parts with similar colors. To circumvent the problem, we introduce a post-processing method, named \textit{Saliency Enhancement over Superpixel Similarity} (SESS), which executes two operations alternately for saliency completion: object-based superpixel segmentation and superpixel-based saliency estimation. SESS uses an input saliency map to estimate seeds for superpixel delineation and define superpixel queries in foreground and background. A new saliency map results from color similarities between queries and superpixels. The process repeats for a given number of iterations, such that all generated saliency maps are combined into a single one by cellular automata. Finally, post-processed and initial maps are merged using their average values per superpixel. We demonstrate that SESS can consistently and considerably improve the results of three deep-learning-based SOD methods on five image datasets.

Related papers

• Superpixels algorithms through network community detection [0.0]
  Community detection is a powerful tool from complex networks analysis that finds applications in various research areas. Superpixels aim at representing the image at a smaller level while preserving as much as possible original information. We study the efficiency of superpixels computed by state-of-the-art community detection algorithms on a 4-connected pixel graph.
  arXiv  Detail & Related papers  (2023-08-27T13:13:28Z)
• Efficient Multiscale Object-based Superpixel Framework [62.48475585798724]
  We propose a novel superpixel framework, named Superpixels through Iterative CLEarcutting (SICLE) SICLE exploits object information being able to generate a multiscale segmentation on-the-fly. It generalizes recent superpixel methods, surpassing them and other state-of-the-art approaches in efficiency and effectiveness according to multiple delineation metrics.
  arXiv  Detail & Related papers  (2022-04-07T15:59:38Z)
• Generating Superpixels for High-resolution Images with Decoupled Patch Calibration [82.21559299694555]
  Patch Networks (PCNet) is designed to efficiently and accurately implement high-resolution superpixel segmentation. DPC takes a local patch from the high-resolution images and dynamically generates a binary mask to impose the network to focus on region boundaries. In particular, DPC takes a local patch from the high-resolution images and dynamically generates a binary mask to impose the network to focus on region boundaries.
  arXiv  Detail & Related papers  (2021-08-19T10:33:05Z)
• HERS Superpixels: Deep Affinity Learning for Hierarchical Entropy Rate Segmentation [0.0]
  We propose a two-stage graph-based framework for superpixel segmentation. In the first stage, we introduce an efficient Deep Affinity Learning network that learns pairwise pixel affinities. In the second stage, we propose a highly efficient superpixel method called Hierarchical Entropy Rate (HERS)
  arXiv  Detail & Related papers  (2021-06-07T16:20:04Z)
• Deep Superpixel Cut for Unsupervised Image Segmentation [0.9281671380673306]
  We propose a deep unsupervised method for image segmentation, which contains the following two stages. First, a Superpixelwise Autoencoder (SuperAE) is designed to learn the deep embedding and reconstruct a smoothed image, then the smoothed image is passed to generate superpixels. Second, we present a novel clustering algorithm called Deep Superpixel Cut (DSC), which measures the deep similarity between superpixels and formulates image segmentation as a soft partitioning problem.
  arXiv  Detail & Related papers  (2021-03-10T13:07:41Z)
• Implicit Integration of Superpixel Segmentation into Fully Convolutional Networks [11.696069523681178]
  We propose a way to implicitly integrate a superpixel scheme into CNNs. Our proposed method hierarchically groups pixels at downsampling layers and generates superpixels. We evaluate our method on several tasks such as semantic segmentation, superpixel segmentation, and monocular depth estimation.
  arXiv  Detail & Related papers  (2021-03-05T02:20:26Z)
• Propagate Yourself: Exploring Pixel-Level Consistency for Unsupervised Visual Representation Learning [60.75687261314962]
  We introduce pixel-level pretext tasks for learning dense feature representations. A pixel-to-propagation consistency task produces better results than state-of-the-art approaches. Results demonstrate the strong potential of defining pretext tasks at the pixel level.
  arXiv  Detail & Related papers  (2020-11-19T18:59:45Z)
• Learning RGB-D Feature Embeddings for Unseen Object Instance Segmentation [67.88276573341734]
  We propose a new method for unseen object instance segmentation by learning RGB-D feature embeddings from synthetic data. A metric learning loss function is utilized to learn to produce pixel-wise feature embeddings. We further improve the segmentation accuracy with a new two-stage clustering algorithm.
  arXiv  Detail & Related papers  (2020-07-30T00:23:07Z)
• Superpixel Segmentation using Dynamic and Iterative Spanning Forest [0.0]
  We present Dynamic ISF (DISF) -- a method based on the following steps. As compared to other seed-based superpixel methods, DISF is more likely to find relevant seeds. It also introduces dynamic arc-weight estimation in the ISF framework for more effective superpixel delineation.
  arXiv  Detail & Related papers  (2020-07-08T16:46:58Z)
• ITSELF: Iterative Saliency Estimation fLexible Framework [68.8204255655161]
  Saliency object detection estimates the objects that most stand out in an image. We propose a superpixel-based ITerative Saliency Estimation fLexible Framework (ITSELF) that allows any user-defined assumptions to be added to the model. We compare ITSELF to two state-of-the-art saliency estimators on five metrics and six datasets.
  arXiv  Detail & Related papers  (2020-06-30T16:51:31Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.