Comprehensive Saliency Fusion for Object Co-segmentation

• URL: http://arxiv.org/abs/2201.12828v1
• Date: Sun, 30 Jan 2022 14:22:58 GMT
• Title: Comprehensive Saliency Fusion for Object Co-segmentation
• Authors: Harshit Singh Chhabra, Koteswar Rao Jerripothula
• Abstract summary: Saliency fusion has been one of the promising ways to carry out object co-segmentation. This paper revisits the problem and proposes fusing saliency maps of both the same image and different images. It also leverages advances in deep learning for the saliency extraction and correspondence processes.
• Score: 3.908842679355254
• License: http://creativecommons.org/licenses/by-nc-nd/4.0/
• Abstract: Object co-segmentation has drawn significant attention in recent years, thanks to its clarity on the expected foreground, the shared object in a group of images. Saliency fusion has been one of the promising ways to carry it out. However, prior works either fuse saliency maps of the same image or saliency maps of different images to extract the expected foregrounds. Also, they rely on hand-crafted saliency extraction and correspondence processes in most cases. This paper revisits the problem and proposes fusing saliency maps of both the same image and different images. It also leverages advances in deep learning for the saliency extraction and correspondence processes. Hence, we call it comprehensive saliency fusion. Our experiments reveal that our approach achieves much-improved object co-segmentation results compared to prior works on important benchmark datasets such as iCoseg, MSRC, and Internet Images.

Related papers

• From Latent to Engine Manifolds: Analyzing ImageBind's Multimodal Embedding Space [0.0]
  We propose a simplistic embedding fusion workflow that aims to capture the overlapping information of image/text pairs. After storing such fused embeddings in a vector database, we experiment with dimensionality reduction and provide empirical evidence to convey the semantic quality of the joint embeddings.
  arXiv  Detail & Related papers  (2024-08-30T17:16:33Z)
• TSJNet: A Multi-modality Target and Semantic Awareness Joint-driven Image Fusion Network [2.7387720378113554]
  We introduce a target and semantic awareness-driven fusion network called TSJNet. It comprises fusion, detection, and segmentationworks arranged in a series structure. It can generate visually pleasing fused results, achieving an average increase of 2.84% and 7.47% in object detection and segmentation mAP @0.5 and mIoU, respectively.
  arXiv  Detail & Related papers  (2024-02-02T08:37:38Z)
• Image Fusion in Remote Sensing: An Overview and Meta Analysis [12.500746892824338]
  Image fusion in Remote Sensing (RS) has been a consistent demand due to its ability to turn raw images of different resolutions, sources, and modalities into accurate, complete, and coherent images. Yet, image fusion solutions are highly disparate to various remote sensing problems and thus are often narrowly defined in existing reviews as topical applications. This paper comprehensively surveying relevant works with a simple taxonomy: 1) many-to-one image fusion; 2) many-to-many image fusion.
  arXiv  Detail & Related papers  (2024-01-16T21:21:17Z)
• An Interactively Reinforced Paradigm for Joint Infrared-Visible Image Fusion and Saliency Object Detection [59.02821429555375]
  This research focuses on the discovery and localization of hidden objects in the wild and serves unmanned systems. Through empirical analysis, infrared and visible image fusion (IVIF) enables hard-to-find objects apparent. multimodal salient object detection (SOD) accurately delineates the precise spatial location of objects within the picture.
  arXiv  Detail & Related papers  (2023-05-17T06:48:35Z)
• SemIE: Semantically-aware Image Extrapolation [1.5588799679661636]
  We propose a semantically-aware novel paradigm to perform image extrapolation. The proposed approach focuses on (i) extending the already present objects but also on (ii) adding new objects in the extended region based on the context. We conduct experiments on Cityscapes and ADE20K-bedroom datasets and show that our method outperforms all baselines in terms of FID, and similarity in object co-occurrence statistics.
  arXiv  Detail & Related papers  (2021-08-31T09:31:27Z)
• NeuralFusion: Online Depth Fusion in Latent Space [77.59420353185355]
  We present a novel online depth map fusion approach that learns depth map aggregation in a latent feature space. Our approach is real-time capable, handles high noise levels, and is particularly able to deal with gross outliers common for photometric stereo-based depth maps.
  arXiv  Detail & Related papers  (2020-11-30T13:50:59Z)
• Mining Cross-Image Semantics for Weakly Supervised Semantic Segmentation [128.03739769844736]
  Two neural co-attentions are incorporated into the classifier to capture cross-image semantic similarities and differences. In addition to boosting object pattern learning, the co-attention can leverage context from other related images to improve localization map inference. Our algorithm sets new state-of-the-arts on all these settings, demonstrating well its efficacy and generalizability.
  arXiv  Detail & Related papers  (2020-07-03T21:53:46Z)
• Gradient-Induced Co-Saliency Detection [81.54194063218216]
  Co-saliency detection (Co-SOD) aims to segment the common salient foreground in a group of relevant images. In this paper, inspired by human behavior, we propose a gradient-induced co-saliency detection method.
  arXiv  Detail & Related papers  (2020-04-28T08:40:55Z)
• Unsupervised Learning of Landmarks based on Inter-Intra Subject Consistencies [72.67344725725961]
  We present a novel unsupervised learning approach to image landmark discovery by incorporating the inter-subject landmark consistencies on facial images. This is achieved via an inter-subject mapping module that transforms original subject landmarks based on an auxiliary subject-related structure. To recover from the transformed images back to the original subject, the landmark detector is forced to learn spatial locations that contain the consistent semantic meanings both for the paired intra-subject images and between the paired inter-subject images.
  arXiv  Detail & Related papers  (2020-04-16T20:38:16Z)
• Image Co-skeletonization via Co-segmentation [102.59781674888657]
  We propose a new joint processing topic: image co-skeletonization. Object skeletonization in a single natural image is a challenging problem because there is hardly any prior knowledge about the object. We propose a coupled framework for co-skeletonization and co-segmentation tasks so that they are well informed by each other.
  arXiv  Detail & Related papers  (2020-04-12T09:35:54Z)

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.