Learning Multiple Representations with Inconsistency-Guided Detail Regularization for Mask-Guided Matting

• URL: http://arxiv.org/abs/2403.19213v1
• Date: Thu, 28 Mar 2024 08:21:56 GMT
• Title: Learning Multiple Representations with Inconsistency-Guided Detail Regularization for Mask-Guided Matting
• Authors: Weihao Jiang, Zhaozhi Xie, Yuxiang Lu, Longjie Qi, Jingyong Cai, Hiroyuki Uchiyama, Bin Chen, Yue Ding, Hongtao Lu,
• Abstract summary: Mask-guided matting networks have shown great potential in practical applications in recent years. These approaches tend to overfit low-level details in wrong regions. We propose a novel auxiliary learning framework for mask-guided matting models.
• Score: 20.55342666783899
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: Mask-guided matting networks have achieved significant improvements and have shown great potential in practical applications in recent years. However, simply learning matting representation from synthetic and lack-of-real-world-diversity matting data, these approaches tend to overfit low-level details in wrong regions, lack generalization to objects with complex structures and real-world scenes such as shadows, as well as suffer from interference of background lines or textures. To address these challenges, in this paper, we propose a novel auxiliary learning framework for mask-guided matting models, incorporating three auxiliary tasks: semantic segmentation, edge detection, and background line detection besides matting, to learn different and effective representations from different types of data and annotations. Our framework and model introduce the following key aspects: (1) to learn real-world adaptive semantic representation for objects with diverse and complex structures under real-world scenes, we introduce extra semantic segmentation and edge detection tasks on more diverse real-world data with segmentation annotations; (2) to avoid overfitting on low-level details, we propose a module to utilize the inconsistency between learned segmentation and matting representations to regularize detail refinement; (3) we propose a novel background line detection task into our auxiliary learning framework, to suppress interference of background lines or textures. In addition, we propose a high-quality matting benchmark, Plant-Mat, to evaluate matting methods on complex structures. Extensively quantitative and qualitative results show that our approach outperforms state-of-the-art mask-guided methods.

Related papers

• Deep ContourFlow: Advancing Active Contours with Deep Learning [3.9948520633731026]
  We present a framework for both unsupervised and one-shot approaches for image segmentation. It is capable of capturing complex object boundaries without the need for extensive labeled training data. This is particularly required in histology, a field facing a significant shortage of annotations.
  arXiv  Detail & Related papers  (2024-07-15T13:12:34Z)
• Multi-Grained Contrast for Data-Efficient Unsupervised Representation Learning [10.630297877530614]
  We propose a novel Multi-Grained Contrast method (MGC) for unsupervised representation learning. Specifically, we construct delicate multi-grained correspondences between positive views and then conduct multi-grained contrast by the correspondences to learn more general unsupervised representations. Our method significantly outperforms the existing state-of-the-art methods on extensive downstream tasks, including object detection, instance segmentation, scene parsing, semantic segmentation and keypoint detection.
  arXiv  Detail & Related papers  (2024-07-02T07:35:21Z)
• Enhancing Generalizability of Representation Learning for Data-Efficient 3D Scene Understanding [50.448520056844885]
  We propose a generative Bayesian network to produce diverse synthetic scenes with real-world patterns. A series of experiments robustly display our method's consistent superiority over existing state-of-the-art pre-training approaches.
  arXiv  Detail & Related papers  (2024-06-17T07:43:53Z)
• Mesh Denoising Transformer [104.5404564075393]
  Mesh denoising is aimed at removing noise from input meshes while preserving their feature structures. SurfaceFormer is a pioneering Transformer-based mesh denoising framework. New representation known as Local Surface Descriptor captures local geometric intricacies. Denoising Transformer module receives the multimodal information and achieves efficient global feature aggregation.
  arXiv  Detail & Related papers  (2024-05-10T15:27:43Z)
• Self-supervised Learning of Dense Hierarchical Representations for Medical Image Segmentation [2.2265038612930663]
  This paper demonstrates a self-supervised framework for learning voxel-wise coarse-to-fine representations tailored for dense downstream tasks. We devise a training strategy that balances the contributions of features from multiple scales, ensuring that the learned representations capture both coarse and fine-grained details.
  arXiv  Detail & Related papers  (2024-01-12T09:47:17Z)
• Masked Modeling for Self-supervised Representation Learning on Vision and Beyond [69.64364187449773]
  Masked modeling has emerged as a distinctive approach that involves predicting parts of the original data that are proportionally masked during training. We elaborate on the details of techniques within masked modeling, including diverse masking strategies, recovering targets, network architectures, and more. We conclude by discussing the limitations of current techniques and point out several potential avenues for advancing masked modeling research.
  arXiv  Detail & Related papers  (2023-12-31T12:03:21Z)
• Unsupervised Semantic Segmentation Through Depth-Guided Feature Correlation and Sampling [14.88236554564287]
  In this work, we build upon advances in unsupervised learning by incorporating information about the structure of a scene into the training process. We achieve this by (1) learning depth-feature correlation by spatially correlate the feature maps with the depth maps to induce knowledge about the structure of the scene. We then implement farthest-point sampling to more effectively select relevant features by utilizing 3D sampling techniques on depth information of the scene.
  arXiv  Detail & Related papers  (2023-09-21T11:47:01Z)
• Learning to Model Multimodal Semantic Alignment for Story Visualization [58.16484259508973]
  Story visualization aims to generate a sequence of images to narrate each sentence in a multi-sentence story. Current works face the problem of semantic misalignment because of their fixed architecture and diversity of input modalities. We explore the semantic alignment between text and image representations by learning to match their semantic levels in the GAN-based generative model.
  arXiv  Detail & Related papers  (2022-11-14T11:41:44Z)
• Cross-view Graph Contrastive Representation Learning on Partially Aligned Multi-view Data [52.491074276133325]
  Multi-view representation learning has developed rapidly over the past decades and has been applied in many fields. We propose a new cross-view graph contrastive learning framework, which integrates multi-view information to align data and learn latent representations. Experiments conducted on several real datasets demonstrate the effectiveness of the proposed method on the clustering and classification tasks.
  arXiv  Detail & Related papers  (2022-11-08T09:19:32Z)
• Three Ways to Improve Semantic Segmentation with Self-Supervised Depth Estimation [90.87105131054419]
  We present a framework for semi-supervised semantic segmentation, which is enhanced by self-supervised monocular depth estimation from unlabeled image sequences. We validate the proposed model on the Cityscapes dataset, where all three modules demonstrate significant performance gains.
  arXiv  Detail & Related papers  (2020-12-19T21:18:03Z)
• MARNet: Multi-Abstraction Refinement Network for 3D Point Cloud Analysis [9.34612743192798]
  Existing deep learning methods fail to exploit different granularity of information due to limited interaction between features. We propose Multi-Abstraction Refinement Network (MARNet) that ensures an effective exchange of information between multi-level features. We empirically show the effectiveness of MARNet in terms of state-of-the-art results on two challenging tasks: Shape classification and Coarse-to-fine grained semantic segmentation.
  arXiv  Detail & Related papers  (2020-11-02T12:07:35Z)

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.