BEN: Using Confidence-Guided Matting for Dichotomous Image Segmentation

• URL: http://arxiv.org/abs/2501.06230v1
• Date: Wed, 08 Jan 2025 01:30:11 GMT
• Title: BEN: Using Confidence-Guided Matting for Dichotomous Image Segmentation
• Authors: Maxwell Meyer, Jack Spruyt,
• Abstract summary: We propose a new architectural approach for image segmentation called Confidence-Guided Matting (CGM) BEN is comprised of two components: BEN Base for initial segmentation and BEN Refiner for confidence refinement. Our approach achieves substantial improvements over current state-of-the-art methods on the DIS5K validation dataset.
• Score: 0.0
• License:
• Abstract: Current approaches to dichotomous image segmentation (DIS) treat image matting and object segmentation as fundamentally different tasks. As improvements in image segmentation become increasingly challenging to achieve, combining image matting and grayscale segmentation techniques offers promising new directions for architectural innovation. Inspired by the possibility of aligning these two model tasks, we propose a new architectural approach for DIS called Confidence-Guided Matting (CGM). We created the first CGM model called Background Erase Network (BEN). BEN is comprised of two components: BEN Base for initial segmentation and BEN Refiner for confidence refinement. Our approach achieves substantial improvements over current state-of-the-art methods on the DIS5K validation dataset, demonstrating that matting-based refinement can significantly enhance segmentation quality. This work opens new possibilities for cross-pollination between matting and segmentation techniques in computer vision.

Related papers

• Freestyle Sketch-in-the-Loop Image Segmentation [116.1810651297801]
  We introduce a "sketch-in-the-loop" image segmentation framework, enabling the segmentation of visual concepts partially, completely, or in groupings. This framework capitalises on the synergy between sketch-based image retrieval models and large-scale pre-trained models. Our purpose-made augmentation strategy enhances the versatility of our sketch-guided mask generation, allowing segmentation at multiple levels.
  arXiv  Detail & Related papers  (2025-01-27T13:07:51Z)
• Image Segmentation in Foundation Model Era: A Survey [95.60054312319939]
  Current research in image segmentation lacks a detailed analysis of distinct characteristics, challenges, and solutions. This survey seeks to fill this gap by providing a thorough review of cutting-edge research centered around FM-driven image segmentation. An exhaustive overview of over 300 segmentation approaches is provided to encapsulate the breadth of current research efforts.
  arXiv  Detail & Related papers  (2024-08-23T10:07:59Z)
• Dual-scale Enhanced and Cross-generative Consistency Learning for Semi-supervised Medical Image Segmentation [49.57907601086494]
  Medical image segmentation plays a crucial role in computer-aided diagnosis. We propose a novel Dual-scale Enhanced and Cross-generative consistency learning framework for semi-supervised medical image (DEC-Seg)
  arXiv  Detail & Related papers  (2023-12-26T12:56:31Z)
• Improving Pixel-based MIM by Reducing Wasted Modeling Capability [77.99468514275185]
  We propose a new method that explicitly utilizes low-level features from shallow layers to aid pixel reconstruction. To the best of our knowledge, we are the first to systematically investigate multi-level feature fusion for isotropic architectures. Our method yields significant performance gains, such as 1.2% on fine-tuning, 2.8% on linear probing, and 2.6% on semantic segmentation.
  arXiv  Detail & Related papers  (2023-08-01T03:44:56Z)
• Interpretable Small Training Set Image Segmentation Network Originated from Multi-Grid Variational Model [5.283735137946097]
  Deep learning (DL) methods have been proposed and widely used for image segmentation. DL methods usually require a large amount of manually segmented data as training data and suffer from poor interpretability. In this paper, we replace the hand-crafted regularity term in the MS model with a data adaptive generalized learnable regularity term.
  arXiv  Detail & Related papers  (2023-06-25T02:34:34Z)
• CM-MaskSD: Cross-Modality Masked Self-Distillation for Referring Image Segmentation [29.885991324519463]
  We propose a novel cross-modality masked self-distillation framework named CM-MaskSD. Our method inherits the transferred knowledge of image-text semantic alignment from CLIP model to realize fine-grained patch-word feature alignment. Our framework can considerably boost model performance in a nearly parameter-free manner.
  arXiv  Detail & Related papers  (2023-05-19T07:17:27Z)
• Revisiting Image Reconstruction for Semi-supervised Semantic Segmentation [16.27277238968567]
  We revisit the idea of using image reconstruction as an auxiliary task and incorporate it with a modern semi-supervised semantic segmentation framework. Surprisingly, we discover that such an old idea in semi-supervised learning can produce results competitive with state-of-the-art semantic segmentation algorithms.
  arXiv  Detail & Related papers  (2023-03-17T06:31:06Z)
• CoMFormer: Continual Learning in Semantic and Panoptic Segmentation [45.66711231393775]
  We present the first continual learning model capable of operating on both semantic and panoptic segmentation. Our method carefully exploits the properties of transformer architectures to learn new classes over time. Our CoMFormer outperforms all the existing baselines by forgetting less old classes but also learning more effectively new classes.
  arXiv  Detail & Related papers  (2022-11-25T10:15:06Z)
• Progressively Dual Prior Guided Few-shot Semantic Segmentation [57.37506990980975]
  Few-shot semantic segmentation task aims at performing segmentation in query images with a few annotated support samples. We propose a progressively dual prior guided few-shot semantic segmentation network.
  arXiv  Detail & Related papers  (2022-11-20T16:19:47Z)
• BoundarySqueeze: Image Segmentation as Boundary Squeezing [104.43159799559464]
  We propose a novel method for fine-grained high-quality image segmentation of both objects and scenes. Inspired by dilation and erosion from morphological image processing techniques, we treat the pixel level segmentation problems as squeezing object boundary. Our method yields large gains on COCO, Cityscapes, for both instance and semantic segmentation and outperforms previous state-of-the-art PointRend in both accuracy and speed under the same setting.
  arXiv  Detail & Related papers  (2021-05-25T04:58:51Z)

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.