Background-Aware Pooling and Noise-Aware Loss for Weakly-Supervised Semantic Segmentation

• URL: http://arxiv.org/abs/2104.00905v1
• Date: Fri, 2 Apr 2021 06:38:41 GMT
• Title: Background-Aware Pooling and Noise-Aware Loss for Weakly-Supervised Semantic Segmentation
• Authors: Youngmin Oh, Beomjun Kim, Bumsub Ham
• Abstract summary: We address the problem of weakly-supervised semantic segmentation using bounding box annotations. Background regions are perceptually consistent in part within an image, and this can be leveraged to discriminate foreground and background regions inside object bounding boxes. We introduce a noise-aware loss (NAL) that makes the networks less susceptible to incorrect labels.
• Score: 27.50216933606052
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: We address the problem of weakly-supervised semantic segmentation (WSSS) using bounding box annotations. Although object bounding boxes are good indicators to segment corresponding objects, they do not specify object boundaries, making it hard to train convolutional neural networks (CNNs) for semantic segmentation. We find that background regions are perceptually consistent in part within an image, and this can be leveraged to discriminate foreground and background regions inside object bounding boxes. To implement this idea, we propose a novel pooling method, dubbed background-aware pooling (BAP), that focuses more on aggregating foreground features inside the bounding boxes using attention maps. This allows to extract high-quality pseudo segmentation labels to train CNNs for semantic segmentation, but the labels still contain noise especially at object boundaries. To address this problem, we also introduce a noise-aware loss (NAL) that makes the networks less susceptible to incorrect labels. Experimental results demonstrate that learning with our pseudo labels already outperforms state-of-the-art weakly- and semi-supervised methods on the PASCAL VOC 2012 dataset, and the NAL further boosts the performance.

Related papers

• Semantic Connectivity-Driven Pseudo-labeling for Cross-domain Segmentation [89.41179071022121]
  Self-training is a prevailing approach in cross-domain semantic segmentation. We propose a novel approach called Semantic Connectivity-driven pseudo-labeling. This approach formulates pseudo-labels at the connectivity level and thus can facilitate learning structured and low-noise semantics.
  arXiv  Detail & Related papers  (2023-12-11T12:29:51Z)
• Regularizing Self-training for Unsupervised Domain Adaptation via Structural Constraints [14.593782939242121]
  We propose to incorporate structural cues from auxiliary modalities, such as depth, to regularise conventional self-training objectives. Specifically, we introduce a contrastive pixel-level objectness constraint that pulls the pixel representations within a region of an object instance closer. We show that our regularizer significantly improves top performing self-training methods in various UDA benchmarks for semantic segmentation.
  arXiv  Detail & Related papers  (2023-04-29T00:12:26Z)
• Robust Visual Tracking by Segmentation [103.87369380021441]
  Estimating the target extent poses a fundamental challenge in visual object tracking. We propose a segmentation-centric tracking pipeline that produces a highly accurate segmentation mask. Our tracker is able to better learn a target representation that clearly differentiates the target in the scene from background content.
  arXiv  Detail & Related papers  (2022-03-21T17:59:19Z)
• Weakly Supervised Semantic Segmentation using Out-of-Distribution Data [50.45689349004041]
  Weakly supervised semantic segmentation (WSSS) methods are often built on pixel-level localization maps. We propose a novel source of information to distinguish foreground from the background: Out-of-Distribution (OoD) data.
  arXiv  Detail & Related papers  (2022-03-08T05:33:35Z)
• Box2Seg: Learning Semantics of 3D Point Clouds with Box-Level Supervision [65.19589997822155]
  We introduce a neural architecture, termed Box2Seg, to learn point-level semantics of 3D point clouds with bounding box-level supervision. We show that the proposed network can be trained with cheap, or even off-the-shelf bounding box-level annotations and subcloud-level tags.
  arXiv  Detail & Related papers  (2022-01-09T09:07:48Z)
• Affinity Attention Graph Neural Network for Weakly Supervised Semantic Segmentation [86.44301443789763]
  We propose Affinity Attention Graph Neural Network ($A2$GNN) for weakly supervised semantic segmentation. Our approach achieves new state-of-the-art performances on Pascal VOC 2012 datasets.
  arXiv  Detail & Related papers  (2021-06-08T02:19:21Z)
• Non-Salient Region Object Mining for Weakly Supervised Semantic Segmentation [64.2719590819468]
  We propose a non-salient region object mining approach for weakly supervised semantic segmentation. A potential object mining module is proposed to reduce the false-negative rate in pseudo labels. Our non-salient region masking module helps further discover the objects in the non-salient region.
  arXiv  Detail & Related papers  (2021-03-26T16:44:03Z)
• PCAMs: Weakly Supervised Semantic Segmentation Using Point Supervision [12.284208932393073]
  This paper presents a novel procedure for producing semantic segmentation from images given some point level annotations. We propose training a CNN that is normally fully supervised using our pseudo labels in place of ground truth labels. Our method achieves state of the art results for point supervised semantic segmentation on the PASCAL VOC 2012 dataset citeeveringham2010pascal, even outperforming state of the art methods for stronger bounding box and squiggle supervision.
  arXiv  Detail & Related papers  (2020-07-10T21:25:27Z)
• Towards Bounding-Box Free Panoptic Segmentation [16.4548904544277]
  We introduce a new Bounding-Box Free Network (BBFNet) for panoptic segmentation. BBFNet predicts coarse watershed levels and uses them to detect large instance candidates where boundaries are well defined. For smaller instances, whose boundaries are less reliable, BBFNet also predicts instance centers by means of Hough voting followed by mean-shift to reliably detect small objects.
  arXiv  Detail & Related papers  (2020-02-18T16:34:01Z)

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.