Distilling Inter-Class Distance for Semantic Segmentation

• URL: http://arxiv.org/abs/2205.03650v1
• Date: Sat, 7 May 2022 13:13:55 GMT
• Title: Distilling Inter-Class Distance for Semantic Segmentation
• Authors: Zhengbo Zhang, Chunluan Zhou, Zhigang Tu
• Abstract summary: We propose an Inter-class Distance Distillation (IDD) method to transfer the inter-class distance in the feature space from the teacher network to the student network. Our method is helpful to improve the accuracy of semantic segmentation models and achieves the state-of-the-art performance.
• Score: 17.76592932725305
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: Knowledge distillation is widely adopted in semantic segmentation to reduce the computation cost.The previous knowledge distillation methods for semantic segmentation focus on pixel-wise feature alignment and intra-class feature variation distillation, neglecting to transfer the knowledge of the inter-class distance in the feature space, which is important for semantic segmentation. To address this issue, we propose an Inter-class Distance Distillation (IDD) method to transfer the inter-class distance in the feature space from the teacher network to the student network. Furthermore, semantic segmentation is a position-dependent task,thus we exploit a position information distillation module to help the student network encode more position information. Extensive experiments on three popular datasets: Cityscapes, Pascal VOC and ADE20K show that our method is helpful to improve the accuracy of semantic segmentation models and achieves the state-of-the-art performance. E.g. it boosts the benchmark model("PSPNet+ResNet18") by 7.50% in accuracy on the Cityscapes dataset.

Related papers

• Frequency-based Matcher for Long-tailed Semantic Segmentation [22.199174076366003]
  We focus on a relatively under-explored task setting, long-tailed semantic segmentation (LTSS) We propose a dual-metric evaluation system and construct the LTSS benchmark to demonstrate the performance of semantic segmentation methods and long-tailed solutions. We also propose a transformer-based algorithm to improve LTSS, frequency-based matcher, which solves the oversuppression problem by one-to-many matching.
  arXiv  Detail & Related papers  (2024-06-06T09:57:56Z)
• Exploiting Object-based and Segmentation-based Semantic Features for Deep Learning-based Indoor Scene Classification [0.5572976467442564]
  The work described in this paper uses both semantic information, obtained from object detection, and semantic segmentation techniques. A novel approach that uses a semantic segmentation mask to provide Hu-moments-based segmentation categories' shape characterization, designated by Hu-Moments Features (SHMFs) is proposed. A three-main-branch network, designated by GOS$2$F$2$App, that exploits deep-learning-based global features, object-based features, and semantic segmentation-based features is also proposed.
  arXiv  Detail & Related papers  (2024-04-11T13:37:51Z)
• I2CKD : Intra- and Inter-Class Knowledge Distillation for Semantic Segmentation [1.433758865948252]
  This paper proposes a new knowledge distillation method tailored for image semantic segmentation, termed Intra- and Inter-Class Knowledge Distillation (I2CKD) The focus of this method is on capturing and transferring knowledge between the intermediate layers of teacher (cumbersome model) and student (compact model)
  arXiv  Detail & Related papers  (2024-03-27T12:05:22Z)
• Attention-guided Feature Distillation for Semantic Segmentation [8.344263189293578]
  This paper showcases the efficacy of a simple yet powerful method for utilizing refined feature maps to transfer attention. The proposed method has proven to be effective in distilling rich information, outperforming existing methods in semantic segmentation as a dense prediction task.
  arXiv  Detail & Related papers  (2024-03-08T16:57:47Z)
• Auxiliary Tasks Enhanced Dual-affinity Learning for Weakly Supervised Semantic Segmentation [79.05949524349005]
  We propose AuxSegNet+, a weakly supervised auxiliary learning framework to explore the rich information from saliency maps. We also propose a cross-task affinity learning mechanism to learn pixel-level affinities from the saliency and segmentation feature maps.
  arXiv  Detail & Related papers  (2024-03-02T10:03:21Z)
• EAA-Net: Rethinking the Autoencoder Architecture with Intra-class Features for Medical Image Segmentation [4.777011444412729]
  We propose a light-weight end-to-end segmentation framework based on multi-task learning, termed Edge Attention autoencoder Network (EAA-Net) Our approach not only utilizes the segmentation network to obtain inter-class features, but also applies the reconstruction network to extract intra-class features among the foregrounds. Experimental results show that our method performs well in medical image segmentation tasks.
  arXiv  Detail & Related papers  (2022-08-19T07:42:55Z)
• SemAffiNet: Semantic-Affine Transformation for Point Cloud Segmentation [94.11915008006483]
  We propose SemAffiNet for point cloud semantic segmentation. We conduct extensive experiments on the ScanNetV2 and NYUv2 datasets.
  arXiv  Detail & Related papers  (2022-05-26T17:00:23Z)
• X-Distill: Improving Self-Supervised Monocular Depth via Cross-Task Distillation [69.9604394044652]
  We propose a novel method to improve the self-supervised training of monocular depth via cross-task knowledge distillation. During training, we utilize a pretrained semantic segmentation teacher network and transfer its semantic knowledge to the depth network. We extensively evaluate the efficacy of our proposed approach on the KITTI benchmark and compare it with the latest state of the art.
  arXiv  Detail & Related papers  (2021-10-24T19:47:14Z)
• Improving Semi-Supervised and Domain-Adaptive Semantic Segmentation with Self-Supervised Depth Estimation [94.16816278191477]
  We present a framework for semi-adaptive and domain-supervised semantic segmentation. It is enhanced by self-supervised monocular depth estimation trained only on unlabeled image sequences. We validate the proposed model on the Cityscapes dataset.
  arXiv  Detail & Related papers  (2021-08-28T01:33:38Z)
• CTNet: Context-based Tandem Network for Semantic Segmentation [77.4337867789772]
  This work proposes a novel Context-based Tandem Network (CTNet) by interactively exploring the spatial contextual information and the channel contextual information. To further improve the performance of the learned representations for semantic segmentation, the results of the two context modules are adaptively integrated.
  arXiv  Detail & Related papers  (2021-04-20T07:33:11Z)
• 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)

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.