Semantic Segmentation on Multiple Visual Domains

• URL: http://arxiv.org/abs/2107.04326v1
• Date: Fri, 9 Jul 2021 09:34:51 GMT
• Title: Semantic Segmentation on Multiple Visual Domains
• Authors: Floris Naber
• Abstract summary: Training models on multiple existing domains is desired to increase the output label-space. In this paper a method for this is proposed for the datasets Cityscapes, SUIM and SUN RGB-D, by creating a label-space that spans all classes of the datasets. Results show that accuracy of the multi-domain model has higher accuracy than all baseline models together, if hardware performance is equalized.
• Score: 0.0
• License: http://creativecommons.org/licenses/by-nc-sa/4.0/
• Abstract: Semantic segmentation models only perform well on the domain they are trained on and datasets for training are scarce and often have a small label-spaces, because the pixel level annotations required are expensive to make. Thus training models on multiple existing domains is desired to increase the output label-space. Current research shows that there is potential to improve accuracy across datasets by using multi-domain training, but this has not yet been successfully extended to datasets of three different non-overlapping domains without manual labelling. In this paper a method for this is proposed for the datasets Cityscapes, SUIM and SUN RGB-D, by creating a label-space that spans all classes of the datasets. Duplicate classes are merged and discrepant granularity is solved by keeping classes separate. Results show that accuracy of the multi-domain model has higher accuracy than all baseline models together, if hardware performance is equalized, as resources are not limitless, showing that models benefit from additional data even from domains that have nothing in common.

Related papers

• How to Encode Domain Information in Relation Classification [28.006694890849374]
  Current language models require a lot of training data to obtain high performance. For Relation Classification (RC), many datasets are domain-specific. We explore a multi-domain training setup for RC, and attempt to improve performance by encoding domain information.
  arXiv  Detail & Related papers  (2024-04-21T20:16:35Z)
• HGFormer: Hierarchical Grouping Transformer for Domain Generalized Semantic Segmentation [113.6560373226501]
  This work studies semantic segmentation under the domain generalization setting. We propose a novel hierarchical grouping transformer (HGFormer) to explicitly group pixels to form part-level masks and then whole-level masks. Experiments show that HGFormer yields more robust semantic segmentation results than per-pixel classification methods and flat grouping transformers.
  arXiv  Detail & Related papers  (2023-05-22T13:33:41Z)
• Label Name is Mantra: Unifying Point Cloud Segmentation across Heterogeneous Datasets [17.503843467554592]
  We propose a principled approach that supports learning from heterogeneous datasets with different label sets. Our idea is to utilize a pre-trained language model to embed discrete labels to a continuous latent space with the help of their label names. Our model outperforms the state-of-the-art by a large margin.
  arXiv  Detail & Related papers  (2023-03-19T06:14:22Z)
• MSeg: A Composite Dataset for Multi-domain Semantic Segmentation [100.17755160696939]
  We present MSeg, a composite dataset that unifies semantic segmentation datasets from different domains. We reconcile the generalization and bring the pixel-level annotations into alignment by relabeling more than 220,000 object masks in more than 80,000 images. A model trained on MSeg ranks first on the WildDash-v1 leaderboard for robust semantic segmentation, with no exposure to WildDash data during training.
  arXiv  Detail & Related papers  (2021-12-27T16:16:35Z)
• Multi-dataset Pretraining: A Unified Model for Semantic Segmentation [97.61605021985062]
  We propose a unified framework, termed as Multi-Dataset Pretraining, to take full advantage of the fragmented annotations of different datasets. This is achieved by first pretraining the network via the proposed pixel-to-prototype contrastive loss over multiple datasets. In order to better model the relationship among images and classes from different datasets, we extend the pixel level embeddings via cross dataset mixing.
  arXiv  Detail & Related papers  (2021-06-08T06:13:11Z)
• Robust wav2vec 2.0: Analyzing Domain Shift in Self-Supervised Pre-Training [67.71228426496013]
  We show that using target domain data during pre-training leads to large performance improvements across a variety of setups. We find that pre-training on multiple domains improves performance generalization on domains not seen during training.
  arXiv  Detail & Related papers  (2021-04-02T12:53:15Z)
• i-Mix: A Domain-Agnostic Strategy for Contrastive Representation Learning [117.63815437385321]
  We propose i-Mix, a simple yet effective domain-agnostic regularization strategy for improving contrastive representation learning. In experiments, we demonstrate that i-Mix consistently improves the quality of learned representations across domains.
  arXiv  Detail & Related papers  (2020-10-17T23:32:26Z)
• Deep Domain-Adversarial Image Generation for Domain Generalisation [115.21519842245752]
  Machine learning models typically suffer from the domain shift problem when trained on a source dataset and evaluated on a target dataset of different distribution. To overcome this problem, domain generalisation (DG) methods aim to leverage data from multiple source domains so that a trained model can generalise to unseen domains. We propose a novel DG approach based on emphDeep Domain-Adversarial Image Generation (DDAIG)
  arXiv  Detail & Related papers  (2020-03-12T23:17:47Z)
• LiDARNet: A Boundary-Aware Domain Adaptation Model for Point Cloud Semantic Segmentation [18.211513930388417]
  We present a boundary-aware domain adaptation model for LiDAR scan full-scene semantic segmentation (LiDARNet) Our model can extract both the domain private features and the domain shared features with a two-branch structure. Using our approach, we can get a single projection-based LiDAR full-scene semantic segmentation model working on both domains.
  arXiv  Detail & Related papers  (2020-03-02T20:18:31Z)

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.