Automatic universal taxonomies for multi-domain semantic segmentation
- URL: http://arxiv.org/abs/2207.08445v1
- Date: Mon, 18 Jul 2022 08:53:17 GMT
- Title: Automatic universal taxonomies for multi-domain semantic segmentation
- Authors: Petra Bevandi\'c, Sini\v{s}a \v{S}egvi\'c
- Abstract summary: Training semantic segmentation models on multiple datasets has sparked a lot of recent interest in the computer vision community.
established datasets have mutually incompatible labels which disrupt principled inference in the wild.
We address this issue by automatic construction of universal through iterative dataset integration.
- Score: 1.4364491422470593
- License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
- Abstract: Training semantic segmentation models on multiple datasets has sparked a lot
of recent interest in the computer vision community. This interest has been
motivated by expensive annotations and a desire to achieve proficiency across
multiple visual domains. However, established datasets have mutually
incompatible labels which disrupt principled inference in the wild. We address
this issue by automatic construction of universal taxonomies through iterative
dataset integration. Our method detects subset-superset relationships between
dataset-specific labels, and supports learning of sub-class logits by treating
super-classes as partial labels. We present experiments on collections of
standard datasets and demonstrate competitive generalization performance with
respect to previous work.
Related papers
- Generalized Category Discovery with Clustering Assignment Consistency [56.92546133591019]
Generalized category discovery (GCD) is a recently proposed open-world task.
We propose a co-training-based framework that encourages clustering consistency.
Our method achieves state-of-the-art performance on three generic benchmarks and three fine-grained visual recognition datasets.
arXiv Detail & Related papers (2023-10-30T00:32:47Z) - LMSeg: Language-guided Multi-dataset Segmentation [15.624630978858324]
We propose a Language-guided Multi-dataset framework, dubbed LMSeg, which supports both semantic and panoptic segmentation.
LMSeg maps category names to a text embedding space as a unified taxonomy, instead of using inflexible one-hot label.
Experiments demonstrate that our method achieves significant improvements on four semantic and three panoptic segmentation datasets.
arXiv Detail & Related papers (2023-02-27T03:43:03Z) - Association Graph Learning for Multi-Task Classification with Category
Shifts [68.58829338426712]
We focus on multi-task classification, where related classification tasks share the same label space and are learned simultaneously.
We learn an association graph to transfer knowledge among tasks for missing classes.
Our method consistently performs better than representative baselines.
arXiv Detail & Related papers (2022-10-10T12:37:41Z) - Learning Semantic Segmentation from Multiple Datasets with Label Shifts [101.24334184653355]
This paper proposes UniSeg, an effective approach to automatically train models across multiple datasets with differing label spaces.
Specifically, we propose two losses that account for conflicting and co-occurring labels to achieve better generalization performance in unseen domains.
arXiv Detail & Related papers (2022-02-28T18:55:19Z) - 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) - Using Psuedolabels for training Sentiment Classifiers makes the model
generalize better across datasets [0.0]
For a public sentiment classification API, how can we set up a classifier that works well on different types of data, having limited ability to annotate data from across domains?
We show that given a large amount of unannotated data from across different domains and pseudolabels on this dataset, we can train a sentiment classifier that generalizes better across different datasets.
arXiv Detail & Related papers (2021-10-05T17:47:15Z) - Multi-domain semantic segmentation with overlapping labels [1.4120796122384087]
We propose a principled method for seamless learning on datasets with overlapping classes based on partial labels and probabilistic loss.
Our method achieves competitive within-dataset and cross-dataset generalization, as well as ability to learn visual concepts which are not separately labeled in any of the training datasets.
arXiv Detail & Related papers (2021-08-25T13:25:41Z) - 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) - Simple multi-dataset detection [83.9604523643406]
We present a simple method for training a unified detector on multiple large-scale datasets.
We show how to automatically integrate dataset-specific outputs into a common semantic taxonomy.
Our approach does not require manual taxonomy reconciliation.
arXiv Detail & Related papers (2021-02-25T18:55:58Z) - On Cross-Dataset Generalization in Automatic Detection of Online Abuse [7.163723138100273]
We show that the benign examples in the Wikipedia Detox dataset are biased towards platform-specific topics.
We identify these examples using unsupervised topic modeling and manual inspection of topics' keywords.
For a robust dataset design, we suggest applying inexpensive unsupervised methods to inspect the collected data and downsize the non-generalizable content.
arXiv Detail & Related papers (2020-10-14T21:47:03Z)
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.