Mixed-Query Transformer: A Unified Image Segmentation Architecture

• URL: http://arxiv.org/abs/2404.04469v1
• Date: Sat, 6 Apr 2024 01:54:17 GMT
• Title: Mixed-Query Transformer: A Unified Image Segmentation Architecture
• Authors: Pei Wang, Zhaowei Cai, Hao Yang, Ashwin Swaminathan, R. Manmatha, Stefano Soatto,
• Abstract summary: Existing unified image segmentation models either employ a unified architecture across multiple tasks but use separate weights tailored to each dataset, or apply a single set of weights to multiple datasets but are limited to a single task. We introduce the Mixed-Query Transformer (MQ-Former), a unified architecture for multi-task and multi-dataset image segmentation using a single set of weights.
• Score: 57.32212654642384
• License: http://creativecommons.org/licenses/by-nc-nd/4.0/
• Abstract: Existing unified image segmentation models either employ a unified architecture across multiple tasks but use separate weights tailored to each dataset, or apply a single set of weights to multiple datasets but are limited to a single task. In this paper, we introduce the Mixed-Query Transformer (MQ-Former), a unified architecture for multi-task and multi-dataset image segmentation using a single set of weights. To enable this, we propose a mixed query strategy, which can effectively and dynamically accommodate different types of objects without heuristic designs. In addition, the unified architecture allows us to use data augmentation with synthetic masks and captions to further improve model generalization. Experiments demonstrate that MQ-Former can not only effectively handle multiple segmentation datasets and tasks compared to specialized state-of-the-art models with competitive performance, but also generalize better to open-set segmentation tasks, evidenced by over 7 points higher performance than the prior art on the open-vocabulary SeginW benchmark.

Related papers

• PEM: Prototype-based Efficient MaskFormer for Image Segmentation [10.795762739721294]
  Recent transformer-based architectures have shown impressive results in the field of image segmentation. We propose Prototype-based Efficient MaskFormer (PEM), an efficient transformer-based architecture that can operate in multiple segmentation tasks.
  arXiv  Detail & Related papers  (2024-02-29T18:21:54Z)
• OMG-Seg: Is One Model Good Enough For All Segmentation? [83.17068644513144]
  OMG-Seg is a transformer-based encoder-decoder architecture with task-specific queries and outputs. We show that OMG-Seg can support over ten distinct segmentation tasks and yet significantly reduce computational and parameter overhead.
  arXiv  Detail & Related papers  (2024-01-18T18:59:34Z)
• Bridging the Gap: Exploring the Capabilities of Bridge-Architectures for Complex Visual Reasoning Tasks [4.093474663507322]
  Bridge-architectures project from the image space to the text space to solve tasks such as VQA, captioning, and image retrieval. We extend the traditional bridge architectures for the NLVR2 dataset, by adding object level features to faciliate fine-grained object reasoning. Our analysis shows that adding object level features to bridge architectures does not help, and that pre-training on multi-modal data is key for good performance on complex reasoning tasks such as NLVR2.
  arXiv  Detail & Related papers  (2023-07-31T03:57:31Z)
• An Efficient General-Purpose Modular Vision Model via Multi-Task Heterogeneous Training [79.78201886156513]
  We present a model that can perform multiple vision tasks and can be adapted to other downstream tasks efficiently. Our approach achieves comparable results to single-task state-of-the-art models and demonstrates strong generalization on downstream tasks.
  arXiv  Detail & Related papers  (2023-06-29T17:59:57Z)
• AIMS: All-Inclusive Multi-Level Segmentation [93.5041381700744]
  We propose a new task, All-Inclusive Multi-Level (AIMS), which segments visual regions into three levels: part, entity, and relation. We also build a unified AIMS model through multi-dataset multi-task training to address the two major challenges of annotation inconsistency and task correlation.
  arXiv  Detail & Related papers  (2023-05-28T16:28:49Z)
• High-Quality Entity Segmentation [110.55724145851725]
  CropFormer is designed to tackle the intractability of instance-level segmentation on high-resolution images. It improves mask prediction by fusing high-res image crops that provide more fine-grained image details and the full image. With CropFormer, we achieve a significant AP gain of $1.9$ on the challenging entity segmentation task.
  arXiv  Detail & Related papers  (2022-11-10T18:58:22Z)
• 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)

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.