MUSTER: A Multi-scale Transformer-based Decoder for Semantic Segmentation

• URL: http://arxiv.org/abs/2211.13928v2
• Date: Sat, 17 Aug 2024 01:47:14 GMT
• Title: MUSTER: A Multi-scale Transformer-based Decoder for Semantic Segmentation
• Authors: Jing Xu, Wentao Shi, Pan Gao, Zhengwei Wang, Qizhu Li,
• Abstract summary: MUSTER is a transformer-based decoder that seamlessly integrates with hierarchical encoders. MSKA units enable the fusion of multi-scale features from the encoder and decoder, facilitating comprehensive information integration. On the challenging ADE20K dataset, our best model achieves a single-scale mIoU of 50.23 and a multi-scale mIoU of 51.88.
• Score: 19.83103856355554
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: In recent works on semantic segmentation, there has been a significant focus on designing and integrating transformer-based encoders. However, less attention has been given to transformer-based decoders. We emphasize that the decoder stage is equally vital as the encoder in achieving superior segmentation performance. It disentangles and refines high-level cues, enabling precise object boundary delineation at the pixel level. In this paper, we introduce a novel transformer-based decoder called MUSTER, which seamlessly integrates with hierarchical encoders and consistently delivers high-quality segmentation results, regardless of the encoder architecture. Furthermore, we present a variant of MUSTER that reduces FLOPS while maintaining performance. MUSTER incorporates carefully designed multi-head skip attention (MSKA) units and introduces innovative upsampling operations. The MSKA units enable the fusion of multi-scale features from the encoder and decoder, facilitating comprehensive information integration. The upsampling operation leverages encoder features to enhance object localization and surpasses traditional upsampling methods, improving mIoU (mean Intersection over Union) by 0.4% to 3.2%. On the challenging ADE20K dataset, our best model achieves a single-scale mIoU of 50.23 and a multi-scale mIoU of 51.88, which is on-par with the current state-of-the-art model. Remarkably, we achieve this while significantly reducing the number of FLOPs by 61.3%. Our source code and models are publicly available at: https://github.com/shiwt03/MUSTER.

Related papers

• CFPFormer: Feature-pyramid like Transformer Decoder for Segmentation and Detection [1.837431956557716]
  Feature pyramids have been widely adopted in convolutional neural networks (CNNs) and transformers for tasks like medical image segmentation and object detection. We propose a novel decoder block that integrates feature pyramids and transformers. Our model achieves superior performance in detecting small objects compared to existing methods.
  arXiv  Detail & Related papers  (2024-04-23T18:46:07Z)
• Progressive Token Length Scaling in Transformer Encoders for Efficient Universal Segmentation [67.85309547416155]
  A powerful architecture for universal segmentation relies on transformers that encode multi-scale image features and decode object queries into mask predictions. Mask2Former uses 50% of its compute only on the transformer encoder. This is due to the retention of a full-length token-level representation of all backbone feature scales at each encoder layer. We propose PRO-SCALE to reduce computations by a large margin with minimal sacrifice in performance.
  arXiv  Detail & Related papers  (2024-04-23T01:34:20Z)
• Efficient Encoder-Decoder Transformer Decoding for Decomposable Tasks [53.550782959908524]
  We introduce a new configuration for encoder-decoder models that improves efficiency on structured output and decomposable tasks. Our method, prompt-in-decoder (PiD), encodes the input once and decodes the output in parallel, boosting both training and inference efficiency.
  arXiv  Detail & Related papers  (2024-03-19T19:27:23Z)
• U-MixFormer: UNet-like Transformer with Mix-Attention for Efficient Semantic Segmentation [0.0]
  CNN-based U-Net has seen significant progress in high-resolution medical imaging and remote sensing. This dual success inspired us to merge the strengths of both, leading to the inception of a U-Net-based vision transformer decoder. We propose a novel transformer decoder, U-MixFormer, built upon the U-Net structure, designed for efficient semantic segmentation.
  arXiv  Detail & Related papers  (2023-12-11T10:19:42Z)
• MIST: Medical Image Segmentation Transformer with Convolutional Attention Mixing (CAM) Decoder [0.0]
  We propose a Medical Image Transformer (MIST) incorporating a novel Convolutional Attention Mixing (CAM) decoder. MIST has two parts: a pre-trained multi-axis vision transformer (MaxViT) is used as an encoder, and the encoded feature representation is passed through the CAM decoder for segmenting the images. To enhance spatial information gain, deep and shallow convolutions are used for feature extraction and receptive field expansion.
  arXiv  Detail & Related papers  (2023-10-30T18:07:57Z)
• Medical Image Segmentation via Sparse Coding Decoder [3.9633192172709975]
  Transformers have achieved significant success in medical image segmentation, owing to its capability to capture long-range dependencies. Previous works incorporate convolutional layers into the encoder module of transformers, thereby enhancing their ability to learn local relationships among pixels. However, transformers may suffer from limited generalization capabilities and reduced robustness, attributed to the insufficient spatial recovery ability of their decoders.
  arXiv  Detail & Related papers  (2023-10-17T03:08:35Z)
• More complex encoder is not all you need [0.882348769487259]
  We introduce neU-Net (i.e., not complex encoder U-Net), which incorporates a novel Sub-pixel Convolution for upsampling to construct a powerful decoder. Our model design achieves excellent results, surpassing other state-of-the-art methods on both the Synapse and ACDC datasets.
  arXiv  Detail & Related papers  (2023-09-20T08:34:38Z)
• SegViTv2: Exploring Efficient and Continual Semantic Segmentation with Plain Vision Transformers [76.13755422671822]
  This paper investigates the capability of plain Vision Transformers (ViTs) for semantic segmentation using the encoder-decoder framework. We introduce a novel Attention-to-Mask (atm) module to design a lightweight decoder effective for plain ViT. Our decoder outperforms the popular decoder UPerNet using various ViT backbones while consuming only about $5%$ of the computational cost.
  arXiv  Detail & Related papers  (2023-06-09T22:29:56Z)
• Inception Transformer [151.939077819196]
  Inception Transformer, or iFormer, learns comprehensive features with both high- and low-frequency information in visual data. We benchmark the iFormer on a series of vision tasks, and showcase that it achieves impressive performance on image classification, COCO detection and ADE20K segmentation.
  arXiv  Detail & Related papers  (2022-05-25T17:59:54Z)
• Rethinking Semantic Segmentation from a Sequence-to-Sequence Perspective with Transformers [149.78470371525754]
  We treat semantic segmentation as a sequence-to-sequence prediction task. Specifically, we deploy a pure transformer to encode an image as a sequence of patches. With the global context modeled in every layer of the transformer, this encoder can be combined with a simple decoder to provide a powerful segmentation model, termed SEgmentation TRansformer (SETR) SETR achieves new state of the art on ADE20K (50.28% mIoU), Pascal Context (55.83% mIoU) and competitive results on Cityscapes.
  arXiv  Detail & Related papers  (2020-12-31T18:55:57Z)
• Motion-Attentive Transition for Zero-Shot Video Object Segmentation [99.44383412488703]
  We present a Motion-Attentive Transition Network (MATNet) for zero-shot object segmentation. An asymmetric attention block, called Motion-Attentive Transition (MAT), is designed within a two-stream encoder. In this way, the encoder becomes deeply internative, allowing for closely hierarchical interactions between object motion and appearance.
  arXiv  Detail & Related papers  (2020-03-09T16:58:42Z)

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.