Rethinking Decoders for Transformer-based Semantic Segmentation: Compression is All You Need

• URL: http://arxiv.org/abs/2411.03033v1
• Date: Tue, 05 Nov 2024 12:10:02 GMT
• Title: Rethinking Decoders for Transformer-based Semantic Segmentation: Compression is All You Need
• Authors: Qishuai Wen, Chun-Guang Li,
• Abstract summary: We argue that there are fundamental connections between semantic segmentation and compression. We derive a white-box, fully attentional DEcoder for PrIncipled semantiC segemenTation (DEPICT) Experiments conducted on dataset ADE20K find that DEPICT consistently outperforms its black-box counterpart, Segmenter.
• Score: 3.218600495900291
• License:
• Abstract: State-of-the-art methods for Transformer-based semantic segmentation typically adopt Transformer decoders that are used to extract additional embeddings from image embeddings via cross-attention, refine either or both types of embeddings via self-attention, and project image embeddings onto the additional embeddings via dot-product. Despite their remarkable success, these empirical designs still lack theoretical justifications or interpretations, thus hindering potentially principled improvements. In this paper, we argue that there are fundamental connections between semantic segmentation and compression, especially between the Transformer decoders and Principal Component Analysis (PCA). From such a perspective, we derive a white-box, fully attentional DEcoder for PrIncipled semantiC segemenTation (DEPICT), with the interpretations as follows: 1) the self-attention operator refines image embeddings to construct an ideal principal subspace that aligns with the supervision and retains most information; 2) the cross-attention operator seeks to find a low-rank approximation of the refined image embeddings, which is expected to be a set of orthonormal bases of the principal subspace and corresponds to the predefined classes; 3) the dot-product operation yields compact representation for image embeddings as segmentation masks. Experiments conducted on dataset ADE20K find that DEPICT consistently outperforms its black-box counterpart, Segmenter, and it is light weight and more robust.

Related papers

• White-Box Transformers via Sparse Rate Reduction: Compression Is All There Is? [27.58916930770997]
  We show a family of white-box transformer-like deep network architectures, named CRATE, which are mathematically fully interpretable. Experiments show that these networks, despite their simplicity, indeed learn to compress and sparsify representations of large-scale real-world image and text datasets.
  arXiv  Detail & Related papers  (2023-11-22T02:23:32Z)
• Triple-View Knowledge Distillation for Semi-Supervised Semantic Segmentation [54.23510028456082]
  We propose a Triple-view Knowledge Distillation framework, termed TriKD, for semi-supervised semantic segmentation. The framework includes the triple-view encoder and the dual-frequency decoder.
  arXiv  Detail & Related papers  (2023-09-22T01:02:21Z)
• AICT: An Adaptive Image Compression Transformer [18.05997169440533]
  We propose a more straightforward yet effective Tranformer-based channel-wise auto-regressive prior model, resulting in an absolute image compression transformer (ICT) The proposed ICT can capture both global and local contexts from the latent representations. We leverage a learnable scaling module with a sandwich ConvNeXt-based pre/post-processor to accurately extract more compact latent representation.
  arXiv  Detail & Related papers  (2023-07-12T11:32:02Z)
• Robust and Efficient Segmentation of Cross-domain Medical Images [37.38861543166964]
  We propose a generalizable knowledge distillation method for robust and efficient segmentation of medical images. We propose two generalizable knowledge distillation schemes, Dual Contrastive Graph Distillation (DCGD) and Domain-Invariant Cross Distillation (DICD) In DICD, the domain-invariant semantic vectors from the two models (i.e., teacher and student) are leveraged to cross-reconstruct features by the header exchange of MSAN.
  arXiv  Detail & Related papers  (2022-07-26T15:55:36Z)
• CSformer: Bridging Convolution and Transformer for Compressive Sensing [65.22377493627687]
  This paper proposes a hybrid framework that integrates the advantages of leveraging detailed spatial information from CNN and the global context provided by transformer for enhanced representation learning. The proposed approach is an end-to-end compressive image sensing method, composed of adaptive sampling and recovery. The experimental results demonstrate the effectiveness of the dedicated transformer-based architecture for compressive sensing.
  arXiv  Detail & Related papers  (2021-12-31T04:37:11Z)
• Exploring Feature Representation Learning for Semi-supervised Medical Image Segmentation [30.608293915653558]
  We present a two-stage framework for semi-supervised medical image segmentation. Key insight is to explore the feature representation learning with labeled and unlabeled (i.e., pseudo labeled) images. A stage-adaptive contrastive learning method is proposed, containing a boundary-aware contrastive loss. We present an aleatoric uncertainty-aware method, namely AUA, to generate higher-quality pseudo labels.
  arXiv  Detail & Related papers  (2021-11-22T05:06:12Z)
• Segmenter: Transformer for Semantic Segmentation [79.9887988699159]
  We introduce Segmenter, a transformer model for semantic segmentation. We build on the recent Vision Transformer (ViT) and extend it to semantic segmentation. It outperforms the state of the art on the challenging ADE20K dataset and performs on-par on Pascal Context and Cityscapes.
  arXiv  Detail & Related papers  (2021-05-12T13:01:44Z)
• TFill: Image Completion via a Transformer-Based Architecture [69.62228639870114]
  We propose treating image completion as a directionless sequence-to-sequence prediction task. We employ a restrictive CNN with small and non-overlapping RF for token representation. In a second phase, to improve appearance consistency between visible and generated regions, a novel attention-aware layer (AAL) is introduced.
  arXiv  Detail & Related papers  (2021-04-02T01:42:01Z)
• 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)
• Bi-directional Cross-Modality Feature Propagation with Separation-and-Aggregation Gate for RGB-D Semantic Segmentation [59.94819184452694]
  Depth information has proven to be a useful cue in the semantic segmentation of RGBD images for providing a geometric counterpart to the RGB representation. Most existing works simply assume that depth measurements are accurate and well-aligned with the RGB pixels and models the problem as a cross-modal feature fusion. In this paper, we propose a unified and efficient Crossmodality Guided to not only effectively recalibrate RGB feature responses, but also to distill accurate depth information via multiple stages and aggregate the two recalibrated representations alternatively.
  arXiv  Detail & Related papers  (2020-07-17T18:35:24Z)

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.