Cross Resolution Encoding-Decoding For Detection Transformers

• URL: http://arxiv.org/abs/2410.04088v1
• Date: Sat, 5 Oct 2024 09:01:59 GMT
• Title: Cross Resolution Encoding-Decoding For Detection Transformers
• Authors: Ashish Kumar, Jaesik Park,
• Abstract summary: Cross-Resolution. Decoding (CRED) is designed to fuse multiscale. detection mechanisms. CRED delivers accuracy similar to the high-resolution DETR counterpart in roughly 50% fewer FLOPs. We plan to release pretrained CRED-DETRs for use by the community.
• Score: 33.248031676529635
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: Detection Transformers (DETR) are renowned object detection pipelines, however computationally efficient multiscale detection using DETR is still challenging. In this paper, we propose a Cross-Resolution Encoding-Decoding (CRED) mechanism that allows DETR to achieve the accuracy of high-resolution detection while having the speed of low-resolution detection. CRED is based on two modules; Cross Resolution Attention Module (CRAM) and One Step Multiscale Attention (OSMA). CRAM is designed to transfer the knowledge of low-resolution encoder output to a high-resolution feature. While OSMA is designed to fuse multiscale features in a single step and produce a feature map of a desired resolution enriched with multiscale information. When used in prominent DETR methods, CRED delivers accuracy similar to the high-resolution DETR counterpart in roughly 50% fewer FLOPs. Specifically, state-of-the-art DN-DETR, when used with CRED (calling CRED-DETR), becomes 76% faster, with ~50% reduced FLOPs than its high-resolution counterpart with 202 G FLOPs on MS-COCO benchmark. We plan to release pretrained CRED-DETRs for use by the community. Code: https://github.com/ashishkumar822/CRED-DETR

Related papers

• Global Context Aggregation Network for Lightweight Saliency Detection of Surface Defects [70.48554424894728]
  We develop a Global Context Aggregation Network (GCANet) for lightweight saliency detection of surface defects on the encoder-decoder structure. First, we introduce a novel transformer encoder on the top layer of the lightweight backbone, which captures global context information through a novel Depth-wise Self-Attention (DSA) module. The experimental results on three public defect datasets demonstrate that the proposed network achieves a better trade-off between accuracy and running efficiency compared with other 17 state-of-the-art methods.
  arXiv  Detail & Related papers  (2023-09-22T06:19:11Z)
• CIR-Net: Cross-modality Interaction and Refinement for RGB-D Salient Object Detection [144.66411561224507]
  We present a convolutional neural network (CNN) model, named CIR-Net, based on the novel cross-modality interaction and refinement. Our network outperforms the state-of-the-art saliency detectors both qualitatively and quantitatively.
  arXiv  Detail & Related papers  (2022-10-06T11:59:19Z)
• Efficient Decoder-free Object Detection with Transformers [75.00499377197475]
  Vision transformers (ViTs) are changing the landscape of object detection approaches. We propose a decoder-free fully transformer-based (DFFT) object detector. DFFT_SMALL achieves high efficiency in both training and inference stages.
  arXiv  Detail & Related papers  (2022-06-14T13:22:19Z)
• Pyramid Grafting Network for One-Stage High Resolution Saliency Detection [29.013012579688347]
  We propose a one-stage framework called Pyramid Grafting Network (PGNet) to extract features from different resolution images independently. An attention-based Cross-Model Grafting Module (CMGM) is proposed to enable CNN branch to combine broken detailed information more holistically. We contribute a new Ultra-High-Resolution Saliency Detection dataset UHRSD, containing 5,920 images at 4K-8K resolutions.
  arXiv  Detail & Related papers  (2022-04-11T12:22:21Z)
• D^2ETR: Decoder-Only DETR with Computationally Efficient Cross-Scale Attention [27.354159713970322]
  We propose a decoder-only detector called D2ETR. In the absence of encoder, the decoder directly attends to the fine-fused feature maps generated by the Transformer backbone. D2ETR demonstrates low computational complexity and high detection accuracy in evaluations on the COCO benchmark.
  arXiv  Detail & Related papers  (2022-03-02T04:21:12Z)
• Recurrent Glimpse-based Decoder for Detection with Transformer [85.64521612986456]
  We introduce a novel REcurrent Glimpse-based decOder (REGO) in this paper. In particular, the REGO employs a multi-stage recurrent processing structure to help the attention of DETR gradually focus on foreground objects. REGO consistently boosts the performance of different DETR detectors by up to 7% relative gain at the same setting of 50 training epochs.
  arXiv  Detail & Related papers  (2021-12-09T00:29:19Z)
• Sparse DETR: Efficient End-to-End Object Detection with Learnable Sparsity [10.098578160958946]
  We show that Sparse DETR achieves better performance than Deformable DETR even with only 10% encoder tokens on the COCO dataset. Albeit only the encoder tokens are sparsified, the total computation cost decreases by 38% and the frames per second (FPS) increases by 42% compared to Deformable DETR.
  arXiv  Detail & Related papers  (2021-11-29T05:22:46Z)
• Cross-modality Discrepant Interaction Network for RGB-D Salient Object Detection [78.47767202232298]
  We propose a novel Cross-modality Discrepant Interaction Network (CDINet) for RGB-D SOD. Two components are designed to implement the effective cross-modality interaction. Our network outperforms $15$ state-of-the-art methods both quantitatively and qualitatively.
  arXiv  Detail & Related papers  (2021-08-04T11:24:42Z)
• 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.