FastInstShadow: A Simple Query-Based Model for Instance Shadow Detection
Not on the map. Why?
Abstract (arXiv)
Instance shadow detection is the task of detecting pairs of shadows and objects, where existing methods first detect shadows and objects independently, then associate them. This paper introduces FastInstShadow, a method that enhances detection accuracy through a query-based architecture featuring an association transformer decoder with two dual-path transformer decoders to assess relationships between shadows and objects during detection. Experimental results using the SOBA dataset showed that the proposed method outperforms all existing methods across all criteria. This method makes real-time processing feasible for moderate-resolution images with better accuracy than SSISv2, the most accurate existing method. Our code is available at https://github.com/wlotkr/FastInstShadow.
Key facts. No citing papers in the map yet (data through 14 Oct 2026). Builds on 38 of its 48 references that are in the map. First posted on arXiv 10 Mar 2025.
Builds on
38 of 48 references.
References · 38
- 2020Denoising Diffusion Probabilistic Modelscited by 21,076
- 2014Microsoft COCO: Common Objects in Contextcited by 17,608
- 2015Faster R-CNN: Towards Real-Time Object Detection with Region Proposal Networkscited by 9,639
- 2020End-to-End Object Detection with Transformerscited by 7,414
- 2017Mask R-CNNcited by 7,277
- 2015Deep Unsupervised Learning using Nonequilibrium Thermodynamicscited by 7,058
- 2015Fast R-CNNcited by 2,933
- 2021Masked-attention Mask Transformer for Universal Image Segmentationcited by 2,351
- 2016V-Net: Fully Convolutional Neural Networks for Volumetric Medical Image Segmentationcited by 2,292
- 2019FCOS: Fully Convolutional One-Stage Object Detectioncited by 1,577
- 2016Semantic Understanding of Scenes through the ADE20K Datasetcited by 1,069
- 2018Path Aggregation Network for Instance Segmentationcited by 798
26 more
- 2018Deformable ConvNets v2: More Deformable, Better Resultscited by 670
- 2019Hybrid Task Cascade for Instance Segmentationcited by 481
- 2019PointRend: Image Segmentation as Renderingcited by 440
- 2018Bag of Tricks for Image Classification with Convolutional Neural Networkscited by 431
- 2019Cascade R-CNN: High Quality Object Detection and Instance Segmentationcited by 429
- 2019Mask Scoring R-CNNcited by 266
- 2019CenterMask : Real-Time Anchor-Free Instance Segmentationcited by 201
- 2017Stacked Conditional Generative Adversarial Networks for Jointly Learning Shadow Detection and Shadow Removalcited by 161
- 2015End-to-end people detection in crowded scenescited by 140
- 2021Panoptic SegFormer: Delving Deeper into Panoptic Segmentation with Transformerscited by 109
- 2022ShadowDiffusion: When Degradation Prior Meets Diffusion Model for Shadow Removalcited by 103
- 2019TensorMask: A Foundation for Dense Object Segmentationcited by 101
- 2019YOLACT++: Better Real-time Instance Segmentationcited by 84
- 2021SOLQ: Segmenting Objects by Learning Queriescited by 68
- 2022Sparse Instance Activation for Real-Time Instance Segmentationcited by 63
- 2021ISTR: End-to-End Instance Segmentation with Transformerscited by 52
- 2020Mask Encoding for Single Shot Instance Segmentationcited by 47
- 2019Instance Shadow Detectioncited by 37
- 2021Shadow Generation for Composite Image in Real-world Scenescited by 35
- 2021SOLO: A Simple Framework for Instance Segmentationcited by 32
- 2023FastInst: A Simple Query-Based Model for Real-Time Instance Segmentationcited by 32
- 2022Instance Shadow Detection with A Single-Stage Detectorcited by 22
- 2024Thinking Outside the BBox: Unconstrained Generative Object Compositingcited by 19
- 2024Shadow Generation for Composite Image Using Diffusion modelcited by 17
- 2023Shadow Generation with Decomposed Mask Prediction and Attentive Shadow Fillingcited by 8
- 2022Video Instance Shadow Detection Under the Sun and Skycited by 3
Built on by
Not cited yet.