# PatchDCT: Patch Refinement for High Quality Instance Segmentation

arXiv: https://arxiv.org/abs/2302.02693 · HTML: https://mlsanity.com/paper/2302.02693/

## Key facts

- Cited by 8 papers in the map (data through 14 Oct 2026).
- Builds on 34 of its 39 references that are in the map.
- First posted on arXiv 6 Feb 2023.

## Builds on (most cited first, 30 of 34)

- [Microsoft COCO: Common Objects in Context](https://mlsanity.com/paper/1405.0312/) (2014)
- [Semi-Supervised Classification with Graph Convolutional Networks](https://mlsanity.com/paper/1609.02907/) (2016)
- [Faster R-CNN: Towards Real-Time Object Detection with Region Proposal Networks](https://mlsanity.com/paper/1506.01497/) (2015)
- [Mask R-CNN](https://mlsanity.com/paper/1703.06870/) (2017)
- [Feature Pyramid Networks for Object Detection](https://mlsanity.com/paper/1612.03144/) (2016)
- [Fully Convolutional Networks for Semantic Segmentation](https://mlsanity.com/paper/1411.4038/) (2014)
- [The Cityscapes Dataset for Semantic Urban Scene Understanding](https://mlsanity.com/paper/1604.01685/) (2016)
- [DeepLab: Semantic Image Segmentation with Deep Convolutional Nets, Atrous Convolution, and Fully Connected CRFs](https://mlsanity.com/paper/1606.00915/) (2016)
- [LVIS: A Dataset for Large Vocabulary Instance Segmentation](https://mlsanity.com/paper/1908.03195/) (2019)
- [Hybrid Task Cascade for Instance Segmentation](https://mlsanity.com/paper/1901.07518/) (2019)
- [PointRend: Image Segmentation as Rendering](https://mlsanity.com/paper/1912.08193/) (2019)
- [Panoptic-DeepLab](https://mlsanity.com/paper/1910.04751/) (2019)
- [Mask Scoring R-CNN](https://mlsanity.com/paper/1903.00241/) (2019)
- [Conditional Random Fields as Recurrent Neural Networks](https://mlsanity.com/paper/1502.03240/) (2015)
- [R3Det: Refined Single-Stage Detector with Feature Refinement for Rotating Object](https://mlsanity.com/paper/1908.05612/) (2019)
- [Boundary IoU: Improving Object-Centric Image Segmentation Evaluation](https://mlsanity.com/paper/2103.16562/) (2021)
- [Rethinking Rotated Object Detection with Gaussian Wasserstein Distance Loss](https://mlsanity.com/paper/2101.11952/) (2021)
- [Learning High-Precision Bounding Box for Rotated Object Detection via Kullback-Leibler Divergence](https://mlsanity.com/paper/2106.01883/) (2021)
- [Fully Convolutional Instance-aware Semantic Segmentation](https://mlsanity.com/paper/1611.07709/) (2016)
- [MMRotate: A Rotated Object Detection Benchmark using PyTorch](https://mlsanity.com/paper/2204.13317/) (2022)
- [CascadePSP: Toward Class-Agnostic and Very High-Resolution Segmentation via Global and Local Refinement](https://mlsanity.com/paper/2005.02551/) (2020)
- [Deep Occlusion-Aware Instance Segmentation with Overlapping BiLayers](https://mlsanity.com/paper/2103.12340/) (2021)
- [Boundary-preserving Mask R-CNN](https://mlsanity.com/paper/2007.08921/) (2020)
- [SOLQ: Segmenting Objects by Learning Queries](https://mlsanity.com/paper/2106.02351/) (2021)
- [Mask Transfiner for High-Quality Instance Segmentation](https://mlsanity.com/paper/2111.13673/) (2021)
- [SCRDet++: Detecting Small, Cluttered and Rotated Objects via Instance-Level Feature Denoising and Rotation Loss Smoothing](https://mlsanity.com/paper/2004.13316/) (2020)
- [Mask Encoding for Single Shot Instance Segmentation](https://mlsanity.com/paper/2003.11712/) (2020)
- [RefineMask: Towards High-Quality Instance Segmentation with Fine-Grained Features](https://mlsanity.com/paper/2104.08569/) (2021)
- [Look Closer to Segment Better: Boundary Patch Refinement for Instance Segmentation](https://mlsanity.com/paper/2104.05239/) (2021)
- [Detecting Rotated Objects as Gaussian Distributions and Its 3-D Generalization](https://mlsanity.com/paper/2209.10839/) (2022)

## Built on by (most cited first, 8 of 8)

- [Segment Anything in High Quality](https://mlsanity.com/paper/2306.01567/) (2023)
- [Transformer-Based Visual Segmentation: A Survey](https://mlsanity.com/paper/2304.09854/) (2023)
- [Parameter-Inverted Image Pyramid Networks](https://mlsanity.com/paper/2406.04330/) (2024)
- [Parameter-Inverted Image Pyramid Networks for Visual Perception and Multimodal Understanding](https://mlsanity.com/paper/2501.07783/) (2025)
- [E-SAM: Training-Free Segment Every Entity Model](https://mlsanity.com/paper/2503.12094/) (2025)
- [Multi-Task Learning-Enabled Automatic Vessel Draft Reading for Intelligent Maritime Surveillance](https://mlsanity.com/paper/2310.07212/) (2023)
- [ContourFormer: Real-Time Contour-Based End-to-End Instance Segmentation Transformer](https://mlsanity.com/paper/2501.17688/) (2025)
- [MFH: Marrying Frequency Domain with Handwritten Mathematical Expression Recognition](https://mlsanity.com/paper/2507.00430/) (2025)

## Abstract (arXiv)

High-quality instance segmentation has shown emerging importance in computer vision. Without any refinement, DCT-Mask directly generates high-resolution masks by compressed vectors. To further refine masks obtained by compressed vectors, we propose for the first time a compressed vector based multi-stage refinement framework. However, the vanilla combination does not bring significant gains, because changes in some elements of the DCT vector will affect the prediction of the entire mask. Thus, we propose a simple and novel method named PatchDCT, which separates the mask decoded from a DCT vector into several patches and refines each patch by the designed classifier and regressor. Specifically, the classifier is used to distinguish mixed patches from all patches, and to correct previously mispredicted foreground and background patches. In contrast, the regressor is used for DCT vector prediction of mixed patches, further refining the segmentation quality at boundary locations. Experiments on COCO show that our method achieves 2.0%, 3.2%, 4.5% AP and 3.4%, 5.3%, 7.0% Boundary AP improvements over Mask-RCNN on COCO, LVIS, and Cityscapes, respectively. It also surpasses DCT-Mask by 0.7%, 1.1%, 1.3% AP and 0.9%, 1.7%, 4.2% Boundary AP on COCO, LVIS and Cityscapes. Besides, the performance of PatchDCT is also competitive with other state-of-the-art methods.