# DCT-Mask: Discrete Cosine Transform Mask Representation for Instance Segmentation

arXiv: https://arxiv.org/abs/2011.09876 · HTML: https://mlsanity.com/paper/2011.09876/

## Key facts

- Cited by 27 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 19 Nov 2020.

## Built on by (most cited first, 27 of 27)

- [PETRv2: A Unified Framework for 3D Perception from Multi-Camera Images](https://mlsanity.com/paper/2206.01256/) (2022)
- [Transformer-Based Visual Segmentation: A Survey](https://mlsanity.com/paper/2304.09854/) (2023)
- [SOLQ: Segmenting Objects by Learning Queries](https://mlsanity.com/paper/2106.02351/) (2021)
- [Betrayed by Captions: Joint Caption Grounding and Generation for Open Vocabulary Instance Segmentation](https://mlsanity.com/paper/2301.00805/) (2023)
- [Global Spectral Filter Memory Network for Video Object Segmentation](https://mlsanity.com/paper/2210.05567/) (2022)
- [RGB no more: Minimally-decoded JPEG Vision Transformers](https://mlsanity.com/paper/2211.16421/) (2022)
- [SOIT: Segmenting Objects with Instance-Aware Transformers](https://mlsanity.com/paper/2112.11037/) (2021)
- [TextDCT: Arbitrary-Shaped Text Detection via Discrete Cosine Transform Mask](https://mlsanity.com/paper/2206.13381/) (2022)
- [Painterly Image Harmonization in Dual Domains](https://mlsanity.com/paper/2212.08846/) (2022)
- [Eigencontours: Novel Contour Descriptors Based on Low-Rank Approximation](https://mlsanity.com/paper/2203.15259/) (2022)
- [RF-Next: Efficient Receptive Field Search for Convolutional Neural Networks](https://mlsanity.com/paper/2206.06637/) (2022)
- [DynaMask: Dynamic Mask Selection for Instance Segmentation](https://mlsanity.com/paper/2303.07868/) (2023)
- [On the Robustness of Medical Vision-Language Models: Are they Truly Generalizable?](https://mlsanity.com/paper/2505.15425/) (2025)
- [Recurrent Generic Contour-based Instance Segmentation with Progressive Learning](https://mlsanity.com/paper/2301.08898/) (2023)
- [PatchDCT: Patch Refinement for High Quality Instance Segmentation](https://mlsanity.com/paper/2302.02693/) (2023)
- [CutS3D: Cutting Semantics in 3D for 2D Unsupervised Instance Segmentation](https://mlsanity.com/paper/2411.16319/) (2024)
- [Deep Learning Based Image Retrieval in the JPEG Compressed Domain](https://mlsanity.com/paper/2107.03648/) (2021)
- [SCR: Smooth Contour Regression with Geometric Priors](https://mlsanity.com/paper/2202.03784/) (2022)
- [High-Quality Unknown Object Instance Segmentation via Quadruple Boundary Error Refinement](https://mlsanity.com/paper/2306.16132/) (2023)
- [DEFormer: DCT-driven Enhancement Transformer for Low-light Image and Dark Vision](https://mlsanity.com/paper/2309.06941/) (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)
- [Semantic Communication Enabling Robust Edge Intelligence for Time-Critical IoT Applications](https://mlsanity.com/paper/2211.13787/) (2022)
- [Perceive, Excavate and Purify: A Novel Object Mining Framework for Instance Segmentation](https://mlsanity.com/paper/2304.08826/) (2023)
- [Evaluating Adversarial Robustness in the Spatial Frequency Domain](https://mlsanity.com/paper/2405.06345/) (2024)
- [DCT-Mamba3D: Spectral Decorrelation and Spatial-Spectral Feature Extraction for Hyperspectral Image Classification](https://mlsanity.com/paper/2502.01986/) (2025)
- [Adept: Annotation-Denoising Auxiliary Tasks with Discrete Cosine Transform Map and Keypoint for Human-Centric Pretraining](https://mlsanity.com/paper/2504.20800/) (2025)

## Abstract (arXiv)

Binary grid mask representation is broadly used in instance segmentation. A representative instantiation is Mask R-CNN which predicts masks on a 28× 28 binary grid. Generally, a low-resolution grid is not sufficient to capture the details, while a high-resolution grid dramatically increases the training complexity. In this paper, we propose a new mask representation by applying the discrete cosine transform(DCT) to encode the high-resolution binary grid mask into a compact vector. Our method, termed DCT-Mask, could be easily integrated into most pixel-based instance segmentation methods. Without any bells and whistles, DCT-Mask yields significant gains on different frameworks, backbones, datasets, and training schedules. It does not require any pre-processing or pre-training, and almost no harm to the running speed. Especially, for higher-quality annotations and more complex backbones, our method has a greater improvement. Moreover, we analyze the performance of our method from the perspective of the quality of mask representation. The main reason why DCT-Mask works well is that it obtains a high-quality mask representation with low complexity. Code is available at https://github.com/aliyun/DCT-Mask.git.