# CascadePSP: Toward Class-Agnostic and Very High-Resolution Segmentation via Global and Local Refinement

arXiv: https://arxiv.org/abs/2005.02551 · HTML: https://mlsanity.com/paper/2005.02551/

## Key facts

- Cited by 113 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 6 May 2020.

## Built on by (most cited first, 30 of 113)

- [XMem: Long-Term Video Object Segmentation with an Atkinson-Shiffrin Memory Model](https://mlsanity.com/paper/2207.07115/) (2022)
- [Segment Anything in High Quality](https://mlsanity.com/paper/2306.01567/) (2023)
- [Rethinking Space-Time Networks with Improved Memory Coverage for Efficient Video Object Segmentation](https://mlsanity.com/paper/2106.05210/) (2021)
- [Tracking Anything with Decoupled Video Segmentation](https://mlsanity.com/paper/2309.03903/) (2023)
- [Putting the Object Back into Video Object Segmentation](https://mlsanity.com/paper/2310.12982/) (2023)
- [ST++: Make Self-training Work Better for Semi-supervised Semantic Segmentation](https://mlsanity.com/paper/2106.05095/) (2021)
- [Modular Interactive Video Object Segmentation: Interaction-to-Mask, Propagation and Difference-Aware Fusion](https://mlsanity.com/paper/2103.07941/) (2021)
- [Transformer-Based Visual Segmentation: A Survey](https://mlsanity.com/paper/2304.09854/) (2023)
- [Cost Aggregation with 4D Convolutional Swin Transformer for Few-Shot Segmentation](https://mlsanity.com/paper/2207.10866/) (2022)
- [Highly Accurate Dichotomous Image Segmentation](https://mlsanity.com/paper/2203.03041/) (2022)
- [Inst-Inpaint: Instructing to Remove Objects with Diffusion Models](https://mlsanity.com/paper/2304.03246/) (2023)
- [InverseForm: A Loss Function for Structured Boundary-Aware Segmentation](https://mlsanity.com/paper/2104.02745/) (2021)
- [Mask Transfiner for High-Quality Instance Segmentation](https://mlsanity.com/paper/2111.13673/) (2021)
- [Lite Vision Transformer with Enhanced Self-Attention](https://mlsanity.com/paper/2112.10809/) (2021)
- [Recurrent Dynamic Embedding for Video Object Segmentation](https://mlsanity.com/paper/2205.03761/) (2022)
- [Mining Contextual Information Beyond Image for Semantic Segmentation](https://mlsanity.com/paper/2108.11819/) (2021)
- [Active Boundary Loss for Semantic Segmentation](https://mlsanity.com/paper/2102.02696/) (2021)
- [Per-Clip Video Object Segmentation](https://mlsanity.com/paper/2208.01924/) (2022)
- [Instance Neural Radiance Field](https://mlsanity.com/paper/2304.04395/) (2023)
- [Revisiting Image Pyramid Structure for High Resolution Salient Object Detection](https://mlsanity.com/paper/2209.09475/) (2022)
- [Progressive Semantic Segmentation](https://mlsanity.com/paper/2104.03778/) (2021)
- [Learning Quality-aware Dynamic Memory for Video Object Segmentation](https://mlsanity.com/paper/2207.07922/) (2022)
- [Look Before You Match: Instance Understanding Matters in Video Object Segmentation](https://mlsanity.com/paper/2212.06826/) (2022)
- [High Quality Segmentation for Ultra High-resolution Images](https://mlsanity.com/paper/2111.14482/) (2021)
- [Matting Anything](https://mlsanity.com/paper/2306.05399/) (2023)
- [SegRefiner: Towards Model-Agnostic Segmentation Refinement with Discrete Diffusion Process](https://mlsanity.com/paper/2312.12425/) (2023)
- [Video Mask Transfiner for High-Quality Video Instance Segmentation](https://mlsanity.com/paper/2207.14012/) (2022)
- [Segment Anything without Supervision](https://mlsanity.com/paper/2406.20081/) (2024)
- [Human Instance Matting via Mutual Guidance and Multi-Instance Refinement](https://mlsanity.com/paper/2205.10767/) (2022)
- [Global Spectral Filter Memory Network for Video Object Segmentation](https://mlsanity.com/paper/2210.05567/) (2022)

## Abstract (arXiv)

State-of-the-art semantic segmentation methods were almost exclusively trained on images within a fixed resolution range. These segmentations are inaccurate for very high-resolution images since using bicubic upsampling of low-resolution segmentation does not adequately capture high-resolution details along object boundaries. In this paper, we propose a novel approach to address the high-resolution segmentation problem without using any high-resolution training data. The key insight is our CascadePSP network which refines and corrects local boundaries whenever possible. Although our network is trained with low-resolution segmentation data, our method is applicable to any resolution even for very high-resolution images larger than 4K. We present quantitative and qualitative studies on different datasets to show that CascadePSP can reveal pixel-accurate segmentation boundaries using our novel refinement module without any finetuning. Thus, our method can be regarded as class-agnostic. Finally, we demonstrate the application of our model to scene parsing in multi-class segmentation.