# Tensor Low-Rank Reconstruction for Semantic Segmentation

arXiv: https://arxiv.org/abs/2008.00490 · HTML: https://mlsanity.com/paper/2008.00490/

## Key facts

- Cited by 29 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 2 Aug 2020.

## Built on by (most cited first, 29 of 29)

- [SegViT: Semantic Segmentation with Plain Vision Transformers](https://mlsanity.com/paper/2210.05844/) (2022)
- [Large-scale Unsupervised Semantic Segmentation](https://mlsanity.com/paper/2106.03149/) (2021)
- [Single-Model and Any-Modality for Video Object Tracking](https://mlsanity.com/paper/2311.15851/) (2023)
- [Cylindrical and Asymmetrical 3D Convolution Networks for LiDAR-based Perception](https://mlsanity.com/paper/2109.05441/) (2021)
- [Learning Statistical Texture for Semantic Segmentation](https://mlsanity.com/paper/2103.04133/) (2021)
- [Many-to-many Splatting for Efficient Video Frame Interpolation](https://mlsanity.com/paper/2204.03513/) (2022)
- [StructToken : Rethinking Semantic Segmentation with Structural Prior](https://mlsanity.com/paper/2203.12612/) (2022)
- [Mining Relations among Cross-Frame Affinities for Video Semantic Segmentation](https://mlsanity.com/paper/2207.10436/) (2022)
- [SegViTv2: Exploring Efficient and Continual Semantic Segmentation with Plain Vision Transformers](https://mlsanity.com/paper/2306.06289/) (2023)
- [Fully Transformer Networks for Semantic Image Segmentation](https://mlsanity.com/paper/2106.04108/) (2021)
- [Learning Local and Global Temporal Contexts for Video Semantic Segmentation](https://mlsanity.com/paper/2204.03330/) (2022)
- [Fully Attentional Network for Semantic Segmentation](https://mlsanity.com/paper/2112.04108/) (2021)
- [PREF: Phasorial Embedding Fields for Compact Neural Representations](https://mlsanity.com/paper/2205.13524/) (2022)
- [Structural and Statistical Texture Knowledge Distillation and Learning for Segmentation](https://mlsanity.com/paper/2503.08043/) (2025)
- [Tensor Decomposition Based Attention Module for Spiking Neural Networks](https://mlsanity.com/paper/2310.14576/) (2023)
- [E-CRF: Embedded Conditional Random Field for Boundary-caused Class Weights Confusion in Semantic Segmentation](https://mlsanity.com/paper/2112.07106/) (2021)
- [LR-CSNet: Low-Rank Deep Unfolding Network for Image Compressive Sensing](https://mlsanity.com/paper/2212.09088/) (2022)
- [CurbNet: Curb Detection Framework Based on LiDAR Point Cloud Segmentation](https://mlsanity.com/paper/2403.16794/) (2024)
- [PRSeg: A Lightweight Patch Rotate MLP Decoder for Semantic Segmentation](https://mlsanity.com/paper/2305.00671/) (2023)
- [Position: Tensor Networks are a Valuable Asset for Green AI](https://mlsanity.com/paper/2205.12961/) (2022)
- [Video Frame Interpolation with Many-to-many Splatting and Spatial Selective Refinement](https://mlsanity.com/paper/2310.18946/) (2023)
- [SeSame: Simple, Easy 3D Object Detection with Point-Wise Semantics](https://mlsanity.com/paper/2403.06501/) (2024)
- [M2MRF: Many-to-Many Reassembly of Features for Tiny Lesion Segmentation in Fundus Images](https://mlsanity.com/paper/2111.00193/) (2021)
- [It's Not the Target, It's the Background: Rethinking Infrared Small Target Detection via Deep Patch-Free Low-Rank Representations](https://mlsanity.com/paper/2506.10425/) (2025)
- [Denoised Non-Local Neural Network for Semantic Segmentation](https://mlsanity.com/paper/2110.14200/) (2021)
- [Feature Selective Transformer for Semantic Image Segmentation](https://mlsanity.com/paper/2203.14124/) (2022)
- [FBNet: Feature Balance Network for Urban-Scene Segmentation](https://mlsanity.com/paper/2111.03286/) (2021)
- [Real-time Rail Recognition Based on 3D Point Clouds](https://mlsanity.com/paper/2201.02726/) (2022)
- [Reload-Mamba: Hierarchical Anti-Dilution State-Space Modeling for Multi-Class Semantic Segmentation](https://mlsanity.com/paper/2606.17966/) (2026)

## Abstract (arXiv)

Context information plays an indispensable role in the success of semantic segmentation. Recently, non-local self-attention based methods are proved to be effective for context information collection. Since the desired context consists of spatial-wise and channel-wise attentions, 3D representation is an appropriate formulation. However, these non-local methods describe 3D context information based on a 2D similarity matrix, where space compression may lead to channel-wise attention missing. An alternative is to model the contextual information directly without compression. However, this effort confronts a fundamental difficulty, namely the high-rank property of context information. In this paper, we propose a new approach to model the 3D context representations, which not only avoids the space compression but also tackles the high-rank difficulty. Here, inspired by tensor canonical-polyadic decomposition theory (i.e, a high-rank tensor can be expressed as a combination of rank-1 tensors.), we design a low-rank-to-high-rank context reconstruction framework (i.e, RecoNet). Specifically, we first introduce the tensor generation module (TGM), which generates a number of rank-1 tensors to capture fragments of context feature. Then we use these rank-1 tensors to recover the high-rank context features through our proposed tensor reconstruction module (TRM). Extensive experiments show that our method achieves state-of-the-art on various public datasets. Additionally, our proposed method has more than 100 times less computational cost compared with conventional non-local-based methods.