# Multi-Task Dense Prediction via Mixture of Low-Rank Experts

arXiv: https://arxiv.org/abs/2403.17749 · HTML: https://mlsanity.com/paper/2403.17749/

## Key facts

- Cited by 58 papers in the map (data through 14 Oct 2026).
- Placed in Mixture of LoRA experts, one of 12 directions in Mixture-of-experts.
- Builds on 47 of its 60 references that are in the map.
- First posted on arXiv 26 Mar 2024.

## Placed in

- Mixture-of-experts / [Mixture of LoRA experts](https://mlsanity.com/moe/mixture-of-lora-experts/)

## Builds on (most cited first, 30 of 47)

- [An Image is Worth 16x16 Words: Transformers for Image Recognition at Scale](https://mlsanity.com/paper/2010.11929/) (2020)
- [LoRA: Low-Rank Adaptation of Large Language Models](https://mlsanity.com/paper/2106.09685/) (2021)
- [DINOv2: Learning Robust Visual Features without Supervision](https://mlsanity.com/paper/2304.07193/) (2023)
- [Fully Convolutional Networks for Semantic Segmentation](https://mlsanity.com/paper/1411.4038/) (2014)
- [Outrageously Large Neural Networks: The Sparsely-Gated Mixture-of-Experts Layer](https://mlsanity.com/paper/1701.06538/) (2017)
- [DeepLab: Semantic Image Segmentation with Deep Convolutional Nets, Atrous Convolution, and Fully Connected CRFs](https://mlsanity.com/paper/1606.00915/) (2016)
- [Switch Transformers: Scaling to Trillion Parameter Models with Simple and Efficient Sparsity](https://mlsanity.com/paper/2101.03961/) (2021)
- [Vision Transformers for Dense Prediction](https://mlsanity.com/paper/2103.13413/) (2021)
- [Multi-Task Learning Using Uncertainty to Weigh Losses for Scene Geometry and Semantics](https://mlsanity.com/paper/1705.07115/) (2017)
- [Deep High-Resolution Representation Learning for Human Pose Estimation](https://mlsanity.com/paper/1902.09212/) (2019)
- [BDD100K: A Diverse Driving Dataset for Heterogeneous Multitask Learning](https://mlsanity.com/paper/1805.04687/) (2018)
- [GradNorm: Gradient Normalization for Adaptive Loss Balancing in Deep Multitask Networks](https://mlsanity.com/paper/1711.02257/) (2017)
- [Scaling Vision with Sparse Mixture of Experts](https://mlsanity.com/paper/2106.05974/) (2021)
- [Intrinsic Dimensionality Explains the Effectiveness of Language Model Fine-Tuning](https://mlsanity.com/paper/2012.13255/) (2020)
- [BiSeNet: Bilateral Segmentation Network for Real-time Semantic Segmentation](https://mlsanity.com/paper/1808.00897/) (2018)
- [AdaBins: Depth Estimation using Adaptive Bins](https://mlsanity.com/paper/2011.14141/) (2020)
- [End-to-End Multi-Task Learning with Attention](https://mlsanity.com/paper/1803.10704/) (2018)
- [RepVGG: Making VGG-style ConvNets Great Again](https://mlsanity.com/paper/2101.03697/) (2021)
- [Cross-stitch Networks for Multi-task Learning](https://mlsanity.com/paper/1604.03539/) (2016)
- [RefineNet: Multi-Path Refinement Networks for High-Resolution Semantic Segmentation](https://mlsanity.com/paper/1611.06612/) (2016)
- [VL-Adapter: Parameter-Efficient Transfer Learning for Vision-and-Language Tasks](https://mlsanity.com/paper/2112.06825/) (2021)
- [Unified Scaling Laws for Routed Language Models](https://mlsanity.com/paper/2202.01169/) (2022)
- [Coordinate Attention for Efficient Mobile Network Design](https://mlsanity.com/paper/2103.02907/) (2021)
- [Detect What You Can: Detecting and Representing Objects using Holistic Models and Body Parts](https://mlsanity.com/paper/1406.2031/) (2014)
- [PAD-Net: Multi-Tasks Guided Prediction-and-Distillation Network for Simultaneous Depth Estimation and Scene Parsing](https://mlsanity.com/paper/1805.04409/) (2018)
- [Just Pick a Sign: Optimizing Deep Multitask Models with Gradient Sign Dropout](https://mlsanity.com/paper/2010.06808/) (2020)
- [MTI-Net: Multi-Scale Task Interaction Networks for Multi-Task Learning](https://mlsanity.com/paper/2001.06902/) (2020)
- [Attentive Single-Tasking of Multiple Tasks](https://mlsanity.com/paper/1904.08918/) (2019)
- [Pattern-Affinitive Propagation across Depth, Surface Normal and Semantic Segmentation](https://mlsanity.com/paper/1906.03525/) (2019)
- [FacT: Factor-Tuning for Lightweight Adaptation on Vision Transformer](https://mlsanity.com/paper/2212.03145/) (2022)

## Built on by (most cited first, 30 of 58)

- [RADIOv2.5: Improved Baselines for Agglomerative Vision Foundation Models](https://mlsanity.com/paper/2412.07679/) (2024)
- [A Survey on LoRA of Large Language Models](https://mlsanity.com/paper/2407.11046/) (2024)
- [SM3Det: A Unified Model for Multi-Modal Remote Sensing Object Detection](https://mlsanity.com/paper/2412.20665/) (2024)
- [Learning Robust Stereo Matching in the Wild with Selective Mixture-of-Experts](https://mlsanity.com/paper/2507.04631/) (2025)
- [PhysMLE: Generalizable and Priors-Inclusive Multi-task Remote Physiological Measurement](https://mlsanity.com/paper/2405.06201/) (2024)
- [MTMamba++: Enhancing Multi-Task Dense Scene Understanding via Mamba-Based Decoders](https://mlsanity.com/paper/2408.15101/) (2024)
- [Swiss Army Knife: Synergizing Biases in Knowledge from Vision Foundation Models for Multi-Task Learning](https://mlsanity.com/paper/2410.14633/) (2024)
- [VA-MoE: Variables-Adaptive Mixture of Experts for Incremental Weather Forecasting](https://mlsanity.com/paper/2412.02503/) (2024)
- [FeatSharp: Your Vision Model Features, Sharper](https://mlsanity.com/paper/2502.16025/) (2025)
- [Towards All-in-One Medical Image Re-Identification](https://mlsanity.com/paper/2503.08173/) (2025)
- [TADFormer : Task-Adaptive Dynamic Transformer for Efficient Multi-Task Learning](https://mlsanity.com/paper/2501.04293/) (2025)
- [Synchronizing Task Behavior: Aligning Multiple Tasks during Test-Time Training](https://mlsanity.com/paper/2507.07778/) (2025)
- [Proto-Former: Unified Facial Landmark Detection by Prototype Transformer](https://mlsanity.com/paper/2510.15338/) (2025)
- [Semi-MoE: Mixture-of-Experts meets Semi-Supervised Histopathology Segmentation](https://mlsanity.com/paper/2509.13834/) (2025)
- [UniMRSeg: Unified Modality-Relax Segmentation via Hierarchical Self-Supervised Compensation](https://mlsanity.com/paper/2509.16170/) (2025)
- [Revisit the Imbalance Optimization in Multi-task Learning: An Experimental Analysis](https://mlsanity.com/paper/2509.23915/) (2025)
- [Adaptive Shared Experts with LoRA-Based Mixture of Experts for Multi-Task Learning](https://mlsanity.com/paper/2510.00570/) (2025)
- [M2H: Multi-Task Learning with Efficient Window-Based Cross-Task Attention for Monocular Spatial Perception](https://mlsanity.com/paper/2510.17363/) (2025)
- [One-Prompt Strikes Back: Sparse Mixture of Experts for Prompt-based Continual Learning](https://mlsanity.com/paper/2509.24483/) (2025)
- [Rethinking Efficient Mixture-of-Experts for Remote Sensing Modality-Missing Classification](https://mlsanity.com/paper/2511.11460/) (2025)
- [3D-Aware Multi-Task Learning with Cross-View Correlations for Dense Scene Understanding](https://mlsanity.com/paper/2511.20646/) (2025)
- [UniRoute: Unified Routing Mixture-of-Experts for Modality-Adaptive Remote Sensing Change Detection](https://mlsanity.com/paper/2601.14797/) (2026)
- [A Unified Study of LoRA Variants: Taxonomy, Review, Codebase, and Empirical Evaluation](https://mlsanity.com/paper/2601.22708/) (2026)
- [UV-M3TL: A Unified and Versatile Multimodal Multi-Task Learning Framework for Assistive Driving Perception](https://mlsanity.com/paper/2602.01594/) (2026)
- [Collaborative and Efficient Personalization with Mixtures of Adaptors](https://mlsanity.com/paper/2410.03497/) (2024)
- [Optimizing Dense Visual Predictions Through Multi-Task Coherence and Prioritization](https://mlsanity.com/paper/2412.03179/) (2024)
- [Mr. DETR++: Instructive Multi-Route Training for Detection Transformers with Mixture-of-Experts](https://mlsanity.com/paper/2412.10028/) (2024)
- [DA2Diff: Exploring Degradation-aware Adaptive Diffusion Priors for All-in-One Weather Restoration](https://mlsanity.com/paper/2504.05135/) (2025)
- [Mixture of Group Experts for Learning Invariant Representations](https://mlsanity.com/paper/2504.09265/) (2025)
- [Occlusion Boundary and Depth: Mutual Enhancement via Multi-Task Learning](https://mlsanity.com/paper/2505.21231/) (2025)

## Abstract (arXiv)

Previous multi-task dense prediction methods based on the Mixture of Experts (MoE) have received great performance but they neglect the importance of explicitly modeling the global relations among all tasks. In this paper, we present a novel decoder-focused method for multi-task dense prediction, called Mixture-of-Low-Rank-Experts (MLoRE). To model the global task relationships, MLoRE adds a generic convolution path to the original MoE structure, where each task feature can go through this path for explicit parameter sharing. Furthermore, to control the parameters and computational cost brought by the increase in the number of experts, we take inspiration from LoRA and propose to leverage the low-rank format of a vanilla convolution in the expert network. Since the low-rank experts have fewer parameters and can be dynamically parameterized into the generic convolution, the parameters and computational cost do not change much with the increase of experts. Benefiting from this design, we increase the number of experts and its reception field to enlarge the representation capacity, facilitating multiple dense tasks learning in a unified network. Extensive experiments on the PASCAL-Context and NYUD-v2 benchmarks show that our MLoRE achieves superior performance compared to previous state-of-the-art methods on all metrics. Our code is available at https://github.com/YuqiYang213/MLoRE.