# DFormer: Rethinking RGBD Representation Learning for Semantic Segmentation

arXiv: https://arxiv.org/abs/2309.09668 · HTML: https://mlsanity.com/paper/2309.09668/

## Key facts

- Cited by 60 papers in the map (data through 14 Oct 2026).
- Builds on 65 of its 96 references that are in the map.
- First posted on arXiv 18 Sep 2023.

## Builds on (most cited first, 30 of 65)

- [Attention Is All You Need](https://mlsanity.com/paper/1706.03762/) (2017)
- [Deep Residual Learning for Image Recognition](https://mlsanity.com/paper/1512.03385/) (2015)
- [Adam: A Method for Stochastic Optimization](https://mlsanity.com/paper/1412.6980/) (2014)
- [Learning Transferable Visual Models From Natural Language Supervision](https://mlsanity.com/paper/2103.00020/) (2021)
- [ImageNet Large Scale Visual Recognition Challenge](https://mlsanity.com/paper/1409.0575/) (2014)
- [A ConvNet for the 2020s](https://mlsanity.com/paper/2201.03545/) (2022)
- [SegFormer: Simple and Efficient Design for Semantic Segmentation with Transformers](https://mlsanity.com/paper/2105.15203/) (2021)
- [BEiT: BERT Pre-Training of Image Transformers](https://mlsanity.com/paper/2106.08254/) (2021)
- [AdaBins: Depth Estimation using Adaptive Bins](https://mlsanity.com/paper/2011.14141/) (2020)
- [KITTI-360: A Novel Dataset and Benchmarks for Urban Scene Understanding in 2D and 3D](https://mlsanity.com/paper/2109.13410/) (2021)
- [Structure-measure: A New Way to Evaluate Foreground Maps](https://mlsanity.com/paper/1708.00786/) (2017)
- [Pseudo-LiDAR from Visual Depth Estimation: Bridging the Gap in 3D Object Detection for Autonomous Driving](https://mlsanity.com/paper/1812.07179/) (2018)
- [VATT: Transformers for Multimodal Self-Supervised Learning from Raw Video, Audio and Text](https://mlsanity.com/paper/2104.11178/) (2021)
- [Multi-Modal Fusion Transformer for End-to-End Autonomous Driving](https://mlsanity.com/paper/2104.09224/) (2021)
- [Enhanced-alignment Measure for Binary Foreground Map Evaluation](https://mlsanity.com/paper/1805.10421/) (2018)
- [Omnidata: A Scalable Pipeline for Making Multi-Task Mid-Level Vision Datasets from 3D Scans](https://mlsanity.com/paper/2110.04994/) (2021)
- [MultiMAE: Multi-modal Multi-task Masked Autoencoders](https://mlsanity.com/paper/2204.01678/) (2022)
- [SegNeXt: Rethinking Convolutional Attention Design for Semantic Segmentation](https://mlsanity.com/paper/2209.08575/) (2022)
- [Function4D: Real-time Human Volumetric Capture from Very Sparse Consumer RGBD Sensors](https://mlsanity.com/paper/2105.01859/) (2021)
- [CMX: Cross-Modal Fusion for RGB-X Semantic Segmentation with Transformers](https://mlsanity.com/paper/2203.04838/) (2022)
- [Omnivore: A Single Model for Many Visual Modalities](https://mlsanity.com/paper/2201.08377/) (2022)
- [Visual Attention Network](https://mlsanity.com/paper/2202.09741/) (2022)
- [Co-SLAM: Joint Coordinate and Sparse Parametric Encodings for Neural Real-Time SLAM](https://mlsanity.com/paper/2304.14377/) (2023)
- [Visual Saliency Transformer](https://mlsanity.com/paper/2104.12099/) (2021)
- [Multimodal Token Fusion for Vision Transformers](https://mlsanity.com/paper/2204.08721/) (2022)
- [Rethinking RGB-D Salient Object Detection: Models, Data Sets, and Large-Scale Benchmarks](https://mlsanity.com/paper/1907.06781/) (2019)
- [Bi-directional Cross-Modality Feature Propagation with Separation-and-Aggregation Gate for RGB-D Semantic Segmentation](https://mlsanity.com/paper/2007.09183/) (2020)
- [Deep Multimodal Fusion by Channel Exchanging](https://mlsanity.com/paper/2011.05005/) (2020)
- [Delivering Arbitrary-Modal Semantic Segmentation](https://mlsanity.com/paper/2303.01480/) (2023)
- [ACNet: Attention Based Network to Exploit Complementary Features for RGBD Semantic Segmentation](https://mlsanity.com/paper/1905.10089/) (2019)

## Built on by (most cited first, 30 of 60)

- [Sigma: Siamese Mamba Network for Multi-Modal Semantic Segmentation](https://mlsanity.com/paper/2404.04256/) (2024)
- [GeminiFusion: Efficient Pixel-wise Multimodal Fusion for Vision Transformer](https://mlsanity.com/paper/2406.01210/) (2024)
- [StitchFusion: Weaving Any Visual Modalities to Enhance Multimodal Semantic Segmentation](https://mlsanity.com/paper/2408.01343/) (2024)
- [DFormerv2: Geometry Self-Attention for RGBD Semantic Segmentation](https://mlsanity.com/paper/2504.04701/) (2025)
- [Efficient Multimodal Semantic Segmentation via Dual-Prompt Learning](https://mlsanity.com/paper/2312.00360/) (2023)
- [Benchmarking Multi-modal Semantic Segmentation under Sensor Failures: Missing and Noisy Modality Robustness](https://mlsanity.com/paper/2503.18445/) (2025)
- [AsymFormer: Asymmetrical Cross-Modal Representation Learning for Mobile Platform Real-Time RGB-D Semantic Segmentation](https://mlsanity.com/paper/2309.14065/) (2023)
- [TeMO: Towards Text-Driven 3D Stylization for Multi-Object Meshes](https://mlsanity.com/paper/2312.04248/) (2023)
- [Strip R-CNN: Large Strip Convolution for Remote Sensing Object Detection](https://mlsanity.com/paper/2501.03775/) (2025)
- [Depth Anything at Any Condition](https://mlsanity.com/paper/2507.01634/) (2025)
- [HAPNet: Toward Superior RGB-Thermal Scene Parsing via Hybrid, Asymmetric, and Progressive Heterogeneous Feature Fusion](https://mlsanity.com/paper/2404.03527/) (2024)
- [RoadFormer+: Delivering RGB-X Scene Parsing through Scale-Aware Information Decoupling and Advanced Heterogeneous Feature Fusion](https://mlsanity.com/paper/2407.21631/) (2024)
- [Ultra-High Resolution Segmentation via Boundary-Enhanced Patch-Merging Transformer](https://mlsanity.com/paper/2412.10181/) (2024)
- [MemorySAM: Memorize Modalities and Semantics with Segment Anything Model 2 for Multi-modal Semantic Segmentation](https://mlsanity.com/paper/2503.06700/) (2025)
- [Rethinking Early-Fusion Strategies for Improved Multispectral Object Detection](https://mlsanity.com/paper/2405.16038/) (2024)
- [LIX: Implicitly Infusing Spatial Geometric Prior Knowledge into Visual Semantic Segmentation for Autonomous Driving](https://mlsanity.com/paper/2403.08215/) (2024)
- [SegSTRONG-C: Segmenting Surgical Tools Robustly On Non-adversarial Generated Corruptions -- An EndoVis'24 Challenge](https://mlsanity.com/paper/2407.11906/) (2024)
- [ShareCMP: Polarization-Aware RGB-P Semantic Segmentation](https://mlsanity.com/paper/2312.03430/) (2023)
- [SSFam: Scribble Supervised Salient Object Detection Family](https://mlsanity.com/paper/2409.04817/) (2024)
- [Revisiting Efficient Semantic Segmentation: Learning Offsets for Better Spatial and Class Feature Alignment](https://mlsanity.com/paper/2508.08811/) (2025)
- [OmniSegmentor: A Flexible Multi-Modal Learning Framework for Semantic Segmentation](https://mlsanity.com/paper/2509.15096/) (2025)
- [TiCoSS: Tightening the Coupling between Semantic Segmentation and Stereo Matching within A Joint Learning Framework](https://mlsanity.com/paper/2407.18038/) (2024)
- [Depth Matters: Exploring Deep Interactions of RGB-D for Semantic Segmentation in Traffic Scenes](https://mlsanity.com/paper/2409.07995/) (2024)
- [Cross-Modal Interactive Perception Network with Mamba for Lung Tumor Segmentation in PET-CT Images](https://mlsanity.com/paper/2503.17261/) (2025)
- [MANGO: Multimodal Attention-based Normalizing Flow Approach to Fusion Learning](https://mlsanity.com/paper/2508.10133/) (2025)
- [UniMRSeg: Unified Modality-Relax Segmentation via Hierarchical Self-Supervised Compensation](https://mlsanity.com/paper/2509.16170/) (2025)
- [SAMSOD: Rethinking SAM Optimization for RGB-T Salient Object Detection](https://mlsanity.com/paper/2510.03689/) (2025)
- [Enhancing Representations through Heterogeneous Self-Supervised Learning](https://mlsanity.com/paper/2310.05108/) (2023)
- [Depth-guided Texture Diffusion for Image Semantic Segmentation](https://mlsanity.com/paper/2408.09097/) (2024)
- [Order-aware Interactive Segmentation](https://mlsanity.com/paper/2410.12214/) (2024)

## Abstract (arXiv)

We present DFormer, a novel RGB-D pretraining framework to learn transferable representations for RGB-D segmentation tasks. DFormer has two new key innovations: 1) Unlike previous works that encode RGB-D information with RGB pretrained backbone, we pretrain the backbone using image-depth pairs from ImageNet-1K, and hence the DFormer is endowed with the capacity to encode RGB-D representations; 2) DFormer comprises a sequence of RGB-D blocks, which are tailored for encoding both RGB and depth information through a novel building block design. DFormer avoids the mismatched encoding of the 3D geometry relationships in depth maps by RGB pretrained backbones, which widely lies in existing methods but has not been resolved. We finetune the pretrained DFormer on two popular RGB-D tasks, i.e., RGB-D semantic segmentation and RGB-D salient object detection, with a lightweight decoder head. Experimental results show that our DFormer achieves new state-of-the-art performance on these two tasks with less than half of the computational cost of the current best methods on two RGB-D semantic segmentation datasets and five RGB-D salient object detection datasets. Our code is available at: https://github.com/VCIP-RGBD/DFormer.