# Fully Exploiting Vision Foundation Model's Profound Prior Knowledge for Generalizable RGB-Depth Driving Scene Parsing

arXiv: https://arxiv.org/abs/2502.06219 · HTML: https://mlsanity.com/paper/2502.06219/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Builds on 50 of its 65 references that are in the map.
- First posted on arXiv 10 Feb 2025.

## Builds on (most cited first, 30 of 50)

- [Deep Residual Learning for Image Recognition](https://mlsanity.com/paper/1512.03385/) (2015)
- [Swin Transformer: Hierarchical Vision Transformer using Shifted Windows](https://mlsanity.com/paper/2103.14030/) (2021)
- [Segment Anything](https://mlsanity.com/paper/2304.02643/) (2023)
- [DINOv2: Learning Robust Visual Features without Supervision](https://mlsanity.com/paper/2304.07193/) (2023)
- [EfficientNet: Rethinking Model Scaling for Convolutional Neural Networks](https://mlsanity.com/paper/1905.11946/) (2019)
- [Layer Normalization](https://mlsanity.com/paper/1607.06450/) (2016)
- [The Cityscapes Dataset for Semantic Urban Scene Understanding](https://mlsanity.com/paper/1604.01685/) (2016)
- [SegFormer: Simple and Efficient Design for Semantic Segmentation with Transformers](https://mlsanity.com/paper/2105.15203/) (2021)
- [Masked-attention Mask Transformer for Universal Image Segmentation](https://mlsanity.com/paper/2112.01527/) (2021)
- [Depth Anything V2](https://mlsanity.com/paper/2406.09414/) (2024)
- [Depth Anything: Unleashing the Power of Large-Scale Unlabeled Data](https://mlsanity.com/paper/2401.10891/) (2024)
- [UNet++: Redesigning Skip Connections to Exploit Multiscale Features in Image Segmentation](https://mlsanity.com/paper/1912.05074/) (2019)
- [Segmentation Transformer: Object-Contextual Representations for Semantic Segmentation](https://mlsanity.com/paper/1909.11065/) (2019)
- [Vision Transformer Adapter for Dense Predictions](https://mlsanity.com/paper/2205.08534/) (2022)
- [DriveLM: Driving with Graph Visual Question Answering](https://mlsanity.com/paper/2312.14150/) (2023)
- [RAFT-Stereo: Multilevel Recurrent Field Transforms for Stereo Matching](https://mlsanity.com/paper/2109.07547/) (2021)
- [Incorporating Convolution Designs into Visual Transformers](https://mlsanity.com/paper/2103.11816/) (2021)
- [K-Net: Towards Unified Image Segmentation](https://mlsanity.com/paper/2106.14855/) (2021)
- [Expectation-Maximization Attention Networks for Semantic Segmentation](https://mlsanity.com/paper/1907.13426/) (2019)
- [Bi-directional Cross-Modality Feature Propagation with Separation-and-Aggregation Gate for RGB-D Semantic Segmentation](https://mlsanity.com/paper/2007.09183/) (2020)
- [LiDAR-LLM: Exploring the Potential of Large Language Models for 3D LiDAR Understanding](https://mlsanity.com/paper/2312.14074/) (2023)
- [Salient Object Detection: A Discriminative Regional Feature Integration Approach](https://mlsanity.com/paper/1410.5926/) (2014)
- [Efficient RGB-D Semantic Segmentation for Indoor Scene Analysis](https://mlsanity.com/paper/2011.06961/) (2020)
- [FaPN: Feature-aligned Pyramid Network for Dense Image Prediction](https://mlsanity.com/paper/2108.07058/) (2021)
- [Hierarchical Dynamic Filtering Network for RGB-D Salient Object Detection](https://mlsanity.com/paper/2007.06227/) (2020)
- [SNE-RoadSeg: Incorporating Surface Normal Information into Semantic Segmentation for Accurate Freespace Detection](https://mlsanity.com/paper/2008.11351/) (2020)
- [Three Ways to Improve Semantic Segmentation with Self-Supervised Depth Estimation](https://mlsanity.com/paper/2012.10782/) (2020)
- [ViT-CoMer: Vision Transformer with Convolutional Multi-scale Feature Interaction for Dense Predictions](https://mlsanity.com/paper/2403.07392/) (2024)
- [Conv-Adapter: Exploring Parameter Efficient Transfer Learning for ConvNets](https://mlsanity.com/paper/2208.07463/) (2022)
- [GFF: Gated Fully Fusion for Semantic Segmentation](https://mlsanity.com/paper/1904.01803/) (2019)

## Abstract (arXiv)

Recent vision foundation models (VFMs), typically based on Vision Transformer (ViT), have significantly advanced numerous computer vision tasks. Despite their success in tasks focused solely on RGB images, the potential of VFMs in RGB-depth driving scene parsing remains largely under-explored. In this article, we take one step toward this emerging research area by investigating a feasible technique to fully exploit VFMs for generalizable RGB-depth driving scene parsing. Specifically, we explore the inherent characteristics of RGB and depth data, thereby presenting a Heterogeneous Feature Integration Transformer (HFIT). This network enables the efficient extraction and integration of comprehensive heterogeneous features without re-training ViTs. Relative depth prediction results from VFMs, used as inputs to the HFIT side adapter, overcome the limitations of the dependence on depth maps. Our proposed HFIT demonstrates superior performance compared to all other traditional single-modal and data-fusion scene parsing networks, pre-trained VFMs, and ViT adapters on the Cityscapes and KITTI Semantics datasets. We believe this novel strategy paves the way for future innovations in VFM-based data-fusion techniques for driving scene parsing. Our source code is publicly available at https://mias.group/HFIT.