paper-with-me

Papers

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

2025-02-10 · Sicen Guo, Tianyou Wen, Chuang-Wei Liu, Qijun Chen, Rui Fan

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.

📄 PDF Abstract BibTeX arXiv:2502.06219

Code (0)

등록된 구현이 없습니다.

Tasks

Depth EstimationDepth PredictionScene Parsing

Methods 이 논문이 사용한 방법론

Attention 설명 없음
Linear Layer A Linear Layer is a projection $\mathbf{XW + b}$.
Multi-Head Attention 설명 없음
Position-Wise Feed-Forward Layer 설명 없음
Adam 설명 없음
Softmax The Softmax output function transforms a previous layer's output into a vector of probabilities. It is commonly used for multiclass classification. Given an input vector $x$…
Dropout Dropout is a regularization technique for neural networks that drops a unit (along with connections) at training time with a specified probability $p$ (a common value is…
Absolute Position Encodings Absolute Position Encodings are a type of position embeddings for [Transformer-based models] where positional encodings are…

Similar Papers 제목 키워드 기반

ProFound: A moderate-sized vision foundation model for multi-task prostate imaging

2026-03-04 · Yipei Wang, Yinsong Xu, Weixi Yi, Shaheer Ullah Saeed 외 arxiv

Many diagnostic and therapeutic clinical tasks for prostate cancer increasingly rely on multi-parametric MRI. Automating these tasks is challenging because they necessitate expert interpretations, which are difficult to …

Divide and Conquer: Decoupled Representation Alignment for Multimodal World Models

2026-05-03 · Junyuan Xiao, Dingkang Liang, Xin Zhou, Yixuan Ye 외 arxiv

Emerging multi-modal world models attempt to jointly generate videos across diverse modalities (e.g., RGB, depth, and mask), yet they fail to fully exploit the rich priors of existing foundation models. We propose $M^2$-…

Video Generation

A Comprehensive Survey on Segment Anything Model for Vision and Beyond

2023-05-14 · Chunhui Zhang, Li Liu, Yawen Cui, Guanjie Huang 외

Artificial intelligence (AI) is evolving towards artificial general intelligence, which refers to the ability of an AI system to perform a wide range of tasks and exhibit a level of intelligence similar to that of a huma…

TP-DRSeg: Improving Diabetic Retinopathy Lesion Segmentation with Explicit Text-Prompts Assisted SAM

2024-06-22 · Wenxue Li, Xinyu Xiong, Peng Xia, Lie Ju 외

Recent advances in large foundation models, such as the Segment Anything Model (SAM), have demonstrated considerable promise across various tasks. Despite their progress, these models still encounter challenges in specia…

Lesion SegmentationMedical Image AnalysisSegmentation

TransMed: Large Language Models Enhance Vision Transformer for Biomedical Image Classification

2023-12-12 · Kaipeng Zheng, Weiran Huang, Lichao Sun

Few-shot learning has been studied to adapt models to tasks with very few samples. It holds profound significance, particularly in clinical tasks, due to the high annotation cost of medical images. Several works have exp…

Few-Shot Learningimage-classificationImage Classification