PriorLane: A Prior Knowledge Enhanced Lane Detection Approach Based on
Transformer
- URL: http://arxiv.org/abs/2209.06994v1
- Date: Thu, 15 Sep 2022 01:48:08 GMT
- Title: PriorLane: A Prior Knowledge Enhanced Lane Detection Approach Based on
Transformer
- Authors: Qibo Qiu, Haiming Gao, Wei Hua, Gang Huang and Xiaofei He
- Abstract summary: PriorLane is used to enhance the segmentation performance of the fully vision transformer.
PriorLane utilizes an encoder-only transformer to fuse the feature extracted by a pre-trained segmentation model with prior knowledge embeddings.
Experiments on our Zjlab dataset show that Prior-Lane outperforms SOTA lane detection methods by a 2.82% mIoU.
- Score: 10.55399679259444
- License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
- Abstract: Lane detection is one of the fundamental modules in self-driving. In this
paper we employ a transformer-only method for lane detection, thus it could
benefit from the blooming development of fully vision transformer and achieves
the state-of-the-art (SOTA) performance on both CULane and TuSimple benchmarks,
by fine-tuning the weight fully pre-trained on large datasets. More
importantly, this paper proposes a novel and general framework called
PriorLane, which is used to enhance the segmentation performance of the fully
vision transformer by introducing the low-cost local prior knowledge. PriorLane
utilizes an encoder-only transformer to fuse the feature extracted by a
pre-trained segmentation model with prior knowledge embeddings. Note that a
Knowledge Embedding Alignment (KEA) module is adapted to enhance the fusion
performance by aligning the knowledge embedding. Extensive experiments on our
Zjlab dataset show that Prior-Lane outperforms SOTA lane detection methods by a
2.82% mIoU, and the code will be released at: https://github.
com/vincentqqb/PriorLane.
Related papers
- Remote Sensing Change Detection With Transformers Trained from Scratch [62.96911491252686]
transformer-based change detection (CD) approaches either employ a pre-trained model trained on large-scale image classification ImageNet dataset or rely on first pre-training on another CD dataset and then fine-tuning on the target benchmark.
We develop an end-to-end CD approach with transformers that is trained from scratch and yet achieves state-of-the-art performance on four public benchmarks.
arXiv Detail & Related papers (2023-04-13T17:57:54Z) - Integral Migrating Pre-trained Transformer Encoder-decoders for Visual
Object Detection [78.2325219839805]
imTED improves the state-of-the-art of few-shot object detection by up to 7.6% AP.
Experiments on MS COCO dataset demonstrate that imTED consistently outperforms its counterparts by 2.8%.
arXiv Detail & Related papers (2022-05-19T15:11:20Z) - An Extendable, Efficient and Effective Transformer-based Object Detector [95.06044204961009]
We integrate Vision and Detection Transformers (ViDT) to construct an effective and efficient object detector.
ViDT introduces a reconfigured attention module to extend the recent Swin Transformer to be a standalone object detector.
We extend it to ViDT+ to support joint-task learning for object detection and instance segmentation.
arXiv Detail & Related papers (2022-04-17T09:27:45Z) - Laneformer: Object-aware Row-Column Transformers for Lane Detection [96.62919884511287]
Laneformer is a transformer-based architecture tailored for lane detection in autonomous driving.
Inspired by recent advances of the transformer encoder-decoder architecture in various vision tasks, we move forwards to design a new end-to-end Laneformer architecture.
arXiv Detail & Related papers (2022-03-18T10:14:35Z) - TransDARC: Transformer-based Driver Activity Recognition with Latent
Space Feature Calibration [31.908276711898548]
We present a vision-based framework for recognizing secondary driver behaviours based on visual transformers and an augmented feature distribution calibration module.
Our framework consistently leads to better recognition rates, surpassing previous state-of-the-art results of the public Drive&Act benchmark on all levels.
arXiv Detail & Related papers (2022-03-02T08:14:06Z) - TransKD: Transformer Knowledge Distillation for Efficient Semantic
Segmentation [51.93878604106518]
Transformer-based Knowledge Distillation (TransKD) framework learns compact student transformers by distilling both feature maps and patch embeddings of large teacher transformers.
Experiments on Cityscapes, ACDC, NYUv2, and Pascal VOC2012 datasets show that TransKD outperforms state-of-the-art distillation frameworks and rivals the time-consuming pre-training method.
arXiv Detail & Related papers (2022-02-27T16:34:10Z) - ViDT: An Efficient and Effective Fully Transformer-based Object Detector [97.71746903042968]
Detection transformers are the first fully end-to-end learning systems for object detection.
vision transformers are the first fully transformer-based architecture for image classification.
In this paper, we integrate Vision and Detection Transformers (ViDT) to build an effective and efficient object detector.
arXiv Detail & Related papers (2021-10-08T06:32:05Z)
This list is automatically generated from the titles and abstracts of the papers in this site.
This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.