In this paper, we revisit the limitations of anchor-based lane detection
methods, which have predominantly focused on fixed anchors that stem from the
edges of the image, disregarding their versatility and quality. To overcome the
inflexibility of anchors, we decompose them into learning the heat map of
starting points and their associated directions. This decomposition removes the
limitations on the starting point of anchors, making our algorithm adaptable to
different lane types in various datasets. To enhance the quality of anchors, we
introduce the Large Kernel Attention (LKA) for Feature Pyramid Network (FPN).
This significantly increases the receptive field, which is crucial in capturing
the sufficient context as lane lines typically run throughout the entire image.
We have named our proposed system the Anchor Decomposition Network (ADNet).
Additionally, we propose the General Lane IoU (GLIoU) loss, which significantly
improves the performance of ADNet in complex scenarios. Experimental results on
three widely used lane detection benchmarks, VIL-100, CULane, and TuSimple,
demonstrate that our approach outperforms the state-of-the-art methods on
VIL-100 and exhibits competitive accuracy on CULane and TuSimple. Code and
models will be released on this https URL Sephirex-X/ADNet.

本文中，我们重新审视了基于锚点的车道检测方法的局限性，这些方法主要关注来自图像边缘的固定锚点，忽视了锚点的灵活性和质量。为了克服锚点的不灵活性，我们将其分解成起始点的热图和与之相关的方向。此分解消除了锚点起始点的限制，使得我们的算法能够适应不同数据集中的不同车道类型。为了提高锚点的质量，我们引入了 Feature Pyramid Network (FPN) 的 Large Kernel Attention (LKA)。这显著增加了感受野，对于捕捉足够的上下文是至关重要的，因为车道线通常贯穿整个图像。我们将我们提出的系统命名为 Anchor Decomposition Network (ADNet)。此外，我们提出了 General Lane IoU (GLIoU) 损失，该损失显著改善了 ADNet 在复杂场景中的性能。对 VIL-100、CULane 和 TuSimple 这三个广泛使用的车道检测基准进行的实验结果表明，我们的方法在 VIL-100 上优于现有方法，并在 CULane 和 TuSimple 上表现出竞争力。代码和模型将在此 URL https Sephirex-X/ADNet 上发布。

ADNet: 通过锚点分解进行车道形状预测

ADNet: Lane Shape Prediction via Anchor Decomposition

By exploiting large kernel decomposition and attention mechanisms,
convolutional neural networks (CNN) can compete with transformer-based methods
in many high-level computer vision tasks. However, due to the advantage of
long-range modeling, the transformers with self-attention still dominate the
low-level vision, including the super-resolution task. In this paper, we
propose a CNN-based multi-scale attention network (MAN), which consists of
multi-scale large kernel attention (MLKA) and a gated spatial attention unit
(GSAU), to improve the performance of convolutional SR networks. Within our
MLKA, we rectify LKA with multi-scale and gate schemes to obtain the abundant
attention map at various granularity levels, therefore jointly aggregating
global and local information and avoiding the potential blocking artifacts. In
GSAU, we integrate gate mechanism and spatial attention to remove the
unnecessary linear layer and aggregate informative spatial context. To confirm
the effectiveness of our designs, we evaluate MAN with multiple complexities by
simply stacking different numbers of MLKA and GSAU. Experimental results
illustrate that our MAN can achieve varied trade-offs between state-of-the-art
performance and computations. Code is available at
this https URL

本文提出了一个卷积神经网络（CNN）的多尺度关注网络（MAN），其中包括多尺度大型核关注（MLKA）和门控空间关注单元（GSAU），以提高卷积 SR 网络的性能。实验结果表明，我们的 MAN 可以在不同的状态下实现各种平衡。