S$^3$-MonoDETR: Supervised Shape&Scale-perceptive Deformable Transformer for Monocular 3D Object Detection
This work addresses a key bottleneck in monocular 3D object detection for autonomous driving systems, offering a novel solution to enhance multi-category detection in a single training process.
The paper tackles the problem of noisy features in transformer-based monocular 3D object detection by proposing a Supervised Shape&Scale-perceptive Deformable Attention (S³-DA) module, which improves detection accuracy and achieves state-of-the-art performance on KITTI and Waymo Open datasets for both single-category and multi-category detection.
Recently, transformer-based methods have shown exceptional performance in monocular 3D object detection, which can predict 3D attributes from a single 2D image. These methods typically use visual and depth representations to generate query points on objects, whose quality plays a decisive role in the detection accuracy. However, current unsupervised attention mechanisms without any geometry appearance awareness in transformers are susceptible to producing noisy features for query points, which severely limits the network performance and also makes the model have a poor ability to detect multi-category objects in a single training process. To tackle this problem, this paper proposes a novel ``Supervised Shape&Scale-perceptive Deformable Attention'' (S$^3$-DA) module for monocular 3D object detection. Concretely, S$^3$-DA utilizes visual and depth features to generate diverse local features with various shapes and scales and predict the corresponding matching distribution simultaneously to impose valuable shape&scale perception for each query. Benefiting from this, S$^3$-DA effectively estimates receptive fields for query points belonging to any category, enabling them to generate robust query features. Besides, we propose a Multi-classification-based Shape&Scale Matching (MSM) loss to supervise the above process. Extensive experiments on KITTI and Waymo Open datasets demonstrate that S$^3$-DA significantly improves the detection accuracy, yielding state-of-the-art performance of single-category and multi-category 3D object detection in a single training process compared to the existing approaches. The source code will be made publicly available at https://github.com/mikasa3lili/S3-MonoDETR.