Author name cluster

Kai Ni

Possible papers associated with this exact author name in Arrow. This page groups case-insensitive exact name matches and is not a full identity disambiguation profile.

3 papers

2 author rows

AAAI Conference 2024 Conference Paper

Geometry-Guided Domain Generalization for Monocular 3D Object Detection

Fan Yang
Hui Chen
Yuwei He
Sicheng Zhao
Chenghao Zhang
Kai Ni
Guiguang Ding

Monocular 3D object detection (M3OD) is important for autonomous driving. However, existing deep learning-based methods easily suffer from performance degradation in real-world scenarios due to the substantial domain gap between training and testing. M3OD's domain gaps are complex, including camera intrinsic parameters, extrinsic parameters, image appearance, etc. Existing works primarily focus on the domain gaps of camera intrinsic parameters, ignoring other key factors. Moreover, at the feature level, conventional domain invariant learning methods generally cause the negative transfer issue, due to the ignorance of dependency between geometry tasks and domains. To tackle these issues, in this paper, we propose MonoGDG, a geometry-guided domain generalization framework for M3OD, which effectively addresses the domain gap at both camera and feature levels. Specifically, MonoGDG consists of two major components. One is geometry-based image reprojection, which mitigates the impact of camera discrepancy by unifying intrinsic parameters, randomizing camera orientations, and unifying the field of view range. The other is geometry-dependent feature disentanglement, which overcomes the negative transfer problems by incorporating domain-shared and domain-specific features. Additionally, we leverage a depth-disentangled domain discriminator and a domain-aware geometry regression attention mechanism to account for the geometry-domain dependency. Extensive experiments on multiple autonomous driving benchmarks demonstrate that our method achieves state-of-the-art performance in domain generalization for M3OD.

PDF Details DOI

ICML Conference 2023 Conference Paper

Boosting Graph Contrastive Learning via Graph Contrastive Saliency

Chunyu Wei
Yu Wang
Bing Bai
Kai Ni
David Brady
Lu Fang

Graph augmentation plays a crucial role in achieving good generalization for contrastive graph self-supervised learning. However, mainstream Graph Contrastive Learning (GCL) often favors random graph augmentations, by relying on random node dropout or edge perturbation on graphs. Random augmentations may inevitably lead to semantic information corruption during the training, and force the network to mistakenly focus on semantically irrelevant environmental background structures. To address these limitations and to improve generalization, we propose a novel self-supervised learning framework for GCL, which can adaptively screen the semantic-related substructure in graphs by capitalizing on the proposed gradient-based Graph Contrastive Saliency (GCS). The goal is to identify the most semantically discriminative structures of a graph via contrastive learning, such that we can generate semantically meaningful augmentations by leveraging on saliency. Empirical evidence on 16 benchmark datasets demonstrates the exclusive merits of the GCS-based framework. We also provide rigorous theoretical justification for GCS’s robustness properties. Code is available at https: //github. com/GCS2023/GCS.

Details

IROS Conference 2012 Conference Paper

Robust optimization of factor graphs by using condensed measurements

Giorgio Grisetti
Rainer Kümmerle
Kai Ni

Popular problems in robotics and computer vision like simultaneous localization and mapping (SLAM) or structure from motion (SfM) require to solve a least-squares problem that can be effectively represented by factor graphs. The chance to find the global minimum of such problems depends on both the initial guess and the non-linearity of the sensor models. In this paper we propose an approach to determine an approximation of the original problem that has a larger convergence basin. To this end, we employ a divide-and-conquer approach that exploits the structure of the factor graph. Our approach has been validated on real-world and simulated experiments and is able to succeed in finding the global minimum in situations where other state-of-the-art methods fail.

Details