Author name cluster

Xiaoming Hu

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.

5 papers

2 author rows

AAAI Conference 2024 Conference Paper

A Dynamic Learning Method towards Realistic Compositional Zero-Shot Learning

Xiaoming Hu
Zilei Wang

To tackle the challenge of recognizing images of unseen attribute-object compositions, Compositional Zero-Shot Learning (CZSL) methods have been previously addressed. However, test images in realistic scenarios may also incorporate other forms of unknown factors, such as novel semantic concepts or novel image styles. As previous CZSL works have overlooked this critical issue, in this research, we first propose the Realistic Compositional Zero-Shot Learning (RCZSL) task which considers the various types of unknown factors in an unified experimental setting. To achieve this, we firstly conduct re-labelling on MIT-States and use the pre-trained generative models to obtain images of various domains. Then the entire dataset is split into a training set and a test set, with the latter containing images of unseen concepts, unseen compositions, unseen domains as well as their combinations. Following this, we show that the visual-semantic relationship changes on unseen images, leading us to construct two dynamic modulators to adapt the visual features and composition prototypes in accordance with the input image. We believe that such a dynamic learning method could effectively alleviate the domain shift problem caused by various types of unknown factors. We conduct extensive experiments on benchmark datasets for both the conventional CZSL setting and the proposed RCZSL setting. The effectiveness of our method has been proven by empirical results, which significantly outperformed both our baseline method and state-of-the-art approaches.

PDF Details DOI

AAAI Conference 2023 Conference Paper

Leveraging Sub-class Discimination for Compositional Zero-Shot Learning

Xiaoming Hu
Zilei Wang

Compositional Zero-Shot Learning (CZSL) aims at identifying unseen compositions composed of previously seen attributes and objects during the test phase. In real images, the visual appearances of attributes and objects (primitive concepts) generally interact with each other. Namely, the visual appearances of an attribute may change when composed with different objects, and vice versa. But previous works overlook this important property. In this paper, we introduce a simple yet effective approach with leveraging sub-class discrimination. Specifically, we define the primitive concepts in different compositions as sub-classes, and then maintain the sub-class discrimination to address the above challenge. More specifically, inspired by the observation that the composed recognition models could account for the differences across sub-classes, we first propose to impose the embedding alignment between the composed and disentangled recognition to incorporate sub-class discrimination at the feature level. Then we develop the prototype modulator networks to adjust the class prototypes w.r.t. the composition information, which can enhance sub-class discrimination at the classifier level. We conduct extensive experiments on the challenging benchmark datasets, and the considerable performance improvement over state-of-the-art approaches is achieved, which indicates the effectiveness of our method. Our code is available at https://github.com/hxm97/SCD-CZSL.

PDF Details DOI

AAAI Conference 2021 Conference Paper

Learning Intact Features by Erasing-Inpainting for Few-shot Classification

Junjie Li
Zilei Wang
Xiaoming Hu

Few-shot classification aims to categorize the samples from unseen classes with only few labeled samples. To address such a challenge, many methods exploit a base set consisting of massive labeled samples to learn an instance embedding function, i. e. , image feature extractor, and it is expected to possess good transferability among different tasks. Such characteristics of few-shot learning are essentially different from that of traditional image classification only pursuing to get discriminative image representations. In this paper, we propose to learn intact features by erasing-inpainting for fewshot classification. Specifically, we argue that extracting intact features of target objects is more transferable, and then propose a novel cross-set erasing-inpainting (CSEI) method. CSEI processes the images in the support set using erasing and inpainting, and then uses them to augment the query set of the same task. Consequently, the feature embedding produced by our proposed method can contain more complete information of target objects. In addition, we propose taskspecific feature modulation to make the features adaptive to the current task. The extensive experiments on two widely used benchmarks well demonstrates the effectiveness of our proposed method, which can consistently get considerable performance gains for different baseline methods.

PDF Details

EAAI Journal 2020 Journal Article

Fuzzy adaptive automatic train operation control with protection constraints: A residual nonlinearity approximation-based approach

Shigen Gao
Jin Wei
Haifeng Song
Zixuan Zhang
Hairong Dong
Xiaoming Hu

In this study, we present fuzzy adaptive control based on residual nonlinearity approximation in the presence of protection constraints for the target trajectory tracking problem observed in automatic train operation. Herein, protection constraints refer to a condition wherein the speed and position of a controlled train are not allowed to surpass the boundaries imposed by automatic train protection and moving authority. By defining proper coordinate transformation, the protection constraints are converted to an error-prescribed performance control problem that facilitates operational efficiency by reducing the margin with respect to target trajectories. Based on the prescribed performance control methodology, we present an improved scheme using fuzzy residual nonlinearity approximation and establish the uniformly ultimately boundedness (UUB) property. A novel feature therein is that the ultimate boundary of the proposed scheme is simultaneously characterized by the prescribed performance functions and control parameters, with rigorous and analytically mathematical expressions; while pioneering the prescribed performance control methodology, the ultimate boundary is characterized solely by the prescribed performance functions. To verify the effectiveness and advantages of the proposed scheme, the controllers are applied to the automatic train operation on the Beijing Yizhuang line, which contains 13 operational intervals. Finally, comparative and simulation results are presented to validate the proposed method.

Details DOI

ICRA Conference 2000 Conference Paper

Nonlinear Pitch and Roll Estimation for Walking Robots

Henrik Rehbinder
Xiaoming Hu

We study a nonlinear pitch and roll estimation problem for a 4-rigid body, aiming at a walking robot application. The approach taken is that sensor data from rate gyros and inclinometers are combined using a high-gain observer that can be proven to be exponentially convergent. The algorithm has successfully been evaluated experimentally during conditions resembling walking robot motion and has been compared with the more standard extended Kalman filter (EKF). It is shown that the much simpler high-gain observer performs slightly better than the EKF and that both algorithms provide small and bounded estimation errors.

Details