General Place Recognition Survey: Towards the Real-world Autonomy Age

1 code implementation • 9 Sep 2022 • Peng Yin, Shiqi Zhao, Ivan Cisneros, Abulikemu Abuduweili, Guoquan Huang, Micheal Milford, Changliu Liu, Howie Choset, Sebastian Scherer

A summary of this work and our datasets and evaluation API is publicly available to the robotics community at: https://github. com/MetaSLAM/GPRS.

Loop Closure Detection Simultaneous Localization and Mapping

BioSLAM: A Bio-inspired Lifelong Memory System for General Place Recognition

no code implementations • 30 Aug 2022 • Peng Yin, Abulikemu Abuduweili, Shiqi Zhao, Changliu Liu, Sebastian Scherer

We present BioSLAM, a lifelong SLAM framework for learning various new appearances incrementally and maintaining accurate place recognition for previously visited areas.

An Optical Controlling Environment and Reinforcement Learning Benchmarks

1 code implementation • 23 Mar 2022 • Abulikemu Abuduweili, Changliu Liu

Deep reinforcement learning has the potential to address various scientific problems.

reinforcement-learning Reinforcement Learning (RL)

An Optics Controlling Environment and Reinforcement Learning Benchmarks

no code implementations • 29 Sep 2021 • Abulikemu Abuduweili

Deep reinforcement learning has the potential to address various scientific problems.

reinforcement-learning Reinforcement Learning (RL)

Property-Aware Relation Networks for Few-Shot Molecular Property Prediction

no code implementations • NeurIPS 2021 • Yaqing Wang, Abulikemu Abuduweili, Quanming Yao, Dejing Dou

the target property, such that the limited labels can be effectively propagated among similar molecules.

Drug Discovery Graph Learning +2

Escaping the Big Data Paradigm with Compact Transformers

6 code implementations • 12 Apr 2021 • Ali Hassani, Steven Walton, Nikhil Shah, Abulikemu Abuduweili, Jiachen Li, Humphrey Shi

Our models are flexible in terms of model size, and can have as little as 0. 28M parameters while achieving competitive results.

Fine-Grained Image Classification Superpixel Image Classification

Adaptive Consistency Regularization for Semi-Supervised Transfer Learning

1 code implementation • CVPR 2021 • Abulikemu Abuduweili, Xingjian Li, Humphrey Shi, Cheng-Zhong Xu, Dejing Dou

To better exploit the value of both pre-trained weights and unlabeled target examples, we introduce adaptive consistency regularization that consists of two complementary components: Adaptive Knowledge Consistency (AKC) on the examples between the source and target model, and Adaptive Representation Consistency (ARC) on the target model between labeled and unlabeled examples.

Pseudo Label Transfer Learning

Robust Online Model Adaptation by Extended Kalman Filter with Exponential Moving Average and Dynamic Multi-Epoch Strategy

1 code implementation • L4DC 2020 • Abulikemu Abuduweili, Changliu Liu

The challenge motivates the adoption of online adaptation algorithms to update prediction models in real-time to improve the prediction performance.

Adaptable Human Intention and Trajectory Prediction for Human-Robot Collaboration

1 code implementation • 11 Sep 2019 • Abulikemu Abuduweili, Siyan Li, Changliu Liu

The effectiveness and flexibility of the proposed method has been validated in experiments.

Robotics

Efficient Method for Categorize Animals in the Wild

1 code implementation • 30 Jul 2019 • Abulikemu Abuduweili, Xin Wu, Xingchen Tao

Thanks to advanced regularization strategies and ensemble learning, we got top 7/336 places in the final leaderboard.

Ensemble Learning General Classification +1

Automatic Generation of Personalized Comment Based on User Profile

1 code implementation • ACL 2019 • Wenhuan Zeng, Abulikemu Abuduweili, Lei LI, Pengcheng Yang

Comments on social media are very diverse, in terms of content, style and vocabulary, which make generating comments much more challenging than other existing natural language generation~(NLG) tasks.

Text Generation