publications
You can also find me on Google Scholar.
2024
-
Evolving Parameterized Prompt Memory for Continual LearningProceedings of the AAAI Conference on Artificial Intelligence (AAAI), 2024Recent studies have demonstrated the potency of leveraging prompts in Transformers for continual learning (CL). Nevertheless, employing a discrete key-prompt bottleneck can lead to selection mismatches and inappropriate prompt associations during testing. Furthermore, this approach hinders adaptive prompting due to the lack of shareability among nearly identical instances at more granular level. To address these challenges, we introduce the Evolving Parameterized Prompt Memory (EvoPrompt), a novel method involving adaptive and continuous prompting attached to pre-trained Vision Transformer (ViT), conditioned on specific instance. We formulate a continuous prompt function as a neural bottleneck and encode the collection of prompts on network weights. We establish a paired prompt memory system consisting of a stable reference and a flexible working prompt memory. Inspired by linear mode connectivity, we progressively fuse the working prompt memory and reference prompt memory during inter-task periods, resulting in continually evolved prompt memory. This fusion involves aligning functionally equivalent prompts using optimal transport and aggregating them in parameter space with an adjustable bias based on prompt node attribution. Additionally, to enhance backward compatibility, we propose compositional classifier initialization, which leverages prior prototypes from pre-trained models to guide the initialization of new classifiers in a subspace-aware manner. Comprehensive experiments validate that our approach achieves state-of-the-art performance in both class and domain incremental learning scenarios.
@article{kurniawan2024evoprompt, title = {Evolving Parameterized Prompt Memory for Continual Learning}, author = {Kurniawan, Muhammad Rifki and Song, Xiang and Ma, Zhiheng and He, Yuhang and Gong, Yihong and Qi, Yang and Wei, Xing}, year = {2024}, journal = {Proceedings of the AAAI Conference on Artificial Intelligence (AAAI)}, }
2023
-
Topology-preserving transfer learning for weakly-supervised anomaly detection and segmentationPattern Recognition Letters, 2023Models pre-trained on the ImageNet dataset are introduced to be exploited for knowledge transfer in numerous downstream computer vision tasks, including the weakly-supervised anomaly detection and segmentation area. Specifically, in anomaly segmentation, the former study shows that representing images with feature maps extracted by pre-trained models significantly improves over previous techniques. This kind of representation method requires both high-quality and task-specific features, but feature extractors obtained from ImageNet directly are very general. One intuition for obtaining stronger features is by transferring a pre-trained model to the target dataset. However, in this paper, we show that under weakly-supervised settings, naïve fine-tune techniques that typically work for supervised learning can lead to catastrophic feature space collapse and reduce performance greatly. Thus, we propose to apply a topology-preserving constraint during transferring. Our method preserves the topology graph to keep the feature space from collapsing under weakly-supervised settings. And then we combine the transferred model with a simple anomaly detection and segmentation baseline for performance evaluation. The experiments show that our method achieves competitive accuracy on several benchmarks meanwhile setting a new state-of-the-art for anomaly detection on CIFAR100/10 and BTAD datasets.
@article{WEI202377, title = {Topology-preserving transfer learning for weakly-supervised anomaly detection and segmentation}, author = {Wei, Shenxing and Wei, Xing and Kurniawan, Muhammad Rifki and Ma, Zhiheng and Gong, Yihong}, journal = {Pattern Recognition Letters}, volume = {170}, pages = {77-84}, issn = {0167-8655}, year = {2023}, doi = {https://doi.org/10.1016/j.patrec.2023.04.019}, }
2021
-
Online Continual Learning via Multiple Deep Metric Learning and Uncertainty-guided Episodic Memory Replay - 3rd Place Solution for ICCV 2021 Workshop SSLAD Track 3A Continual Object ClassificationMuhammad Rifki Kurniawan, Xing Wei, and Yihong GongArXiv, 2021Online continual learning in the wild is a very difficult task in machine learning. Non-stationarity in online continual learning potentially brings about catastrophic forgetting in neural networks. Specifically, online continual learning for autonomous driving with SODA10M dataset exhibits extra problems on extremely long-tailed distribution with continuous distribution shift. To address these problems, we propose multiple deep metric representation learning via both contrastive and supervised contrastive learning alongside soft labels distillation to improve model generalization. Moreover, we exploit modified class-balanced focal loss for sensitive penalization in class imbalanced and hard-easy samples. We also store some samples under guidance of uncertainty metric for rehearsal and perform online and periodical memory updates. Our proposed method achieves considerable generalization with average mean class accuracy (AMCA) 64.01% on validation and 64.53% AMCA on test set.
@article{Kurniawan2021OnlineCL, title = {Online Continual Learning via Multiple Deep Metric Learning and Uncertainty-guided Episodic Memory Replay - 3rd Place Solution for ICCV 2021 Workshop SSLAD Track 3A Continual Object Classification}, author = {Kurniawan, Muhammad Rifki and Wei, Xing and Gong, Yihong}, journal = {ArXiv}, volume = {abs/2111.02757}, year = {2021}, }
2019
- AIPOptimization of neural network based on hybrid method of genetic algorithm and particle swarm optimization for maritime weather forecasting in buoyweather station type IISyamsul Arifin, Dvitiya Srestha Prajna Mahistha, Magfiroh Fatwaning Ukhti, Muhammad Rifki Kurniawan, and Aulia Siti AisjahAIP Conference Proceedings, 2019
The object the research is to forecast maritime weather variables such wind speed and direction, temperature and wave height for an hour ahead by using artificial intelligence approach. Artificial intelligence is comprised of hybrid neural networks modified by genetic algorithms and particle swarm optimization which are functioned as a model predictor. The hybrid predictor works on every single predictor by weighing both artificial neural network-genetic algorithm (ANN-GA) and artificial neural network-particle swarm optimization (ANN-PSO) which weight is calculated by differential evolution algorithm optimization. When the unsurpassed model is obtained, it will be validated across real-time data that is delivered from type II buoyweather station measurement at the Madura Strait, Java Sea. The prediction results of learning and validation process indicate that the ANN-Hybrid predictor perform more accurate than the ANN-GA and ANN PSO on training and validation. However, the gap of RMSE on real-time test is relatively high compared to validation or training. It can be influenced by the different frequent of weather fluctuation between them. Concurring to real-time test stage, the foremost appropriate variable that predicted by this ANN-Hybrid is temperature.
@article{doi:10.1063/1.5095287, title = {Optimization of neural network based on hybrid method of genetic algorithm and particle swarm optimization for maritime weather forecasting in buoyweather station type II}, author = {Arifin, Syamsul and Mahistha, Dvitiya Srestha Prajna and Ukhti, Magfiroh Fatwaning and Kurniawan, Muhammad Rifki and Aisjah, Aulia Siti}, journal = {AIP Conference Proceedings}, volume = {2088}, number = {1}, pages = {020035}, numpages = {0}, year = {2019}, doi = {10.1063/1.5095287}, } - Bachelor ThesisPerancangan Mobile Predictor Cuaca Maritim Menggunakan Metode Hybrid Logika Fuzzy Tipe 2-Jaringan Syaraf Tiruan dengan Optimasi Algoritma Differential EvolutionMuhammad Rifki Kurniawan, Syamsul Arifin, and Aulia Siti AisjahAIP Conference Proceedings, 2019
@article{kurniawanperancangan, title = {Perancangan Mobile Predictor Cuaca Maritim Menggunakan Metode Hybrid Logika Fuzzy Tipe 2-Jaringan Syaraf Tiruan dengan Optimasi Algoritma Differential Evolution}, author = {Kurniawan, Muhammad Rifki and Arifin, Syamsul and Aisjah, Aulia Siti}, journal = {AIP Conference Proceedings}, year = {2019}, doi = {10.13140/RG.2.2.27518.84803}, }