Muhammad Rifki Kurniawan

2024

1. 

   Evolving Parameterized Prompt Memory for Continual Learning

   Muhammad Rifki Kurniawan, Xiang Song, Zhiheng Ma, Yuhang He, Yihong Gong, Yang Qi, and Xing Wei

   Proceedings of the AAAI Conference on Artificial Intelligence (AAAI), 2024

   Abs Bib Blog Oral

   Recent 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

1. 

   Topology-preserving transfer learning for weakly-supervised anomaly detection and segmentation

   Shenxing Wei, Xing Wei, Muhammad Rifki Kurniawan, Zhiheng Ma, and Yihong Gong

   Pattern Recognition Letters, 2023

   Abs Bib PDF

   Models 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

1. 

   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

   Muhammad Rifki Kurniawan, Xing Wei, and Yihong Gong

   ArXiv, 2021

   Abs Bib PDF Code Slides

   Online 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},
   }