arXiv subjects

Novanto Yudistira

Publications and source records attributed to Novanto Yudistira.

At least 19 recordsLinked to original sources

arXiv2026

Zero-Shot Captioning for Cultural Heritage: Automated Image Analysis of Traditional Indonesian Clothing

This paper presents Custom ZeroCLIP, a retrieval-augmented vision-language framework for zero-shot captioning of Indonesian traditional garments. The dataset contains 3,800 expert-annotated images from all 38 Indonesian provinces. Using a province-level inductive zero-shot protocol, the model is trained on 24 seen provinces, validated on 6 seen provinces, and evaluated on 8 unseen provinces. The framework combines a frozen CLIP ViT-B/32 image encoder, a CLIP text encoder, a BERT text encoder, and an LSTM caption decoder. During inference, unseen-province labels and captions are unavailable, and retrieval uses only captions from training provinces. No unseen-province image, label, or caption is used during training, validation, or retrieval-bank construction. Custom ZeroCLIP achieves a CLIPScore of 0.8536, BLEU-4 of 0.3342, and METEOR of 0.4859, outperforming existing baselines. Ablation results show that retrieval improves cultural vocabulary recovery with a 19.3\% METEOR gain, while human evaluation confirms stronger cultural accuracy and fluency. The results demonstrate the effectiveness of retrieval-augmented domain adaptation for culturally grounded caption generation in low-resource heritage settings. The dataset is publicly available at https://github.com/AnugrahAidinYotolembah/Traditional-Indonesian-Clothing-Captioning-Dataset.

cs.CV↗

arXiv2026

Does Language Shift Break Medical Vision-Language Models? Indonesian Radiology Visual Question Answering Case Study

Medical Vision-Language Models (VLMs) are typically evaluated on English radiology visual question answering benchmarks, leaving their robustness under non-English clinical language largely unexplored. We introduce IndoRad-VQA, an Indonesian adaptation of VQA-RAD, to assess whether medical VLMs retain radiology reasoning ability when questions are asked in Bahasa Indonesia. Radiology question-answer pairs are translated into Indonesian with self-evaluation-based quality control to preserve clinical meaning, terminology consistency, and answer equivalence. We evaluate general-purpose, Southeast Asian multilingual, and medical-specific VLMs under English and Indonesian prompting settings. Beyond accuracy, we quantify the language robustness gap between English and Indonesian inputs. We also conduct an error analysis to identify failure modes of question answering, such as yes/no flips, laterality errors, and output-language mismatches. Our findings show that strong performance on English medical VQA benchmarks does not necessarily translate to robust behavior in Indonesian clinical contexts. We observe a performance gap of 8 to 25 percent between the English and Indonesian settings, depending on the evaluation metric. These results highlight the need for more inclusive multilingual evaluation of medical multimodal foundation models. The dataset is available at https://huggingface.co/datasets/Lab-IS/IndoRad-VQA.

cs.CL↗

arXiv2026

Adaptive Conformal Prediction for Reliable and Explainable Medical Image Classification

Deep learning models for medical imaging often exhibit overconfidence, creating safety risks in ambiguous diagnostic scenarios. While Conformal Prediction (CP) provides distribution-free statistical guarantees, standard methods such as Regularized Adaptive Prediction Sets (RAPS) optimize for average efficiency and can mask severe failures on difficult inputs. We propose an Adaptive Lambda Criterion for RAPS that minimizes the worst-case coverage violation across prediction set size strata. On OrganAMNIST (58,850 abdominal CT images, 11 classes), standard size-optimized RAPS converges to near-deterministic behavior with stratified undercoverage on uncertain samples, while our method achieves 95.72 percent global coverage with average set size 1.09 and at least 90 percent coverage across all strata. Cross-domain validation on PathMNIST (107,180 pathology images, 9 classes) confirms generalizability. Quantitative Grad-CAM analysis (rho = -0.30, p < 1e-22) shows that multi-label predictions correspond to focused attention on anatomically ambiguous regions. These results demonstrate that the proposed method improves reliability while maintaining efficiency, making it suitable for safety-critical medical AI applications.

cs.CV↗

arXiv2025

Training-Free Disentangled Text-Guided Image Editing via Sparse Latent Constraints

Text-driven image manipulation often suffers from attribute entanglement, where modifying a target attribute (e.g., adding bangs) unintentionally alters other semantic properties such as identity or appearance. The Predict, Prevent, and Evaluate (PPE) framework addresses this issue by leveraging pre-trained vision-language models for disentangled editing. In this work, we analyze the PPE framework, focusing on its architectural components, including BERT-based attribute prediction and StyleGAN2-based image generation on the CelebA-HQ dataset. Through empirical analysis, we identify a limitation in the original regularization strategy, where latent updates remain dense and prone to semantic leakage. To mitigate this issue, we introduce a sparsity-based constraint using L1 regularization on latent space manipulation. Experimental results demonstrate that the proposed approach enforces more focused and controlled edits, effectively reducing unintended changes in non-target attributes while preserving facial identity.

cs.CV↗

arXiv2025

Input-Adaptive Visual Preprocessing for Efficient Fast Vision-Language Model Inference

Vision-Language Models (VLMs) have demonstrated strong performance on multimodal reasoning tasks, but their deployment remains challenging due to high inference latency and computational cost, particularly when processing high-resolution visual inputs. While recent architectures such as FastVLM improve efficiency through optimized vision encoders, existing pipelines still rely on static visual preprocessing, leading to redundant computation for visually simple inputs. In this work, we propose an adaptive visual preprocessing method that dynamically adjusts input resolution and spatial coverage based on image content characteristics. The proposed approach combines content-aware image analysis, adaptive resolution selection, and content-aware cropping to reduce visual redundancy prior to vision encoding. Importantly, the method is integrated with FastVLM without modifying its architecture or requiring retraining. We evaluate the proposed method on a subset of the DocVQA dataset in an inference-only setting, focusing on efficiency-oriented metrics. Experimental results show that adaptive preprocessing reduces per-image inference time by over 50\%, lowers mean full generation time, and achieves a consistent reduction of more than 55\% in visual token count compared to the baseline pipeline. These findings demonstrate that input-aware preprocessing is an effective and lightweight strategy for improving deployment-oriented efficiency of vision-language models. To facilitate reproducibility, our implementation is provided as a fork of the FastVLM repository, incorporating the files for the proposed method, and is available at https://github.com/kmdavidds/mlfastlm.

cs.CV↗

arXiv2025

Towards Adaptive Fusion of Multimodal Deep Networks for Human Action Recognition

This study introduces a pioneering methodology for human action recognition by harnessing deep neural network techniques and adaptive fusion strategies across multiple modalities, including RGB, optical flows, audio, and depth information. Employing gating mechanisms for multimodal fusion, we aim to surpass limitations inherent in traditional unimodal recognition methods while exploring novel possibilities for diverse applications. Through an exhaustive investigation of gating mechanisms and adaptive weighting-based fusion architectures, our methodology enables the selective integration of relevant information from various modalities, thereby bolstering both accuracy and robustness in action recognition tasks. We meticulously examine various gated fusion strategies to pinpoint the most effective approach for multimodal action recognition, showcasing its superiority over conventional unimodal methods. Gating mechanisms facilitate the extraction of pivotal features, resulting in a more holistic representation of actions and substantial enhancements in recognition performance. Our evaluations across human action recognition, violence action detection, and multiple self-supervised learning tasks on benchmark datasets demonstrate promising advancements in accuracy. The significance of this research lies in its potential to revolutionize action recognition systems across diverse fields. The fusion of multimodal information promises sophisticated applications in surveillance and human-computer interaction, especially in contexts related to active assisted living.

cs.CV↗

arXiv2025

ASVRI-Legal: Fine-Tuning LLMs with Retrieval Augmented Generation for Enhanced Legal Regulation

In this study, we explore the fine-tuning of Large Language Models (LLMs) to better support policymakers in their crucial work of understanding, analyzing, and crafting legal regulations. To equip the model with a deep understanding of legal texts, we curated a supervised dataset tailored to the specific needs of the legal domain. Additionally, we integrated the Retrieval-Augmented Generation (RAG) method, enabling the LLM to access and incorporate up-to-date legal knowledge from external sources. This combination of fine-tuning and RAG-based augmentation results in a tool that not only processes legal information but actively assists policymakers in interpreting regulations and drafting new ones that align with current needs. The results demonstrate that this approach can significantly enhance the effectiveness of legal research and regulation development, offering a valuable resource in the ever-evolving field of law.

cs.CL↗

arXiv2025

Efficient Object Detection of Marine Debris using Pruned YOLO Model

Marine debris poses significant harm to marine life due to substances like microplastics, polychlorinated biphenyls, and pesticides, which damage habitats and poison organisms. Human-based solutions, such as diving, are increasingly ineffective in addressing this issue. Autonomous underwater vehicles (AUVs) are being developed for efficient sea garbage collection, with the choice of object detection architecture being critical. This research employs the YOLOv4 model for real-time detection of marine debris using the Trash-ICRA 19 dataset, consisting of 7683 images at 480x320 pixels. Various modifications-pretrained models, training from scratch, mosaic augmentation, layer freezing, YOLOv4-tiny, and channel pruning-are compared to enhance architecture efficiency. Channel pruning significantly improves detection speed, increasing the base YOLOv4 frame rate from 15.19 FPS to 19.4 FPS, with only a 1.2% drop in mean Average Precision, from 97.6% to 96.4%.

cs.CV↗

arXiv2024

Variational Mode Decomposition and Linear Embeddings are What You Need For Time-Series Forecasting

Time-series forecasting often faces challenges due to data volatility, which can lead to inaccurate predictions. Variational Mode Decomposition (VMD) has emerged as a promising technique to mitigate volatility by decomposing data into distinct modes, thereby enhancing forecast accuracy. In this study, we integrate VMD with linear models to develop a robust forecasting framework. Our approach is evaluated on 13 diverse datasets, including ETTm2, WindTurbine, M4, and 10 air quality datasets from various Southeast Asian cities. The effectiveness of the VMD strategy is assessed by comparing Root Mean Squared Error (RMSE) values from models utilizing VMD against those without it. Additionally, we benchmark linear-based models against well-known neural network architectures such as LSTM, Bidirectional LSTM, and RNN. The results demonstrate a significant reduction in RMSE across nearly all models following VMD application. Notably, the Linear + VMD model achieved the lowest average RMSE in univariate forecasting at 0.619. In multivariate forecasting, the DLinear + VMD model consistently outperformed others, attaining the lowest RMSE across all datasets with an average of 0.019. These findings underscore the effectiveness of combining VMD with linear models for superior time-series forecasting.

cs.LG↗

arXiv2024

IndoHerb: Indonesia Medicinal Plants Recognition using Transfer Learning and Deep Learning

The rich diversity of herbal plants in Indonesia holds immense potential as alternative resources for traditional healing and ethnobotanical practices. However, the dwindling recognition of herbal plants due to modernization poses a significant challenge in preserving this valuable heritage. The accurate identification of these plants is crucial for the continuity of traditional practices and the utilization of their nutritional benefits. Nevertheless, the manual identification of herbal plants remains a time-consuming task, demanding expert knowledge and meticulous examination of plant characteristics. In response, the application of computer vision emerges as a promising solution to facilitate the efficient identification of herbal plants. This research addresses the task of classifying Indonesian herbal plants through the implementation of transfer learning of Convolutional Neural Networks (CNN). To support our study, we curated an extensive dataset of herbal plant images from Indonesia with careful manual selection. Subsequently, we conducted rigorous data preprocessing, and classification utilizing transfer learning methodologies with five distinct models: ResNet, DenseNet, VGG, ConvNeXt, and Swin Transformer. Our comprehensive analysis revealed that ConvNeXt achieved the highest accuracy, standing at an impressive 92.5%. Additionally, we conducted testing using a scratch model, resulting in an accuracy of 53.9%. The experimental setup featured essential hyperparameters, including the ExponentialLR scheduler with a gamma value of 0.9, a learning rate of 0.001, the Cross-Entropy Loss function, the Adam optimizer, and a training epoch count of 50. This study's outcomes offer valuable insights and practical implications for the automated identification of Indonesian medicinal plants.

cs.CV↗

arXiv2024

Hybrid of DiffStride and Spectral Pooling in Convolutional Neural Networks

Stride determines the distance between adjacent filter positions as the filter moves across the input. A fixed stride causes important information contained in the image can not be captured, so that important information is not classified. Therefore, in previous research, the DiffStride Method was applied, namely the Strided Convolution Method with which it can learn its own stride value. Severe Quantization and a constraining lower bound on preserved information are arises with Max Pooling Downsampling Method. Spectral Pooling reduce the constraint lower bound on preserved information by cutting off the representation in the frequency domain. In this research a CNN Model is proposed with the Downsampling Learnable Stride Technique performed by Backpropagation combined with the Spectral Pooling Technique. Diffstride and Spectral Pooling techniques are expected to maintain most of the information contained in the image. In this study, we compare the Hybrid Method, which is a combined implementation of Spectral Pooling and DiffStride against the Baseline Method, which is the DiffStride implementation on ResNet 18. The accuracy result of the DiffStride combination with Spectral Pooling improves over DiffStride which is baseline method by 0.0094. This shows that the Hybrid Method can maintain most of the information by cutting of the representation in the frequency domain and determine the stride of the learning result through Backpropagation.

cs.CV↗

arXiv2024

Learning-Augmented K-Means Clustering Using Dimensional Reduction

Learning augmented is a machine learning concept built to improve the performance of a method or model, such as enhancing its ability to predict and generalize data or features, or testing the reliability of the method by introducing noise and other factors. On the other hand, clustering is a fundamental aspect of data analysis and has long been used to understand the structure of large datasets. Despite its long history, the k-means algorithm still faces challenges. One approach, as suggested by Ergun et al,is to use a predictor to minimize the sum of squared distances between each data point and a specified centroid. However, it is known that the computational cost of this algorithm increases with the value of k, and it often gets stuck in local minima. In response to these challenges, we propose a solution to reduce the dimensionality of the dataset using Principal Component Analysis (PCA). It is worth noting that when using k values of 10 and 25, the proposed algorithm yields lower cost results compared to running it without PCA. "Principal component analysis (PCA) is the problem of fitting a low-dimensional affine subspace to a set of data points in a high-dimensional space. PCA is well-established in the literature and has become one of the most useful tools for data modeling, compression, and visualization."

cs.LG↗

arXiv2024

MAMI: Multi-Attentional Mutual-Information for Long Sequence Neuron Captioning

Neuron labeling is an approach to visualize the behaviour and respond of a certain neuron to a certain pattern that activates the neuron. Neuron labeling extract information about the features captured by certain neurons in a deep neural network, one of which uses the encoder-decoder image captioning approach. The encoder used can be a pretrained CNN-based model and the decoder is an RNN-based model for text generation. Previous work, namely MILAN (Mutual Information-guided Linguistic Annotation of Neuron), has tried to visualize the neuron behaviour using modified Show, Attend, and Tell (SAT) model in the encoder, and LSTM added with Bahdanau attention in the decoder. MILAN can show great result on short sequence neuron captioning, but it does not show great result on long sequence neuron captioning, so in this work, we would like to improve the performance of MILAN even more by utilizing different kind of attention mechanism and additionally adding several attention result into one, in order to combine all the advantages from several attention mechanism. Using our compound dataset, we obtained higher BLEU and F1-Score on our proposed model, achieving 17.742 and 0.4811 respectively. At some point where the model converges at the peak, our model obtained BLEU of 21.2262 and BERTScore F1-Score of 0.4870.

cs.AI↗

arXiv2023

SparseSwin: Swin Transformer with Sparse Transformer Block

Advancements in computer vision research have put transformer architecture as the state of the art in computer vision tasks. One of the known drawbacks of the transformer architecture is the high number of parameters, this can lead to a more complex and inefficient algorithm. This paper aims to reduce the number of parameters and in turn, made the transformer more efficient. We present Sparse Transformer (SparTa) Block, a modified transformer block with an addition of a sparse token converter that reduces the number of tokens used. We use the SparTa Block inside the Swin T architecture (SparseSwin) to leverage Swin capability to downsample its input and reduce the number of initial tokens to be calculated. The proposed SparseSwin model outperforms other state of the art models in image classification with an accuracy of 86.96%, 97.43%, and 85.35% on the ImageNet100, CIFAR10, and CIFAR100 datasets respectively. Despite its fewer parameters, the result highlights the potential of a transformer architecture using a sparse token converter with a limited number of tokens to optimize the use of the transformer and improve its performance.

cs.CV↗

arXiv2023

Mixture of Self-Supervised Learning

Self-supervised learning is popular method because of its ability to learn features in images without using its labels and is able to overcome limited labeled datasets used in supervised learning. Self-supervised learning works by using a pretext task which will be trained on the model before being applied to a specific task. There are some examples of pretext tasks used in self-supervised learning in the field of image recognition, namely rotation prediction, solving jigsaw puzzles, and predicting relative positions on image. Previous studies have only used one type of transformation as a pretext task. This raises the question of how it affects if more than one pretext task is used and to use a gating network to combine all pretext tasks. Therefore, we propose the Gated Self-Supervised Learning method to improve image classification which use more than one transformation as pretext task and uses the Mixture of Expert architecture as a gating network in combining each pretext task so that the model automatically can study and focus more on the most useful augmentations for classification. We test performance of the proposed method in several scenarios, namely CIFAR imbalance dataset classification, adversarial perturbations, Tiny-Imagenet dataset classification, and semi-supervised learning. Moreover, there are Grad-CAM and T-SNE analysis that are used to see the proposed method for identifying important features that influence image classification and representing data for each class and separating different classes properly. Our code is in https://github.com/aristorenaldo/G-SSL

cs.CV↗

arXiv2023

Sparse then Prune: Toward Efficient Vision Transformers

The Vision Transformer architecture is a deep learning model inspired by the success of the Transformer model in Natural Language Processing. However, the self-attention mechanism, large number of parameters, and the requirement for a substantial amount of training data still make Vision Transformers computationally burdensome. In this research, we investigate the possibility of applying Sparse Regularization to Vision Transformers and the impact of Pruning, either after Sparse Regularization or without it, on the trade-off between performance and efficiency. To accomplish this, we apply Sparse Regularization and Pruning methods to the Vision Transformer architecture for image classification tasks on the CIFAR-10, CIFAR-100, and ImageNet-100 datasets. The training process for the Vision Transformer model consists of two parts: pre-training and fine-tuning. Pre-training utilizes ImageNet21K data, followed by fine-tuning for 20 epochs. The results show that when testing with CIFAR-100 and ImageNet-100 data, models with Sparse Regularization can increase accuracy by 0.12%. Furthermore, applying pruning to models with Sparse Regularization yields even better results. Specifically, it increases the average accuracy by 0.568% on CIFAR-10 data, 1.764% on CIFAR-100, and 0.256% on ImageNet-100 data compared to pruning models without Sparse Regularization. Code can be accesed here: https://github.com/yogiprsty/Sparse-ViT

cs.CV↗

arXiv2023

Synthesis of Batik Motifs using a Diffusion -- Generative Adversarial Network

Batik, a unique blend of art and craftsmanship, is a distinct artistic and technological creation for Indonesian society. Research on batik motifs is primarily focused on classification. However, further studies may extend to the synthesis of batik patterns. Generative Adversarial Networks (GANs) have been an important deep learning model for generating synthetic data, but often face challenges in the stability and consistency of results. This research focuses on the use of StyleGAN2-Ada and Diffusion techniques to produce realistic and high-quality synthetic batik patterns. StyleGAN2-Ada is a variation of the GAN model that separates the style and content aspects in an image, whereas diffusion techniques introduce random noise into the data. In the context of batik, StyleGAN2-Ada and Diffusion are used to produce realistic synthetic batik patterns. This study also made adjustments to the model architecture and used a well-curated batik dataset. The main goal is to assist batik designers or craftsmen in producing unique and quality batik motifs with efficient production time and costs. Based on qualitative and quantitative evaluations, the results show that the model tested is capable of producing authentic and quality batik patterns, with finer details and rich artistic variations. The dataset and code can be accessed here:https://github.com/octadion/diffusion-stylegan2-ada-pytorch

cs.CV↗

arXiv2023

Text recognition on images using pre-trained CNN

A text on an image often stores important information and directly carries high level semantics, makes it as important source of information and become a very active research topic. Many studies have shown that the use of CNN-based neural networks is quite effective and accurate for image classification which is the basis of text recognition. It can also be more enhanced by using transfer learning from pre-trained model trained on ImageNet dataset as an initial weight. In this research, the recognition is trained by using Chars74K dataset and the best model results then tested on some samples of IIIT-5K-Dataset. The research results showed that the best accuracy is the model that trained using VGG-16 architecture applied with image transformation of rotation 15°, image scale of 0.9, and the application of gaussian blur effect. The research model has an accuracy of 97.94% for validation data, 98.16% for test data, and 95.62% for the test data from IIIT-5K-Dataset. Based on these results, it can be concluded that pre-trained CNN can produce good accuracy for text recognition, and the model architecture that used in this study can be used as reference material in the development of text detection systems in the future

cs.CV↗