arXiv subjects

Mi Young Lee

Publications and source records attributed to Mi Young Lee.

4 recordsLinked to original sources

arXiv2026

When Do Frozen VLMs Respond to Image-Free Object-Token Edits? An Answer-Key-Free Protocol and What It Reveals

Answering what-if queries about a scene with a VLM usually means injecting the assumption as text or repainting the scene with a generative model. We instead move the edit to the representation level, before the model input. The image is abstracted into a set of object-level tokens, and the original image never enters the VLM. This design rests on an open question: when do frozen VLMs actually respond to such token edits? We introduce an answer-key-free protocol: no post-edit answer is annotated. It scores edits whose answers are logically determined, and audits itself by reversing each scoreable choice. The protocol reveals three structures. The response is not free: explicit edit teaching, not ordinary VQA training, produces it in dense scenes and multiplies it in sparse ones, on all three operations. Once on, it is governed by token cleanliness and density, with deployable detector+segmenter tokens competitive with the oracle and outperforming it on VRSBench. And reading is a separable axis: the image-free token route preserves 92-96% of a matched patch-token baseline's free-text VQA, and the answers measurably depend on the tokens. The response, cleanliness, and reading structures are sign-preserved across two remote-sensing datasets (iSAID, VRSBench) and three frozen LM backbones. We release the probe generator, records, judge logs, and code.

cs.CV↗

arXiv2023

Machine Learning Based Missing Values Imputation in Categorical Datasets

In order to predict and fill in the gaps in categorical datasets, this research looked into the use of machine learning algorithms. The emphasis was on ensemble models constructed using the Error Correction Output Codes framework, including models based on SVM and KNN as well as a hybrid classifier that combines models based on SVM, KNN,and MLP. Three diverse datasets, the CPU, Hypothyroid, and Breast Cancer datasets were employed to validate these algorithms. Results indicated that these machine learning techniques provided substantial performance in predicting and completing missing data, with the effectiveness varying based on the specific dataset and missing data pattern. Compared to solo models, ensemble models that made use of the ECOC framework significantly improved prediction accuracy and robustness. Deep learning for missing data imputation has obstacles despite these encouraging results, including the requirement for large amounts of labeled data and the possibility of overfitting. Subsequent research endeavors ought to evaluate the feasibility and efficacy of deep learning algorithms in the context of the imputation of missing data.

cs.LG↗

arXiv2016

Divide-and-Conquer based Ensemble to Spot Emotions in Speech using MFCC and Random Forest

Besides spoken words, speech signals also carry information about speaker gender, age, and emotional state which can be used in a variety of speech analysis applications. In this paper, a divide and conquer strategy for ensemble classification has been proposed to recognize emotions in speech. Intrinsic hierarchy in emotions has been utilized to construct an emotions tree, which assisted in breaking down the emotion recognition task into smaller sub tasks. The proposed framework generates predictions in three phases. Firstly, emotions are detected in the input speech signal by classifying it as neutral or emotional. If the speech is classified as emotional, then in the second phase, it is further classified into positive and negative classes. Finally, individual positive or negative emotions are identified based on the outcomes of the previous stages. Several experiments have been performed on a widely used benchmark dataset. The proposed method was able to achieve improved recognition rates as compared to several other approaches.

cs.SD↗

arXiv2015

Ontology-based Secure Retrieval of Semantically Significant Visual Contents

Image classification is an enthusiastic research field where large amount of image data is classified into various classes based on their visual contents. Researchers have presented various low-level features-based techniques for classifying images into different categories. However, efficient and effective classification and retrieval is still a challenging problem due to complex nature of visual contents. In addition, the traditional information retrieval techniques are vulnerable to security risks, making it easy for attackers to retrieve personal visual contents such as patients records and law enforcement agencies databases. Therefore, we propose a novel ontology-based framework using image steganography for secure image classification and information retrieval. The proposed framework uses domain-specific ontology for mapping the low-level image features to high-level concepts of ontologies which consequently results in efficient classification. Furthermore, the proposed method utilizes image steganography for hiding the image semantics as a secret message inside them, making the information retrieval process secure from third parties. The proposed framework minimizes the computational complexity of traditional techniques, increasing its suitability for secure and real-time visual contents retrieval from personalized image databases. Experimental results confirm the efficiency, effectiveness, and security of the proposed framework as compared with other state-of-the-art systems.

cs.MM↗