Institution profile

Incheon National University

Academic institutionasia · kr
Official website
Research library10linked papers
Opportunities0open roles
Selected work

Representative Papers

Human-in-the-Loop Neuro-Symbolic Drift Anticipation for Reliable Visual SLAM

Oct 05, 2026

This study addresses the susceptibility of data-driven visual SLAM models to physically inconsistent drift in out-of-distribution environments due to their black-box nature. To overcome this limitation, we propose the HDS framework, introducing a pioneering human-in-the-loop neuro-symbolic architecture. This framework integrates neural drift estimation with symbolic reasoning, leveraging large language models to translate qualitative human context into interpretable symbolic constraints for proactive drift anticipation. By bridging neural perception and symbolic logic, our approach transcends the inherent limitations of purely data-driven paradigms. The proposed method significantly enhances both the reliability and physical consistency of visual SLAM systems operating within complex environments.

0 citationsRead paper

ScratNet: A Swin-Based Multi-Scale Dilated Network with Precision Refinement for Semiconductor Scratch Segmentation

Jul 11, 2026

This work addresses the challenge of reliably detecting surface scratches in semiconductor manufacturing, which are difficult to identify due to their irregular shapes, low contrast, and varying scales. To this end, the authors propose ScratNet, an end-to-end scratch segmentation framework built upon an enhanced Swin Transformer backbone and a custom-designed decoder. ScratNet introduces several key innovations: a multi-scale dilated aggregation module, a stem integration mechanism, and an anisotropic convolution-driven boundary refinement branch, collectively enabling stage-adaptive feature fusion and boundary-aware optimization. Experimental results demonstrate that ScratNet significantly outperforms existing methods under diverse and complex imaging conditions, achieving superior detection accuracy and robustness—particularly for fine and irregular scratches.

0 citationsRead paper

Event Burst Trigger: An Availability Backdoor Attack on Event-Based SNN Object Detection

Jul 10, 2026

This work addresses the underexplored vulnerability of event-driven spiking neural network (SNN)–based object detection models to availability-oriented backdoor attacks. We propose the Event Burst Trigger (EBT) attack, which injects carefully crafted event-based triggers into training data to induce dense event streams during inference, thereby significantly increasing the computational overhead of non-maximum suppression (NMS) and degrading system availability. Notably, EBT requires no modifications to the model architecture, loss function, or inference pipeline, allowing it to evade existing detection mechanisms such as STRIP. Experimental results demonstrate that, with less than a 0.099 drop in mAP@0.5, the attack can increase NMS latency by up to 38%, effectively elevating resource consumption and reducing scheduling slack without producing conspicuous resource usage spikes.

0 citationsRead paper

Context-Guided Semantic Alignment for Feature Fusion Networks

Jun 11, 2026

This work addresses the semantic inconsistency arising from heterogeneous representations in multi-scale feature fusion, which limits object detection accuracy. To this end, the authors propose the FINE module, which leverages high-level contextual guidance to align low-level features through cross-level attention prior to fusion. An alignment-aware token sampling strategy is introduced to substantially reduce computational complexity. Furthermore, spatial-channel modulation combined with residual element-wise modulation is incorporated to enhance responses of semantically relevant pixels while preserving precise localization capabilities. The proposed method demonstrates consistent and significant performance gains across diverse detectors, achieving notable improvements in detection accuracy with negligible additional computational overhead.

0 citationsRead paper
Recent publications

Latest Papers

Human-in-the-Loop Neuro-Symbolic Drift Anticipation for Reliable Visual SLAM

Oct 05, 2026

This study addresses the susceptibility of data-driven visual SLAM models to physically inconsistent drift in out-of-distribution environments due to their black-box nature. To overcome this limitation, we propose the HDS framework, introducing a pioneering human-in-the-loop neuro-symbolic architecture. This framework integrates neural drift estimation with symbolic reasoning, leveraging large language models to translate qualitative human context into interpretable symbolic constraints for proactive drift anticipation. By bridging neural perception and symbolic logic, our approach transcends the inherent limitations of purely data-driven paradigms. The proposed method significantly enhances both the reliability and physical consistency of visual SLAM systems operating within complex environments.

0 citationsRead paper

ScratNet: A Swin-Based Multi-Scale Dilated Network with Precision Refinement for Semiconductor Scratch Segmentation

Jul 11, 2026

This work addresses the challenge of reliably detecting surface scratches in semiconductor manufacturing, which are difficult to identify due to their irregular shapes, low contrast, and varying scales. To this end, the authors propose ScratNet, an end-to-end scratch segmentation framework built upon an enhanced Swin Transformer backbone and a custom-designed decoder. ScratNet introduces several key innovations: a multi-scale dilated aggregation module, a stem integration mechanism, and an anisotropic convolution-driven boundary refinement branch, collectively enabling stage-adaptive feature fusion and boundary-aware optimization. Experimental results demonstrate that ScratNet significantly outperforms existing methods under diverse and complex imaging conditions, achieving superior detection accuracy and robustness—particularly for fine and irregular scratches.

0 citationsRead paper

Event Burst Trigger: An Availability Backdoor Attack on Event-Based SNN Object Detection

Jul 10, 2026

This work addresses the underexplored vulnerability of event-driven spiking neural network (SNN)–based object detection models to availability-oriented backdoor attacks. We propose the Event Burst Trigger (EBT) attack, which injects carefully crafted event-based triggers into training data to induce dense event streams during inference, thereby significantly increasing the computational overhead of non-maximum suppression (NMS) and degrading system availability. Notably, EBT requires no modifications to the model architecture, loss function, or inference pipeline, allowing it to evade existing detection mechanisms such as STRIP. Experimental results demonstrate that, with less than a 0.099 drop in mAP@0.5, the attack can increase NMS latency by up to 38%, effectively elevating resource consumption and reducing scheduling slack without producing conspicuous resource usage spikes.

0 citationsRead paper

Context-Guided Semantic Alignment for Feature Fusion Networks

Jun 11, 2026

This work addresses the semantic inconsistency arising from heterogeneous representations in multi-scale feature fusion, which limits object detection accuracy. To this end, the authors propose the FINE module, which leverages high-level contextual guidance to align low-level features through cross-level attention prior to fusion. An alignment-aware token sampling strategy is introduced to substantially reduce computational complexity. Furthermore, spatial-channel modulation combined with residual element-wise modulation is incorporated to enhance responses of semantically relevant pixels while preserving precise localization capabilities. The proposed method demonstrates consistent and significant performance gains across diverse detectors, achieving notable improvements in detection accuracy with negligible additional computational overhead.

0 citationsRead paper