10 papers
CLON: Cue-Calibrated Linguistic Object Onboarding for Zero-Shot 6D Pose Front-Ends
Seojin Ji, Yoojin Kwon, Hyung-Sin Kim
Novel-object 6D pose pipelines depend on front-end hypotheses that retain target instances under clutter and occlusion without overwhelming downstream pose estimation. We introduce…
Back to the Familiar Future: Failure Recovery for VLA Policies via Pre-Imagined Milestone Selection
Suyeon Shin, Juwon Kim, Hyeonbin Park +4
Vision-language-action (VLA) policies can deviate from nominal trajectories during manipulation, even when tasks remain physically feasible. Recovering from these deviations is cha…
EgoXtreme: A Dataset for Robust Object Pose Estimation in Egocentric Views under Extreme Conditions
Taegyoon Yoon, Yegyu Han, Seojin Ji +4
Smart glass is emerging as an useful device since it provides plenty of insights under hands-busy, eyes-on-task situations. To understand the context of the wearer, 6D object pose…
Measurement Plasticity: Sensor-Level Adaptation for Vision-Language Models
Boyeong Im, Wooseok Lee, Yoojin Kwon +1
We propose Multi-View Physical-prompt (MVP) for Test-Time Adaptation (TTA), a forward-only framework that moves TTA from tokens to photons by treating the camera exposure triangle…
AI Should Sense Better, Not Just Scale Bigger: Adaptive Sensing as a Paradigm Shift
Eunsu Baek, Keondo Park, Jeonggil Ko +3
Current AI advances largely rely on scaling neural models and expanding training datasets to achieve generalization and robustness. Despite notable successes, this paradigm incurs…
SenseShift6D: Multimodal RGB-D Benchmarking for Robust 6D Pose Estimation across Environment and Sensor Variations
Yegyu Han, Taegyoon Yoon, Dayeon Woo +2
Recent advances on 6D object pose estimation have achieved high performance on representative benchmarks such as LM-O, YCB-V, and T-Less. However, these datasets were captured unde…
Frequency Composition for Compressed and Domain-Adaptive Neural Networks
Yoojin Kwon, Hongjun Suh, Wooseok Lee +3
Modern on-device neural network applications must operate under resource constraints while adapting to unpredictable domain shifts. However, this combined challenge-model compressi…
A Revisit to the Decoder for Camouflaged Object Detection
Seung Woo Ko, Joopyo Hong, Suyoung Kim +5
Camouflaged object detection (COD) aims to generate a fine-grained segmentation map of camouflaged objects hidden in their background. Due to the hidden nature of camouflaged objec…
Adaptive Camera Sensor for Vision Models
Eunsu Baek, Sunghwan Han, Taesik Gong +1
Domain shift remains a persistent challenge in deep-learning-based computer vision, often requiring extensive model modifications or large labeled datasets to address. Inspired by…
Unexplored Faces of Robustness and Out-of-Distribution: Covariate Shifts in Environment and Sensor Domains
Eunsu Baek, Keondo Park, Jiyoon Kim +1
Computer vision applications predict on digital images acquired by a camera from physical scenes through light. However, conventional robustness benchmarks rely on perturbations in…