Ai-DAiSY Lab.

• 1 IEEE ACCESS Paper has been accepted (Congratulations!) 

  -.Authors : Seo Yun O and Myung Han Hyun-.AbstractThis paper proposes a continuous anisotropic downscale predictor (ADP) for bitrate-constrained object detection. Existing resolution-control methods often use isotropic scale factors, discrete scale candidates, or pre-generated optimal scaling factors, which limits their ability to preserve direction-dependent image structures under a strict bitrate budget. To address this limitation, the proposed ADP predicts continuous horizontal and vertical downscaling factors for each input image. This continuous prediction provides finer bitrate–accuracy adaptation than discrete resolution candidates, while differentiable anisotropic downscaling is applied before JPEG compression. The framework is trained using a detection objective and a differentiable bitrate surrogate so that resolution control is optimized with respect to both encoded bitrate and detection accuracy. To reduce the mismatch between the estimated bitrate and the actual JPEG bitstream size, we further introduce online bitrate calibration using real JPEG encoding statistics. Experiments on COCO val2017 show that the proposed method provides improved matched-bitrate detection accuracy compared with previous resolution-control methods. Across the evaluated target bitrate points, the proposed method achieves up to 8.41 percentage-point improvement in mAP@50 and 5.28 percentage-point improvement in mAP@50:95 over the compared baselines. In particular, the results on the aspect-ratio-extreme subset show that independent horizontal and vertical resolution control is beneficial for images with strong directional structure. Additional intermediate feature-similarity and efficiency analyses further support that the proposed ADP provides practical bitrate-aware resolution control for object detection.

  2026.06.30 제어로봇공학과

• IPIU2025 Vlog by Ai-DAiSY Lab. 

   IPIU2025 Vlog by Ai-DAiSY Lab.

  2025.03.06 제어로봇공학과

• Summer Vacation Lab. seminar #3 (24.8.22) 

  Please refer to the attached schedule :)

  2024.08.12 제어로봇공학과

• Summer Vacation Lab. seminar #2 (24.8.8) 

  Please refer to the attached file.

  2024.08.04 제어로봇공학과

• Summer Vacation Lab. seminar #1 (24.7.18) 

  Please refer to the attached schedule!

  2024.07.10 제어로봇공학과

• Lab. Seminar will be held on July 4. 

  Our Ai-DAiSY Labbers are planning to present their first presentations with free topics scheduled on July 4, 2024. Please refer to the attached document for the subjects.

  2024.06.04 제어로봇공학과

• 2024 Summer Conference (The Korean Institute of Broadcast and Media Engineers) 

  Our Lab. will join the 2024 summer conference (The Korean Institute of Broadcast and Media Engineers) held in Maisonglad Hotel, Jeju, '24.6.25~28.

  2024.06.04 제어로봇공학과

• The IEEE/CVF Conference on Computer Vision and Pattern Recognition 2024 

  Our Lab. will join the CVPR 2024 (The IEEE/CVF Conference on Computer Vision and Pattern Recognition 2024) held in Seattle, USA, '24.6.17~21. Hope to grab lots of ideas for our future works.

  2024.06.04 제어로봇공학과

• RA recruiting 

  We are looking for the self-motivated graduate students. If you're interested in our Ai-DAiSY Lab., just feel free to visit my office (Building 405, Rm504) or send me the following information via e-mail [drwise@gnu.ac.kr] : (1) Curriculum Vitae (CV) and (2) transcript. 

  2024.06.04 제어로봇공학과