成學

This is a Korean review of"Logit Standardization in Knowledge Distillation"presented at CVPR 2024.TL;DRKD에서 teacher와 student의 soft label $($i.e., prediction$)$을 얻을 때 사용하는 shared temperature은 teacher와 student logits의 range와 variance의 mandatory exact match를 전제로 함. $($in fact, relation is important.$)$기존 방법의 한계를 극복하기 위해, adaptive temperature로 weighted logit standard deviation을 사용함.이를 활용해, softmax를 ..

This is a Korean review of "Instance-conditional knowledge distillation for object detection" presented at NeurIPS 2021.Introduction High performance의 Deep Learning Networks의 성능을 얻기 위해서는, 불가피하게 많은 양의 parameters를 수반하게 되며, 이는 high computational cost와 memory를 요구함.따라서, Resource-limited devices에서 object detection과 같은 실용적인 application을 사용하기 위해, network pruning, quantization, mobile architecture design..

This content, created while I was majoring in Computational Fluid Dynamics, focuses on numerical methods for solving multiphase flow.

This is a Korean review of"CrossKD: Cross-Head Knowledge Distillation for Object Detecton"presented at CVPR 2024.TL;DRCrossKD라는 효과적인 prediction mimicking distillation scheme을 제안하여, student의 dtection head의 중간 feature를 teacher의 detection head에 전달함. 이러한 cross-head prediction은 teacher의 prediction을 모방하게 됨.본 방식은 student head의 annotation과 teacher prediction으로부터의 contradictory supervision signal 전달을 완화하..

This is a Korean review of "ScaleKD: Distilling Scale-Aware Knowledge in Small Object Detectors" presented at CVPR 2023.TL;DRScale-decoupled feautre distllation module을 통해 teacher의 feature를 multi-scale embedding에 disentangled하여, small object에 대한 학생의 feature mimicking을 용이하게 함.Cross-scale assistant를 통해, student에게 부정적인 결과를 초래하는 noisy하고 uninformative한 bounding box prediction을 refine함.Multi-scale cro..

This is a review of "Integral Neural Networks" presented at CVPR 2023.

This is a review of "Cross-Image Relational Knowledge Distillation for Semantic Segmentation" presented at CVPR 2022.

This is a review of "Asymmetric Temperature Scaling Makes Larger Networks Teach Well Again" presented at NeurIPS 2022.

This is a review of "Knowledge Distillation from A Stronger Teacher" presented at NeurIPS 2022.

This is a review of "Multi-level Logit Distillation" presented at CVPR 2023.