CLOVA & AI Lab @ ICML 2022

Presentation schedule of NAVER CLOVA & AI Lab at ICLM 2022: 5 main track and four workshop papers

Main Track

July 19, Tue

Spotlight 10:50 Improving Ensemble Distillation With Weight Averaging and Diversifying Perturbation. Giung Nam · Hyungi Lee · Byeongho Heo · Juho Lee

Spotlight 11:45 Time Is MattEr: Temporal Self-supervision for Video Transformers. Sukmin Yun · Jaehyung Kim · Dongyoon Han · Hwanjun Song · Jung-Woo Ha · Jinwoo Shin

Poster 15:30 Time Is MattEr: Temporal Self-supervision for Video Transformers. Sukmin Yun · Jaehyung Kim · Dongyoon Han · Hwanjun Song · Jung-Woo Ha · Jinwoo Shin

Improving Ensemble Distillation With Weight Averaging and Diversifying Perturbation. Giung Nam · Hyungi Lee · Byeongho Heo · Juho Lee

July 21, Thu

Spotlight 07:30 Blurs Behave Like Ensembles: Spatial Smoothings to Improve Accuracy, Uncertainty, and Robustness. Namuk Park · Songkuk Kim

Spotlight 08:20 Dataset Condensation via Efficient Synthetic-Data Parameterization. Jang-Hyun Kim · Jinuk Kim · Seong Joon Oh · Sangdoo Yun · Hwanjun Song · Joonhyun Jeong · Jung-Woo Ha · Hyun Oh Song

Spotlight 08:35 Dataset Condensation with Contrastive Signals. Saehyung Lee · Sanghyuk Chun · Sangwon Jung · Sangdoo Yun · Sungroh Yoon

Poster 15:00 Blurs Behave Like Ensembles: Spatial Smoothings to Improve Accuracy, Uncertainty, and Robustness. Namuk Park · Songkuk Kim

Dataset Condensation via Efficient Synthetic-Data Parameterization. Jang-Hyun Kim · Jinuk Kim · Seong Joon Oh · Sangdoo Yun · Hwanjun Song · Joonhyun Jeong · Jung-Woo Ha · Hyun Oh Song

Dataset Condensation with Contrastive Signals. Saehyung Lee · Sanghyuk Chun · Sangwon Jung · Sangdoo Yun · Sungroh Yoon

Workshops

July 22, Fri

Workshop on Spurious Correlations, Invariance, and Stability (SCIS) SelecMix: Debiased Learning by Mixing up Contradicting Pairs. Inwoo Hwang, Sangjun Lee, Yunhyeok Kwak, Seong Joon Oh, Damien Teney, Jin-Hwa Kim, Byoung-Tak Zhang. Poster session: 13:30 - 14:50 (Poster ID: #3)

Workshop on ReALML (Adaptive Experimental Design and Active Learning in the Real World) LG-FAL: Federated Active Learning Strategy using Local and Global Models. SangMook Kim, SangMin Bae, Se-Young Yun, Hwanjun Song. Poster session: 15:30pm-17:30pm

July 23, Sat

Workshop on Pre-training: Perspectives, Pitfalls, and Paths Forward (Pre-training) Generative Self-training Improves Pre-training for Visual Dialog. Gi-Cheon Kang, Sungdong Kim, Jin-Hwa Kim, Donghyun Kwak, Byoung-Tak Zhang. Poster session: 15:00 - 16:30

Workshop on UpML (Updatable Machine Learning) ReFine: Re-randomization before Fine-tuning for Cross-domain Few-shot Learning. Jaehoon Oh*, Sungnyun Kim*, Namgyu Ho*, Jin-Hwa Kim, Hwanjun Song, Se-Young Yun. Poster session: 17:05pm-19:30pm