Lab Seminar Videos

• Estimating Training Data Influence by Tracing Gradient Descent (Nov. 15, 2024 / Presenter: Sujin Jeon): https://www.youtube.com/watch?v=AzqUn2en-Ok
  • Pruthi, Garima, Frederick Liu, Satyen Kale, and Mukund Sundararajan. "Estimating training data influence by tracing gradient descent." Advances in Neural Information Processing Systems 33 (2020): 19920-19930.

• Deep Bayesian Active Learning with Image Data (Oct. 18, 2024 / Gyeongho Kim): https://youtu.be/heflb1J195M
  • Gal, Yarin, Riashat Islam, and Zoubin Ghahramani. "Deep bayesian active learning with image data." In International conference on machine learning, pp. 1183-1192. PMLR, 2017.

• DanHAR: Dual Attention Network for multimodal human activity recognition using wearable sensors (Oct. 11, 2024 / Presenter: Soyeon Park): https://youtu.be/8FUNBbG4bec
  • Gao, Wenbin, Lei Zhang, Qi Teng, Jun He, and Hao Wu. "DanHAR: Dual attention network for multimodal human activity recognition using wearable sensors." Applied Soft Computing 111 (2021): 107728.

• Contrastive Adaptation Network for Unsupervised Domain Adaptation (Sep. 27, 2024 / Presenter: Jae Gyeong Choi): https://youtu.be/ZD-RCUfrgz0
  • Kang, Guoliang, Lu Jiang, Yi Yang, and Alexander G. Hauptmann. "Contrastive adaptation network for unsupervised domain adaptation." In Proceedings of the IEEE/CVF conference on computer vision and pattern recognition, pp. 4893-4902. 2019.

• AutoNovel: Automatically Discovering and Learning Novel Visual Categories (Aug. 29, 2024 / Presenter: Sujin Jeon): https://www.youtube.com/watch?v=m7KijNXECIE
  • Han, Kai, Sylvestre-Alvise Rebuffi, Sebastien Ehrhardt, Andrea Vedaldi, and Andrew Zisserman. "Autonovel: Automatically discovering and learning novel visual categories." IEEE Transactions on Pattern Analysis and Machine Intelligence 44, no. 10 (2021): 6767-6781.

• Active Learning Helps Pretrained Models Learn the Intended Task (Jul. 25, 2024 / Presenter: Gyeongho Kim): https://youtu.be/Sz9SW5zF3cg
  • Tamkin, Alex, Dat Nguyen, Salil Deshpande, Jesse Mu, and Noah Goodman. "Active learning helps pretrained models learn the intended task." Advances in Neural Information Processing Systems 35 (2022): 28140-28153.

• Continual Test-Time Domain Adaptation (Jul. 10, 2024 / Presenter: Sujin Jeon): https://youtu.be/qusqyEc2RnQ
  • Wang, Qin, Olga Fink, Luc Van Gool, and Dengxin Dai. "Continual test-time domain adaptation." In Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition, pp. 7201-7211. 2022.

• OCGAN: One-Class Novelty Detection Using GANs With Constrained Latent Representations (Jul. 05, 2024 / Presenter: Soyeon Park): https://youtu.be/xGUmkPc8sNw
  • Perera, Pramuditha, Ramesh Nallapati, and Bing Xiang. "Ocgan: One-class novelty detection using gans with constrained latent representations." In Proceedings of the IEEE/CVF conference on computer vision and pattern recognition, pp. 2898-2906. 2019.

• PT4AL: Using Self-Supervised Pretext Tasks for Active Learning (Jun. 07, 2024 / Presenter: Gyeongho Kim): https://youtu.be/pRrgYaYJCC4
  • Yi, John Seon Keun, Minseok Seo, Jongchan Park, and Dong-Geol Choi. "Pt4al: Using self-supervised pretext tasks for active learning." In European Conference on Computer Vision, pp. 596-612. Cham: Springer Nature Switzerland, 2022.

• BRITS: Bidirectional Recurrent Imputation for Time Series (May 17, 2024 / Presenter: Sujin Jeon): https://youtu.be/yo_re-e9m5k
  • Cao, Wei, Dong Wang, Jian Li, Hao Zhou, Lei Li, and Yitan Li. "Brits: Bidirectional recurrent imputation for time series." Advances in neural information processing systems 31 (2018).

• Denoising Diffusion Probabilistic Models (May 10, 2024 / Presenter: Jae Gyeong Choi): https://youtu.be/0ClUCCYk-BI
  • Ho, Jonathan, Ajay Jain, and Pieter Abbeel. "Denoising diffusion probabilistic models." Advances in neural information processing systems 33 (2020): 6840-6851.

• Gradient Episodic Memory for Continual Learning (Apr. 12 / Presenter: Gyeongho Kim): https://youtu.be/akrCACQQmC0
  • Lopez-Paz, David, and Marc'Aurelio Ranzato. "Gradient episodic memory for continual learning." Advances in neural information processing systems 30 (2017).

• DetCo: Unsupervised Contrastive Learning for Object Detection (Apr. 05 / Presenter: Soyeon Park): https://youtu.be/hWjhy6b01n4
  • Xie, Enze, Jian Ding, Wenhai Wang, Xiaohang Zhan, Hang Xu, Peize Sun, Zhenguo Li, and Ping Luo. "Detco: Unsupervised contrastive learning for object detection." In Proceedings of the IEEE/CVF international conference on computer vision, pp. 8392-8401. 2021.

• Diversify: A General Framework for Time Series Out-of-distribution Detection and Generalization (Mar. 22, 2024 / Presenter: Sujin Jeon): https://youtu.be/2BLL7r_Hjog
  • Lu, Wang, Jindong Wang, Xinwei Sun, Yiqiang Chen, Xiangyang Ji, Qiang Yang, and Xing Xie. "Diversify: A General Framework for Time Series Out-of-distribution Detection and Generalization." IEEE Transactions on Pattern Analysis and Machine Intelligence (2024).

• A Simple Baseline for Bayesian Uncertainty in Deep Learning (Feb. 23, 2024 / Presenter: Gyeongho Kim): https://youtu.be/qc4s_VH5JOY
  • Maddox, Wesley J., Pavel Izmailov, Timur Garipov, Dmitry P. Vetrov, and Andrew Gordon Wilson. "A simple baseline for bayesian uncertainty in deep learning." Advances in neural information processing systems 32 (2019).

• Context-aware Synthesis and Placement of Object Instances (Feb. 02, 2024 / Presenter: Soyeon Park): https://youtu.be/W2a_NPd3Gn8
  • Lee, Donghoon, Sifei Liu, Jinwei Gu, Ming-Yu Liu, Ming-Hsuan Yang, and Jan Kautz. "Context-aware synthesis and placement of object instances." Advances in neural information processing systems 31 (2018).

• Improving Out-of-Distribution Robustness via Selective Augmentation (Jan. 26, 2024 / Presenter: Sujin Jeon): https://youtu.be/W1sTyYRkd4M
  • Yao, Huaxiu, Yu Wang, Sai Li, Linjun Zhang, Weixin Liang, James Zou, and Chelsea Finn. "Improving out-of-distribution robustness via selective augmentation." In International Conference on Machine Learning, pp. 25407-25437. PMLR, 2022.

• High-Resolution Image Synthesis With Latent Diffusion Models (Jan. 05, 2024 / Presenter: Jae Gyeong Choi): https://youtu.be/r_IdGxJlCIk
  • Rombach, Robin, Andreas Blattmann, Dominik Lorenz, Patrick Esser, and Björn Ommer. "High-resolution image synthesis with latent diffusion models." In Proceedings of the IEEE/CVF conference on computer vision and pattern recognition, pp. 10684-10695. 2022.

• Averaging Weights Leads to Wider Optima and Better Generalization (Dec. 22, 2023 / Presenter: Gyeongho Kim): https://youtu.be/pWGXhwrDpHo?si=Gocnbz8jRMB5p6tN
  • Izmailov, Pavel, Dmitrii Podoprikhin, Timur Garipov, Dmitry Vetrov, and Andrew Gordon Wilson. "Averaging weights leads to wider optima and better generalization." arXiv preprint arXiv:1803.05407 (2018).

• Rethinking Minimal Sufficient Representation in Contrastive Learning (Dec. 15, 2023 / Presenter: Soyeon Park): https://youtu.be/y8VuqD2vAzc
  • Wang, Haoqing, Xun Guo, Zhi-Hong Deng, and Yan Lu. "Rethinking minimal sufficient representation in contrastive learning." In Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition, pp. 16041-16050. 2022.

• Domain Generalization by Learning and Removing Domain-specific Features (Dec. 01, 2023 / Presenter: Sujin Jeon): https://youtu.be/-sGFzpQQXTo
  • Ding, Yu, Lei Wang, Bin Liang, Shuming Liang, Yang Wang, and Fang Chen. "Domain generalization by learning and removing domain-specific features." Advances in Neural Information Processing Systems 35 (2022): 24226-24239.

• Deep Batch Active Learning by Diverse, Uncertain Gradient Lower Bounds (Nov. 10, 2023 / Presenter: Gyeongho Kim): https://youtu.be/yTa8Ae4HvNM?si=SV99AlJr-jggDH4L
  • Ash, Jordan T., Chicheng Zhang, Akshay Krishnamurthy, John Langford, and Alekh Agarwal. "Deep batch active learning by diverse, uncertain gradient lower bounds." arXiv preprint arXiv:1906.03671 (2019).

• Unsupervised Time-Series Representation Learning with Iterative Bilinear Temporal-Spectral Fusion (Oct. 13, 2023 / Presenter: Sujin Jeon): https://youtu.be/lhTADMxHU4w
  • Yang, Ling, and Shenda Hong. "Unsupervised time-series representation learning with iterative bilinear temporal-spectral fusion." In International Conference on Machine Learning, pp. 25038-25054. PMLR, 2022.

• Time-Series Representation Learning via Temporal and Contextual Contrasting (Oct. 10, 2023 / Presenter: Jae Gyeong Choi): https://youtu.be/svaTAOyeiNQ
  • Eldele, Emadeldeen, Mohamed Ragab, Zhenghua Chen, Min Wu, Chee Keong Kwoh, Xiaoli Li, and Cuntai Guan. "Time-series representation learning via temporal and contextual contrasting." arXiv preprint arXiv:2106.14112 (2021).

• Rethinking the Augmentation Module in Contrastive Learning: Learning Hierarchical Augmentation Invariance with Expanded Views (Sep. 01, 2023 / Presenter: Soyeon Park): https://youtu.be/WZ42hmtkktg
  • Zhang, Junbo, and Kaisheng Ma. "Rethinking the augmentation module in contrastive learning: Learning hierarchical augmentation invariance with expanded views." In Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition, pp. 16650-16659. 2022.

• SWAD: Domain Generalization by Seeking Flat Minima (Aug. 04, 2023 / Presenter: Sujin Jeon): https://youtu.be/I9MLR-78QzU
  • Cha, Junbum, Sanghyuk Chun, Kyungjae Lee, Han-Cheol Cho, Seunghyun Park, Yunsung Lee, and Sungrae Park. "Swad: Domain generalization by seeking flat minima." Advances in Neural Information Processing Systems 34 (2021): 22405-22418.

• Domain Generalization: A Survey (Jul. 28, 2023 / Presenter: Jae Gyeong Choi): https://youtu.be/ueH89TwBJlg
  • Zhou, Kaiyang, Ziwei Liu, Yu Qiao, Tao Xiang, and Chen Change Loy. "Domain generalization: A survey." IEEE Transactions on Pattern Analysis and Machine Intelligence (2022).

• Active Learning for Convolutional Neural Networks: A Core-Set Approach (Jul. 21, 2023/ Presenter: Gyeongho Kim): https://youtu.be/SogipbE18D4
  • Sener, Ozan, and Silvio Savarese. "Active learning for convolutional neural networks: A core-set approach." arXiv preprint arXiv:1708.00489 (2017).

• Pixel-Wise Anomaly Detection in Complex Driving Scenes (Jul. 07, 2023 / Presenter: Soyeon Park): https://youtu.be/IvqRv5DvXTI
  •  Di Biase, Giancarlo, Hermann Blum, Roland Siegwart, and Cesar Cadena. "Pixel-wise anomaly detection in complex driving scenes." In Proceedings of the IEEE/CVF conference on computer vision and pattern recognition, pp. 16918-16927. 2021.

• PCL: Proxy-Based Contrastive Learning for Domain Generalization (Jun. 30, 2023 / Presenter: Sujin Jeon): https://youtu.be/u6_t4KAWPak
  • Yao, Xufeng, Yang Bai, Xinyun Zhang, Yuechen Zhang, Qi Sun, Ran Chen, Ruiyu Li, and Bei Yu. "PCL: Proxy-based Contrastive Learning for Domain Generalization." In Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition, pp. 7097-7107. 2022.

• Learning Loss for Active Learning (Jun. 22, 2023 / Presenter: Gyeongho Kim): https://youtu.be/lwOysX5pxH0
  • Yoo, Donggeun, and In So Kweon. "Learning loss for active learning." In Proceedings of the IEEE/CVF conference on computer vision and pattern recognition, pp. 93-102. 2019.

• Understanding the Behaviour of Contrastive Loss (Apr. 14, 2023 / Presenter: Sujin Jeon): https://youtu.be/AGvwLTXYH7o
  • Wang, Feng, and Huaping Liu. "Understanding the behaviour of contrastive loss." In Proceedings of the IEEE/CVF conference on computer vision and pattern recognition, pp. 2495-2504. 2021.

• Sharpness-aware Minimization for Efficiently Improving Generalization (Mar. 17, 2023 / Presenter: Gyeongho Kim): https://youtu.be/lcNjbOHf0uo
  • Foret, Pierre, Ariel Kleiner, Hossein Mobahi, and Behnam Neyshabur. "Sharpness-aware minimization for efficiently improving generalization." arXiv preprint arXiv:2010.01412 (2020).

• [Asap-net] Spatially-adaptive pixelwise networks for fast image translation (Feb. 24, 2023 / Presenter: Jae Gyeong Choi): https://youtu.be/drG_YNQ1MVM
  • Shaham, Tamar Rott, Michaël Gharbi, Richard Zhang, Eli Shechtman, and Tomer Michaeli. "Spatially-adaptive pixelwise networks for fast image translation." In Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition, pp. 14882-14891. 2021.

• A Simple Framework for Contrastive Learning of Visual Representations (Feb. 17, 2023 / Presenter: Sujin Jeon): https://youtu.be/zVaXSKvUncE
  • Chen, Ting, Simon Kornblith, Mohammad Norouzi, and Geoffrey Hinton. "A simple framework for contrastive learning of visual representations." In International conference on machine learning, pp. 1597-1607. PMLR, 2020.

• What Uncertainties Do We Need in Bayesian Deep Learning for Computer Vision? (Feb. 03, 2023 / Presenter: Gyeongho Kim): https://youtu.be/2XniGoni_5Q
  • Kendall, Alex, and Yarin Gal. "What uncertainties do we need in bayesian deep learning for computer vision?." Advances in neural information processing systems 30 (2017).

• TabNet: Attentive Interpretable Tabular Learning (Jan. 25, 2023 / Presenter: Jae Gyeong Choi): https://youtu.be/uqaEHcOUCIA
  • Arik, Sercan Ö., and Tomas Pfister. "TabNet: Attentive Interpretable Tabular Learning." In Proceedings of the AAAI Conference on Artificial Intelligence, vol. 35, no. 8, pp. 6679-6687. 2021.

• Tabular data: Deep learning is not all you need (Jan. 18, 2023 / Presenter: Soyeon Park): https://youtu.be/WH39KDQbrb4
  • Shwartz-Ziv, Ravid, and Amitai Armon. "Tabular data: Deep learning is not all you need." Information Fusion 81 (2022): 84-90.

• Prototypical Networks for Few-shot Learning (Nov. 18, 2022 / Presenter: Sujin Jeon): https://youtu.be/ogeBqcSYwgQ
  • Snell, Jake, Kevin Swersky, and Richard Zemel. "Prototypical networks for few-shot learning." Advances in neural information processing systems 30 (2017).

• Weight Uncertainty in Neural Network (Jul. 27, 2022 / Presenter: Gyeongho Kim): https://youtu.be/Pxi_Df6Lx0M
  • Blundell, Charles, Julien Cornebise, Koray Kavukcuoglu, and Daan Wierstra. "Weight uncertainty in neural network." In International conference on machine learning, pp. 1613-1622. PMLR, 2015.

• Interpretability beyond feature attribution: Quantitative testing with concept activation vectors (tcav) (Jul. 13, 2022 / Presenter: Jae Gyeong Choi): https://youtu.be/oHjQCOHhWMM
  • Kim, Been, Martin Wattenberg, Justin Gilmer, Carrie Cai, James Wexler, and Fernanda Viegas. "Interpretability beyond feature attribution: Quantitative testing with concept activation vectors (tcav)." In International conference on machine learning, pp. 2668-2677. PMLR, 2018.

• Domain-adversarial training of neural networks (DANN) (Jul. 01, 2022 / Presenter: Sujin Jeon): https://youtu.be/y1zKpl-rF4E
  • Ganin, Yaroslav, Evgeniya Ustinova, Hana Ajakan, Pascal Germain, Hugo Larochelle, François Laviolette, Mario Marchand, and Victor Lempitsky. "Domain-adversarial training of neural networks." The journal of machine learning research17, no. 1 (2016): 2096-2030.

• An Explainable Convolutional Neural Network for Fault Diagnosis in Linear Motion Guide (Jan. 13, 2022 / Presenter: Jae Gyeong Choi): https://youtu.be/y71Qb5buby8
  • Kim, Min Su, Jong Pil Yun, and PooGyeon Park. "An explainable convolutional neural network for fault diagnosis in linear motion guide." IEEE Transactions on Industrial Informatics 17, no. 6 (2020): 4036-4045.

• Big Self-Supervised Models are Strong Semi-Supervised Learners (Nov. 19, 2021 / Presenter: Gyeongho Kim): https://youtu.be/raYCPNskIEE
  
  • Chen, Ting, Simon Kornblith, Kevin Swersky, Mohammad Norouzi, and Geoffrey E. Hinton. "Big self-supervised models are strong semi-supervised learners." Advances in neural information processing systems 33 (2020): 22243-22255.

• A novel method for predicting delamination of carbon fiber reinforced plastic (CFRP) based on multi-sensor data (Nov. 05, 2021 / Presenter: Jae Gyeong Choi): https://youtu.be/Xo_8z0XV5nQ
  • Cui, Jiacheng, Wei Liu, Yang Zhang, Changyong Gao, Zhe Lu, Ming Li, and Fuji Wang. "A novel method for predicting delamination of carbon fiber reinforced plastic (CFRP) based on multi-sensor data." Mechanical Systems and Signal Processing 157 (2021): 107708.

• BAM: Bottleneck Attention Module (Sep. 24, 2021 / Presenter: Jae Gyeong Choi): https://youtu.be/KJATJc2EpLc
  • Park, Jongchan, Sanghyun Woo, Joon-Young Lee, and In So Kweon. "Bam: Bottleneck attention module." arXiv preprint arXiv:1807.06514 (2018).

• Stacked Hourglass Networks for Human Pose Estimation (Jun. 04, 2021 / Presenter: Jae Gyeong Choi): https://youtu.be/qxXVv3F3bMk
  • Newell, Alejandro, Kaiyu Yang, and Jia Deng. "Stacked hourglass networks for human pose estimation." In European conference on computer vision, pp. 483-499. Springer, Cham, 2016.

• Attention Is All You Need (Feb. 10, 2021 / Presenter: Gyeongho Kim): https://youtu.be/EOTNLT7vTn8
  • Vaswani, Ashish, Noam Shazeer, Niki Parmar, Jakob Uszkoreit, Llion Jones, Aidan N. Gomez, Łukasz Kaiser, and Illia Polosukhin. "Attention is all you need." Advances in neural information processing systems 30 (2017).