Timezone: »

 
Poster
Understanding Cross-Domain Few-Shot Learning Based on Domain Similarity and Few-Shot Difficulty
Jaehoon Oh · Sungnyun Kim · Namgyu Ho · Jin-Hwa Kim · Hwanjun Song · Se-Young Yun

Tue Nov 29 09:00 AM -- 11:00 AM (PST) @ Hall J #238
in Poster Session 1 »

Cross-domain few-shot learning (CD-FSL) has drawn increasing attention for handling large differences between the source and target domains--an important concern in real-world scenarios. To overcome these large differences, recent works have considered exploiting small-scale unlabeled data from the target domain during the pre-training stage. This data enables self-supervised pre-training on the target domain, in addition to supervised pre-training on the source domain. In this paper, we empirically investigate which pre-training is preferred based on domain similarity and few-shot difficulty of the target domain. We discover that the performance gain of self-supervised pre-training over supervised pre-training becomes large when the target domain is dissimilar to the source domain, or the target domain itself has low few-shot difficulty. We further design two pre-training schemes, mixed-supervised and two-stage learning, that improve performance. In this light, we present six findings for CD-FSL, which are supported by extensive experiments and analyses on three source and eight target benchmark datasets with varying levels of domain similarity and few-shot difficulty. Our code is available at https://github.com/sungnyun/understanding-cdfsl.

Keywords: pre-training · Domain Similarity · Cross-domain Few-shot Learning · Few-Shot Difficulty

Author Information

Jaehoon Oh (KAIST)
Sungnyun Kim (KAIST)
Namgyu Ho (KAIST)
Jin-Hwa Kim (NAVER AI Lab)
Jin-Hwa Kim

Jin-Hwa Kim has been Technical Leader and Research Scientist at NAVER AI Lab since August 2021 and Guest Assistant Professor at Artificial Intelligence Institute of Seoul National University (SNU AIIS) since August 2022. He has been studying multimodal deep learning (e.g., [visual question answering](http://visualqa.org)), multimodal generation, ethical AI, and other related topics. In 2018, he received Ph.D. from Seoul National University under the supervision of Professor [Byoung-Tak Zhang](https://bi.snu.ac.kr/~btzhang/) for the work on "Multimodal Deep Learning for Visually-grounded Reasoning." In September 2017, he received [2017 Google Ph.D. Fellowship](https://ai.googleblog.com/2017/09/highlights-from-annual-google-phd.html) in Machine Learning, Ph.D. Completion Scholarship by Seoul National University, and the VQA Challenge 2018 runners-up at the [CVPR 2018 VQA Challenge and Visual Dialog Workshop](https://visualqa.org/workshop_2018.html). He was Research Intern at [Facebook AI Research](https://research.fb.com/category/facebook-ai-research/) (Menlo Park, CA) mentored by [Yuandong Tian](http://yuandong-tian.com), [Devi Parikh](https://www.cc.gatech.edu/~parikh/), and [Dhruv Batra](https://www.cc.gatech.edu/~dbatra/), from January to May in 2017. He had worked for SK Telecom (August 2018 to July 2021) and SK Communications (January 2011 to October 2012).

Hwanjun Song (AWS AI Lab)
Se-Young Yun (KAIST)

More from the Same Authors