Yonsei University · 情報科学
Professor Kyungjune Baek's research lab specializes in deep learning for computer vision, with a strong focus on self-supervised and unsupervised representation learning, particularly in image generation, image translation, and attribute manipulation. The lab explores robust learning under weak or noisy supervision, develops novel self-supervised signal designs such as geometric transformations and frequency-domain statistics, and addresses critical challenges like data privacy, copyright risks, and generalization in few-shot and low-resource settings. A central theme is building models that are not only accurate but also reliable, unbiased, and secure in real-world applications.
Figures are computed from collected data and may differ slightly.
Every recent image-to-image translation model inherently requires either image-level (i.e. input-output pairs) or set-level (i.e. domain labels) supervision. However, even set-level supervision can be a severe bottleneck for data collection in practice. In this paper, we tackle image-to-image translation in a fully unsupervised setting, i.e., neither paired images nor domain labels. To this end, we propose a truly unsupervised image-to-image translation model (TUNIT) that simultaneously learns t
Existing co-localization techniques significantly lose performance over weakly or fully supervised methods in accuracy and inference time. In this paper, we overcome common drawbacks of co-localization techniques by utilizing self-supervised learning approach. The major technical contributions of the proposed method are two-fold. 1) We devise a new geometric transformation, namely point symmetric transformation and utilize its parameters as an artificial label for self-supervised learning. This
Transfer learning for GANs successfully improves generation performance under low-shot regimes. However, existing studies show that the pretrained model using a single benchmark dataset is not generalized to various target datasets. More importantly, the pretrained model can be vulnerable to copyright or privacy risks as membership inference attack advances. To resolve both issues, we propose an effective and unbiased data synthesizer, namely Primitives - PS, inspired by the generic characterist
The remarkable performance of deep neural networks heavily rely on large-scale datasets with high-quality annotations. Since the data collection process such as web crawling naturally involves unreliable supervision (i.e., noisy label), handling samples with noisy labels has been actively studied. Existing methods in learning with noisy labels (LNL) 1) develop the sampling strategy for filtering out the noisy labels or 2) devise the robust loss function against noisy labels. As a result of these
We propose a novel framework for simultaneously generating and manipulating the face images with desired attributes. While the state-of-the-art attribute editing technique has achieved the impressive performance for creating realistic attribute effects, they only address the image editing problem, using the input image as the condition of model. Recently, several studies attempt to tackle both novel face generation and attribute editing problem using a single solution. However, their image quali
Transfer learning for GANs successfully improves generation performance under low-shot regimes. However, existing studies show that the pretrained model using a single benchmark dataset is not generalized to various target datasets. More importantly, the pretrained model can be vulnerable to copyright or privacy risks as membership inference attack advances. To resolve both issues, we propose an effective and unbiased data synthesizer, namely Primitives-PS, inspired by the generic characteristic
Every recent image-to-image translation model inherently requires either image-level (i.e. input-output pairs) or set-level (i.e. domain labels) supervision. However, even set-level supervision can be a severe bottleneck for data collection in practice. In this paper, we tackle image-to-image translation in a fully unsupervised setting, i.e., neither paired images nor domain labels. To this end, we propose a truly unsupervised image-to-image translation model (TUNIT) that simultaneously learns t
Open papers in the app to read, cite, and organize with AI.
