Author name cluster

Jongwon Choi

Possible papers associated with this exact author name in Arrow. This page groups case-insensitive exact name matches and is not a full identity disambiguation profile.

10 papers

2 author rows

AAAI Conference 2026 Conference Paper

Through the Water: Refractive Gaussian Splatting for Water Surface Scenes

Yeonghun Yoon
Hojoon Jung
Jaeyoon Lee
Taegwan Kim
Gyuhyun Kim
Jongwon Choi

Scenes with water surfaces present a significant challenge for Gaussian Splatting due to the simultaneous presence of refraction and reflection, as well as the difficulty of accurately estimating the geometry of transparent water surfaces. To address this, we propose a novel framework for reconstructing scenes involving both reflection and refraction caused by water surfaces. The water surface is modeled as a trainable plane, and 2D Gaussian ray tracing is applied to account for refraction through the water. We extend 2D Gaussian Splatting by introducing a soft mask parameter and a dual set of Gaussian primitives, which handle both reflected and refracted effects. Our method achieves state-of-the-art performance on newly constructed water surface datasets, including both synthetic and real scenes, and significantly outperforms prior approaches in water-interacting regions. Furthermore, we demonstrate the editability of our model by manipulating the index of refraction to suppress or modify refractive effects, enabling scene transformations into different liquids.

PDF Details DOI

ECAI Conference 2025 Conference Paper

Category-Specific Augmentation Search Using Attentional Interpolation for Unsupervised Domain Adaptation

Mingyu Lee 0001
Jongwon Choi

This paper addresses a critical challenge in Unsupervised Domain Adaptation (UDA): achieving effective domain alignment without losing category-specific information. We propose a novel, category-specific augmentation method that applies targeted strategies tailored to each category. This approach reduces the visual domain gap and retains essential contextual information unique to each category, addressing the underfitting problems commonly encountered with traditional category-agnostic augmentation methods. We propose an attentional interpolation method to reduce the computational demands of validating numerous combinations of category-specific augmentations. This method optimizes augmentation strategy selection within a single training session, significantly improving efficiency. Our process, that is compatible with a range of existing UDA techniques, has undergone rigorous validation, demonstrating consistent performance improvements across various domain adaptation frameworks by maintaining fixed hyperparameters in integrated methods.

Details

AAAI Conference 2025 Conference Paper

NBA3D: Neighbor-Based Confidence Adjustment for 3D Rare Object Detection Using LiDAR

Jooyoung Lee
Jaeyoon Lee
Jongwon Choi

Recent research on LiDAR-based 3D object detectors has shown strong performance; however, evaluations typically focus on dominant classes, overlooking rare classes, such as strollers, which could be critical in real autonomous driving scenarios. This oversight is problematic because state-of-the-art 3D object detectors show significantly lower performance on rare classes compared to dominant ones when trained on both. To address this issue and achieve accurate 3D rare object detection using only LiDAR data, we propose the Neighbor-Based confidence Adjustment for 3D rare class predictions (NBA3D). NBA3D utilizes a graph neural network to analyze the surrounding environment of rare class prediction boxes, enabling a more effective distinction between true positives and false positives based on their local context. Our approach utilizes both 3D prediction box characteristics and CLIP-based class semantic information to better contextualize neighboring objects. Various experiments demonstrate that NBA3D effectively improves the detection performance of rare class objects, regardless of the type of 3D object detectors used.

PDF Details DOI

EAAI Journal 2025 Journal Article

Style prompt tuning for bridging visual gaps in autonomous driving

Suyeon Cha
Giyun Choi
Minji Kwak
Jongwon Choi

Artificial intelligence models for semantic segmentation and image classification in autonomous driving must maintain reliability across adverse conditions such as rain, fog, snow, and nighttime. However, models trained on only clear daytime images often fail to generalize under such domain shifts. Existing unsupervised domain adaptation (UDA) methods employ image-level style transfer using generative adversarial networks (GANs) or diffusion models, which necessitate paired data and risk altering content. Therefore, this study proposes Style Prompt Tuning, a novel UDA framework that utilizes image–text models to automatically generate and optimize textual prompts representing target-domain styles. These prompts guide a U-Net-based style network to synthesize source images in the target style while preserving their semantic content. Our approach employs clustering within the Contrastive Language—Image Pretraining (CLIP) embedding space and a composite loss function, including content, style, transfer, patch, and total variation terms to optimize prompt quality. The generated stylized images augment the source dataset and are used to train more robust task models. Experiments on semantic segmentation benchmarks (Cityscapes-to-Adverse Conditions Dataset with Correspondences (ACDC), DarkZurich, BDD100k-night, and Nighttime Driving) and image classification (Visual Domain Adaptation 2017) reveal our approach to achieve improvements of +3. 4 mean intersection-over-union (mIoU) and +0. 8% accuracy over prior UDA methods. These results highlight our method’s practical effectiveness for real-world autonomous driving applications under visually challenging scenarios.

Details DOI

AAAI Conference 2024 Conference Paper

Topic-VQ-VAE: Leveraging Latent Codebooks for Flexible Topic-Guided Document Generation

YoungJoon Yoo
Jongwon Choi

This paper introduces a novel approach for topic modeling utilizing latent codebooks from Vector-Quantized Variational Auto-Encoder~(VQ-VAE), discretely encapsulating the rich information of the pre-trained embeddings such as the pre-trained language model. From the novel interpretation of the latent codebooks and embeddings as conceptual bag-of-words, we propose a new generative topic model called Topic-VQ-VAE~(TVQ-VAE) which inversely generates the original documents related to the respective latent codebook. The TVQ-VAE can visualize the topics with various generative distributions including the traditional BoW distribution and the autoregressive image generation. Our experimental results on document analysis and image generation demonstrate that TVQ-VAE effectively captures the topic context which reveals the underlying structures of the dataset and supports flexible forms of document generation. Official implementation of the proposed TVQ-VAE is available at https://github.com/clovaai/TVQ-VAE.

PDF Details DOI

ICML Conference 2023 Conference Paper

Scaling of Class-wise Training Losses for Post-hoc Calibration

Seungjin Jung
Seungmo Seo
Yonghyun Jeong
Jongwon Choi

The class-wise training losses often diverge as a result of the various levels of intra-class and inter-class appearance variation, and we find that the diverging class-wise training losses cause the uncalibrated prediction with its reliability. To resolve the issue, we propose a new calibration method to synchronize the class-wise training losses. We design a new training loss to alleviate the variance of class-wise training losses by using multiple class-wise scaling factors. Since our framework can compensate the training losses of overfitted classes with those of under-fitted classes, the integrated training loss is preserved, preventing the performance drop even after the model calibration. Furthermore, our method can be easily employed in the post-hoc calibration methods, allowing us to use the pre-trained model as an initial model and reduce the additional computation for model calibration. We validate the proposed framework by employing it in the various post-hoc calibration methods, which generally improves calibration performance while preserving accuracy, and discover through the investigation that our approach performs well with unbalanced datasets and untuned hyperparameters.

Details

AAAI Conference 2022 Conference Paper

FrePGAN: Robust Deepfake Detection Using Frequency-Level Perturbations

Yonghyun Jeong
Doyeon Kim
Youngmin Ro
Jongwon Choi

Various deepfake detectors have been proposed, but challenges still exist to detect images of unknown categories or GAN models outside of the training settings. Such issues arise from the overfitting issue, which we discover from our own analysis and the previous studies to originate from the frequency-level artifacts in generated images. We find that ignoring the frequency-level artifacts can improve the detector’s generalization across various GAN models, but it can reduce the model’s performance for the trained GAN models. Thus, we design a framework to generalize the deepfake detector for both the known and unseen GAN models. Our framework generates the frequency-level perturbation maps to make the generated images indistinguishable from the real images. By updating the deepfake detector along with the training of the perturbation generator, our model is trained to detect the frequency-level artifacts at the initial iterations and consider the image-level irregularities at the last iterations. For experiments, we design new test scenarios varying from the training settings in GAN models, color manipulations, and object categories. Numerous experiments validate the state-of-the-art performance of our deepfake detector.

PDF Details

AAAI Conference 2020 Conference Paper

Associative Variational Auto-Encoder with Distributed Latent Spaces and Associators

Dae Ung Jo
ByeongJu Lee
Jongwon Choi
Haanju Yoo
Jin Young Choi

In this paper, we propose a novel structure for a multimodal data association referred to as Associative Variational Auto-Encoder (AVAE). In contrast to the existing models using a shared latent space among modalities, our structure adopts distributed latent spaces for multi-modalities which are connected through cross-modal associators. The proposed structure successfully associates even heterogeneous modality data and easily incorporates the additional modality to the entire network via the associator. Furthermore, in our structure, only a small amount of supervised (paired) data is enough to train associators after training auto-encoders in an unsupervised manner. Through experiments, the effectiveness of the proposed structure is validated on various datasets including visual and auditory data.

PDF Details

AAAI Conference 2020 Conference Paper

Visual Domain Adaptation by Consensus-Based Transfer to Intermediate Domain

Jongwon Choi
Youngjoon Choi
Jihoon Kim
Jinyeop Chang
Ilhwan Kwon
Youngjune Gwon
Seungjai Min

We describe an unsupervised domain adaptation framework for images by a transform to an abstract intermediate domain and ensemble classiﬁers seeking a consensus. The intermediate domain can be thought as a latent domain where both the source and target domains can be transferred easily. The proposed framework aligns both domains to the intermediate domain, which greatly improves the adaptation performance when the source and target domains are notably dissimilar. In addition, we propose an ensemble model trained by confusing multiple classiﬁers and letting them make a consensus alternately to enhance the adaptation performance for ambiguous samples. To estimate the hidden intermediate domain and the unknown labels of the target domain simultaneously, we develop a training algorithm using a double-structured architecture. We validate the proposed framework in hard adaptation scenarios with real-world datasets from simple synthetic domains to complex real-world domains. The proposed algorithm outperforms the previous state-of-the-art algorithms on various environments.

PDF Details

AAAI Conference 2019 Conference Paper

Backbone Cannot Be Trained at Once: Rolling Back to Pre-Trained Network for Person Re-Identification

Youngmin Ro
Jongwon Choi
Dae Ung Jo
Byeongho Heo
Jongin Lim
Jin Young Choi

In person re-identification (ReID) task, because of its shortage of trainable dataset, it is common to utilize fine-tuning method using a classification network pre-trained on a large dataset. However, it is relatively difficult to sufficiently finetune the low-level layers of the network due to the gradient vanishing problem. In this work, we propose a novel fine-tuning strategy that allows low-level layers to be sufficiently trained by rolling back the weights of high-level layers to their initial pre-trained weights. Our strategy alleviates the problem of gradient vanishing in low-level layers and robustly trains the low-level layers to fit the ReID dataset, thereby increasing the performance of ReID tasks. The improved performance of the proposed strategy is validated via several experiments. Furthermore, without any addons such as pose estimation or segmentation, our strategy exhibits state-of-the-art performance using only vanilla deep convolutional neural network architecture.

PDF Details