DKDaesik Kim

Daesik Kim

*This is an algorithmically generated author record based on publicly available information.

Daesik Kim has a total of 9 co-authors. Here are the top co-authors by number of shared publications:


Latest Publications

  • Open Access

    WAN: Watermarking Attack Network

    by Seung-Hun Nam, In-Jae Yu, Seung-Min Mun, Daesik Kim, Wonhyuk Ahn

    Multi-bit watermarking (MW) has been developed to improve robustness against signal processing operations and geometric distortions. To this end, benchmark tools that test robustness by applying simulated attacks on watermarked images are available. However, limitations in these general attacks exist since they cannot exploit specific characteristics of the targeted MW. In addition, these attacks are usually devised without consideration of visual quality, which rarely occurs in the real world. To address these limitations, we propose a watermarking attack network (WAN), a fully trainable watermarking benchmark tool that utilizes the weak points of the target MW and induces an inversion of the watermark bit, thereby considerably reducing the watermark extractability. To hinder the extraction of hidden information while ensuring high visual quality, we utilize a residual dense blocks-based architecture specialized in local and global feature learning. A novel watermarking attack loss is introduced to break the MW systems. We empirically demonstrate that the WAN can successfully fool various block-based MW systems. Moreover, we show that existing MW methods can be improved with the help of the WAN as an add-on module.


  • Open Access

    Vehicle Image Generation Going Well with The Surroundings

    by Jeesoo Kim, Jangho Kim, Jaeyoung Yoo, Daesik Kim, Nojun Kwak

    Since the generative neural networks have made a breakthrough in the image generation problem, lots of researches on their applications have been studied such as image restoration, style transfer and image completion. However, there has been few research generating objects in uncontrolled real-world environments. In this paper, we propose a novel approach for vehicle image generation in real-world scenes. Using a subnetwork based on a precedent work of image completion, our model makes the shape of an object. Details of objects are trained by an additional colorization and refinement subnetwork, resulting in a better quality of generated objects. Unlike many other works, our method does not require any segmentation layout but still makes a plausible vehicle in the image. We evaluate our method by using images from Berkeley Deep Drive (BDD) and Cityscape datasets, which are widely used for object detection and image segmentation problems. The adequacy of the generated images by the proposed method has also been evaluated using a widely utilized object detection algorithm and the FID score.

  • Open Access

    Maximizing Cosine Similarity Between Spatial Features for Unsupervised Domain Adaptation in Semantic Segmentation

    by Inseop Chung, Daesik Kim, Nojun Kwak

    We propose a novel method that tackles the problem of unsupervised domain adaptation for semantic segmentation by maximizing the cosine similarity between the source and the target domain at the feature level. A segmentation network mainly consists of two parts, a feature extractor and a classification head. We expect that if we can make the two domains have small domain gap at the feature level, they would also have small domain discrepancy at the classification head. Our method computes a cosine similarity matrix between the source feature map and the target feature map, then we maximize the elements exceeding a threshold to guide the target features to have high similarity with the most similar source feature. Moreover, we use a class-wise source feature dictionary which stores the latest features of the source domain to prevent the unmatching problem when computing the cosine similarity matrix and be able to compare a target feature with various source features from various images. Through extensive experiments, we verify that our method gains performance on two unsupervised domain adaptation tasks (GTA5$\to$ Cityscaspes and SYNTHIA$\to$ Cityscapes).