12 papers
Self-Supervised Representation-Guided Generative Dataset Distillation
Mingzhuo Li, Guang Li, Linfeng Ye +4
Dataset distillation compresses a large training set into a compact synthetic set while retaining its downstream utility. Most existing methods target randomly initialized networks…
Region-Wise Correspondence Prediction between Manga Line Art Images
Yingxuan Li, Jiafeng Mao, Qianru Qiu +1
Understanding region-wise correspondences between manga line art images is fundamental for high-level manga processing, supporting downstream tasks such as line art colorization an…
SAS: Semantic-aware Sampling for Generative Dataset Distillation
Mingzhuo Li, Guang Li, Linfeng Ye +4
Deep neural networks have achieved impressive performance across a wide range of tasks, but this success often comes with substantial computational and storage costs due to large-s…
Difficulty-guided Sampling: Bridging the Target Gap between Dataset Distillation and Downstream Tasks
Mingzhuo Li, Guang Li, Linfeng Ye +4
In this paper, we propose difficulty-guided sampling (DGS) to bridge the target gap between the distillation objective and the downstream task, therefore improving the performance…
Difficulty Controlled Diffusion Model for Synthesizing Effective Training Data
Zerun Wang, Jiafeng Mao, Xueting Wang +1
Generative models have become a powerful tool for synthesizing training data in computer vision tasks. Current approaches solely focus on aligning generated images with the target…
Noisy Label Refinement with Semantically Reliable Synthetic Images
Yingxuan Li, Jiafeng Mao, Yusuke Matsui
Semantic noise in image classification datasets, where visually similar categories are frequently mislabeled, poses a significant challenge to conventional supervised learning appr…