9 papers
Pool-Select-Refine for Allocation-Aware Generative Dataset Distillation
Wenmin Li, Shunsuke Sakai, Zhongkai Zhao +1
Diffusion-based dataset distillation has recently emerged as a promising paradigm for condensing large-scale datasets into compact synthetic sets. By leveraging pretrained generati…
VID-AD: A Dataset for Image-Level Logical Anomaly Detection under Vision-Induced Distraction
Hiroto Nakata, Yawen Zou, Shunsuke Sakai +5
Logical anomaly detection in industrial inspection remains challenging due to variations in visual appearance (e.g., background clutter, illumination shift, and blur), which often…
DSeq-JEPA: Discriminative Sequential Joint-Embedding Predictive Architecture
Xiangteng He, Shunsuke Sakai, Shivam Chandhok +5
Recent advances in self-supervised visual representation learning have demonstrated the effectiveness of predictive latent-space objectives for learning transferable features. In p…
Few-shot Human Action Anomaly Detection via a Unified Contrastive Learning Framework
Koichiro Kamide, Shunsuke Sakai, Shun Maeda +2
Human Action Anomaly Detection (HAAD) aims to identify anomalous actions given only normal action data during training. Existing methods typically follow a one-model-per-category p…
Contrastive Learning-Enhanced Trajectory Matching for Small-Scale Dataset Distillation
Wenmin Li, Shunsuke Sakai, Tatsuhito Hasegawa
Deploying machine learning models in resource-constrained environments, such as edge devices or rapid prototyping scenarios, increasingly demands distillation of large datasets int…
Analytical Softmax Temperature Setting from Feature Dimensions for Model- and Domain-Robust Classification
Tatsuhito Hasegawa, Shunsuke Sakai
In deep learning-based classification tasks, the softmax function's temperature parameter critically influences the output distribution and overall performance. This study pres…
Noisy Deep Ensemble: Accelerating Deep Ensemble Learning via Noise Injection
Shunsuke Sakai, Shunsuke Tsuge, Tatsuhito Hasegawa
Neural network ensembles is a simple yet effective approach for enhancing generalization capabilities. The most common method involves independently training multiple neural networ…
InvAD: Inversion-based Reconstruction-Free Anomaly Detection with Diffusion Models
Shunsuke Sakai, Xiangteng He, Chunzhi Gu +2
Despite the remarkable success, recent reconstruction-based anomaly detection (AD) methods via diffusion modeling still involve fine-grained noise-strength tuning and computational…
LADMIM: Logical Anomaly Detection with Masked Image Modeling in Discrete Latent Space
Shunsuke Sakai, Tatushito Hasegawa, Makoto Koshino
Detecting anomalies such as an incorrect combination of objects or deviations in their positions is a challenging problem in unsupervised anomaly detection (AD). Since conventional…