9 citations · 26 across the 13 of their papers we have counts for
13 papers
DPPE: Rethinking Camera-Based Positional Encoding for Scaling Multi-View Transformers
Shun Kenney, Teppei Suzuki
The remarkable scalability of Transformers has expanded their application to 3D computer vision, where camera-aware positional encoding is crucial for providing spatial cues in mul…
Feature Space Particle Inference for Neural Network Ensembles
Shingo Yashima, Teppei Suzuki, Kohta Ishikawa +2
Ensembles of deep neural networks demonstrate improved performance over single models. For enhancing the diversity of ensemble members while keeping their performance, particle-bas…
HCFormer: Unified Image Segmentation with Hierarchical Clustering
Teppei Suzuki
Hierarchical clustering is an effective and efficient approach widely used for classical image segmentation methods. However, many existing methods using neural networks generate s…
TeachAugment: Data Augmentation Optimization Using Teacher Knowledge
Teppei Suzuki
Optimization of image transformation functions for the purpose of data augmentation has been intensively studied. In particular, adversarial data augmentation strategies, which sea…
Implicit Integration of Superpixel Segmentation into Fully Convolutional Networks
Teppei Suzuki
Superpixels are a useful representation to reduce the complexity of image data. However, to combine superpixels with convolutional neural networks (CNNs) in an end-to-end fashion,…
Irregularly Tabulated MLP for Fast Point Feature Embedding
Yusuke Sekikawa, Teppei Suzuki
Aiming at drastic speedup for point-feature embeddings at test time, we propose a new framework that uses a pair of multi-layer perceptrons (MLP) and a lookup table (LUT) to transf…