Search Results for author: Kazuhiro Hotta

Found 16 papers, 3 papers with code

Lite-HRNet Plus: Fast and Accurate Facial Landmark Detection

no code implementations23 Aug 2023 Sota Kato, Kazuhiro Hotta, Yuhki Hatakeyama, Yoshinori Konishi

Lite-HRNet Plus achieves two improvements: a novel fusion block based on a channel attention and a novel output module with less computational intensity using multi-resolution feature maps.

Facial Landmark Detection

Enlarged Large Margin Loss for Imbalanced Classification

1 code implementation15 Jun 2023 Sota Kato, Kazuhiro Hotta

Although, by using LDAM loss, it is possible to obtain large margins for the minority classes and small margins for the majority classes, the relevance to a large margin, which is included in the original softmax cross entropy loss, is not be clarified yet.

Classification Image Classification +1

DeformableFormer: Classification of Endoscopic Ultrasound Guided Fine Needle Biopsy in Pancreatic Diseases

no code implementations21 Apr 2023 Taiji Kurami, Takuya Ishikawa, Kazuhiro Hotta

However, the images of pancreatic tissue fragments used in this study cannot be successfully classified by processing the entire image because the pancreatic tissue fragments are only a part of the image.

Image Classification

One-shot and Partially-Supervised Cell Image Segmentation Using Small Visual Prompt

1 code implementation17 Apr 2023 Sota Kato, Kazuhiro Hotta

Semantic segmentation of microscopic cell images using deep learning is an important technique, however, it requires a large number of images and ground truth labels for training.

Image Segmentation One-Shot Segmentation +1

Reconstructed Student-Teacher and Discriminative Networks for Anomaly Detection

no code implementations14 Oct 2022 Shinji Yamada, Satoshi Kamiya, Kazuhiro Hotta

To improve the accuracy of STPM, this work uses a student network, as in generative models, to reconstruct normal features.

Anomaly Detection

Adaptive t-vMF Dice Loss for Multi-class Medical Image Segmentation

1 code implementation16 Jul 2022 Sota Kato, Kazuhiro Hotta

Based on the t-vMF similarity, our proposed Dice loss is formulated in a more compact similarity loss function than the original Dice loss.

Image Segmentation Medical Image Segmentation +1

Adversarial Mutual Leakage Network for Cell Image Segmentation

no code implementations20 Mar 2022 Hiroki Tsuda, Kazuhiro Hotta

Finally, we propose an Adversarial Mutual Leakage Network (AML-Net) that mutually leaks the information each other between the generator and the discriminator.

Image Segmentation Segmentation +1

Localized Feature Aggregation Module for Semantic Segmentation

no code implementations3 Dec 2021 Ryouichi Furukawa, Kazuhiro Hotta

The proposed method recovers positional information by emphasizing the similarity between decoder's feature maps with superior semantic information and encoder's feature maps with superior positional information.

Decoder Semantic Segmentation

Reconstruction Student with Attention for Student-Teacher Pyramid Matching

no code implementations30 Nov 2021 Shinji Yamada, Kazuhiro Hotta

The other student-teacher network has a role to reconstruct the features of normal products.

Anomaly Detection

Automatic Preprocessing and Ensemble Learning for Low Quality Cell Image Segmentation

no code implementations30 Aug 2021 Sota Kato, Kazuhiro Hotta

We propose an automatic preprocessing and ensemble learning for segmentation of cell images with low quality.

Ensemble Learning Image Segmentation +2

MSE Loss with Outlying Label for Imbalanced Classification

no code implementations6 Jul 2021 Sota Kato, Kazuhiro Hotta

Unlike CE loss, MSE loss is possible to equalize the number of back propagation for all classes and to learn the feature space considering the relationships between classes as metric learning.

Classification imbalanced classification +2

Cell image segmentation by Feature Random Enhancement Module

no code implementations20 Jan 2021 Takamasa Ando, Kazuhiro Hotta

Although loss function is optimized in training deep neural network, far layers from the layers for computing loss function are difficult to train.

Image Segmentation Segmentation +1

Feature Sharing Cooperative Network for Semantic Segmentation

no code implementations20 Jan 2021 Ryota Ikedo, Kazuhiro Hotta

By sharing feature maps, one of two networks can obtain the information that cannot be obtained by a single network.

Segmentation Semantic Segmentation

Feedback Attention for Cell Image Segmentation

no code implementations14 Aug 2020 Hiroki Tsuda, Eisuke Shibuya, Kazuhiro Hotta

In this paper, we address cell image segmentation task by Feedback Attention mechanism like feedback processing.

Image Segmentation Segmentation +1

Feedback U-net for Cell Image Segmentation

no code implementations30 Apr 2020 Eisuke Shibuya, Kazuhiro Hotta

By using Convolutional LSTM, the features in the second round are extracted based on the features acquired in the first round.

Image Segmentation Semantic Segmentation

Mixture of Counting CNNs: Adaptive Integration of CNNs Specialized to Specific Appearance for Crowd Counting

no code implementations28 Mar 2017 Shohei Kumagai, Kazuhiro Hotta, Takio Kurita

In this paper, we propose to predict the number of targets using multiple CNNs specialized to a specific appearance, and those CNNs are adaptively selected according to the appearance of a test image.

Crowd Counting

Cannot find the paper you are looking for? You can Submit a new open access paper.