Search Results for author: Shin'ichi Satoh

Found 31 papers, 9 papers with code

Improving Generalization of Metric Learning via Listwise Self-distillation

1 code implementation17 Jun 2022 Zelong Zeng, Fan Yang, Zheng Wang, Shin'ichi Satoh

Most deep metric learning (DML) methods employ a strategy that forces all positive samples to be close in the embedding space while keeping them away from negative ones.

Metric Learning

Unsupervised Foggy Scene Understanding via Self Spatial-Temporal Label Diffusion

1 code implementation10 Jun 2022 Liang Liao, WenYi Chen, Jing Xiao, Zheng Wang, Chia-Wen Lin, Shin'ichi Satoh

Specifically, based on the two discoveries of local spatial similarity and adjacent temporal correspondence of the sequential image data, we propose a novel Target-Domain driven pseudo label Diffusion (TDo-Dif) scheme.

Autonomous Driving Scene Understanding +3

Geo-Localization via Ground-to-Satellite Cross-View Image Retrieval

no code implementations22 May 2022 Zelong Zeng, Zheng Wang, Fan Yang, Shin'ichi Satoh

The large variation of viewpoint and irrelevant content around the target always hinder accurate image retrieval and its subsequent tasks.

Image Retrieval Representation Learning

Improving Camouflaged Object Detection with the Uncertainty of Pseudo-edge Labels

1 code implementation29 Oct 2021 Nobukatsu Kajiura, Hong Liu, Shin'ichi Satoh

This framework consists of three key components, i. e., a pseudo-edge generator, a pseudo-map generator, and an uncertainty-aware refinement module.

object-detection Object Detection

Scalable Personalised Item Ranking through Parametric Density Estimation

no code implementations11 May 2021 Riku Togashi, Masahiro Kato, Mayu Otani, Tetsuya Sakai, Shin'ichi Satoh

However, such methods have two main drawbacks particularly in large-scale applications; (1) the pairwise approach is severely inefficient due to the quadratic computational cost; and (2) even recent model-based samplers (e. g. IRGAN) cannot achieve practical efficiency due to the training of an extra model.

Density Estimation Learning-To-Rank

Density-Ratio Based Personalised Ranking from Implicit Feedback

no code implementations19 Jan 2021 Riku Togashi, Masahiro Kato, Mayu Otani, Shin'ichi Satoh

Learning from implicit user feedback is challenging as we can only observe positive samples but never access negative ones.

Density Ratio Estimation

Image Inpainting Guided by Coherence Priors of Semantics and Textures

no code implementations CVPR 2021 Liang Liao, Jing Xiao, Zheng Wang, Chia-Wen Lin, Shin'ichi Satoh

In this paper, we introduce coherence priors between the semantics and textures which make it possible to concentrate on completing separate textures in a semantic-wise manner.

Image Inpainting Semantic Segmentation

Alleviating Cold-Start Problems in Recommendation through Pseudo-Labelling over Knowledge Graph

2 code implementations10 Nov 2020 Riku Togashi, Mayu Otani, Shin'ichi Satoh

Solving cold-start problems is indispensable to provide meaningful recommendation results for new users and items.

Towards Unsupervised Crowd Counting via Regression-Detection Bi-knowledge Transfer

no code implementations12 Aug 2020 Yuting Liu, Zheng Wang, Miaojing Shi, Shin'ichi Satoh, Qijun Zhao, Hongyu Yang

We formulate the mutual transformations between the outputs of regression- and detection-based models as two scene-agnostic transformers which enable knowledge distillation between the two models.

Crowd Counting Knowledge Distillation +2

Beyond Intra-modality: A Survey of Heterogeneous Person Re-identification

no code implementations24 May 2019 Zheng Wang, Zhixiang Wang, Yinqiang Zheng, Yang Wu, Wen-Jun Zeng, Shin'ichi Satoh

An efficient and effective person re-identification (ReID) system relieves the users from painful and boring video watching and accelerates the process of video analysis.

Person Re-Identification

DotSCN: Group Re-identification via Domain-Transferred Single and Couple Representation Learning

no code implementations13 May 2019 Ziling Huang, Zheng Wang, Chung-Chi Tsai, Shin'ichi Satoh, Chia-Wen Lin

To gain the superiority of deep learning models, we treat a group as multiple persons and transfer the domain of a labeled ReID dataset to a G-ReID target dataset style to learn single representations.

Person Re-Identification Representation Learning

Illumination-Adaptive Person Re-identification

no code implementations11 May 2019 Zelong Zeng, Zhixiang Wang, Zheng Wang, Yinqiang Zheng, Yung-Yu Chuang, Shin'ichi Satoh

To demonstrate the illumination issue and to evaluate our model, we construct two large-scale simulated datasets with a wide range of illumination variations.

Disentanglement Person Re-Identification +1

Learning More with Less: GAN-based Medical Image Augmentation

no code implementations29 Mar 2019 Changhee Han, Kohei Murao, Shin'ichi Satoh, Hideki Nakayama

Convolutional Neural Network (CNN)-based accurate prediction typically requires large-scale annotated training data.

Image Augmentation object-detection +1

Efficient Image Retrieval via Decoupling Diffusion into Online and Offline Processing

2 code implementations27 Nov 2018 Fan Yang, Ryota Hinami, Yusuke Matsui, Steven Ly, Shin'ichi Satoh

Diffusion is commonly used as a ranking or re-ranking method in retrieval tasks to achieve higher retrieval performance, and has attracted lots of attention in recent years.

Image Retrieval Re-Ranking

Reconfigurable Inverted Index

1 code implementation12 Aug 2018 Yusuke Matsui, Ryota Hinami, Shin'ichi Satoh

Owing to the linear layout, the data structure can be dynamically adjusted after new items are added, maintaining the fast speed of the system.

Harnessing AI for Speech Reconstruction using Multi-view Silent Video Feed

no code implementations2 Jul 2018 Yaman Kumar, Mayank Aggarwal, Pratham Nawal, Shin'ichi Satoh, Rajiv Ratn Shah, Roger Zimmerman

Recently, research has started venturing into generating (audio) speech from silent video sequences but there have been no developments thus far in dealing with divergent views and poses of a speaker.

Sound Audio and Speech Processing

Digital Watermarking for Deep Neural Networks

no code implementations6 Feb 2018 Yuki Nagai, Yusuke Uchida, Shigeyuki Sakazawa, Shin'ichi Satoh

In this paper, we propose a digital watermarking technology for ownership authorization of deep neural networks.

Consensus-based Sequence Training for Video Captioning

no code implementations27 Dec 2017 Sang Phan, Gustav Eje Henter, Yusuke Miyao, Shin'ichi Satoh

First we show that, by replacing model samples with ground-truth sentences, RL training can be seen as a form of weighted cross-entropy loss, giving a fast, RL-based pre-training algorithm.

Video Captioning

Discriminative Learning of Open-Vocabulary Object Retrieval and Localization by Negative Phrase Augmentation

no code implementations EMNLP 2018 Ryota Hinami, Shin'ichi Satoh

The proposed method can retrieve and localize objects specified by a textual query from one million images in only 0. 5 seconds with high precision.

object-detection Object Detection

Region-Based Image Retrieval Revisited

no code implementations26 Sep 2017 Ryota Hinami, Yusuke Matsui, Shin'ichi Satoh

Second, to help users specify spatial relationships among objects in an intuitive way, we propose recommendation techniques of spatial relationships.

Image Retrieval Re-Ranking

Joint Detection and Recounting of Abnormal Events by Learning Deep Generic Knowledge

no code implementations ICCV 2017 Ryota Hinami, Tao Mei, Shin'ichi Satoh

Although convolutional neural networks (CNNs) have achieved promising results in learning such concepts, it remains an open question as to how to effectively use CNNs for abnormal event detection, mainly due to the environment-dependent nature of the anomaly detection.

Anomaly Detection Event Detection

Embedding Watermarks into Deep Neural Networks

1 code implementation15 Jan 2017 Yusuke Uchida, Yuki Nagai, Shigeyuki Sakazawa, Shin'ichi Satoh

Secondly, we propose a general framework to embed a watermark into model parameters using a parameter regularizer.

Image Retrieval with Fisher Vectors of Binary Features

no code implementations27 Sep 2016 Yusuke Uchida, Shigeyuki Sakazawa, Shin'ichi Satoh

Recently, the Fisher vector representation of local features has attracted much attention because of its effectiveness in both image classification and image retrieval.

Classification General Classification +2

Faster R-CNN Features for Instance Search

3 code implementations29 Apr 2016 Amaia Salvador, Xavier Giro-i-Nieto, Ferran Marques, Shin'ichi Satoh

This work explores the suitability for instance retrieval of image- and region-wise representations pooled from an object detection CNN such as Faster R-CNN.

Instance Search object-detection +2

Generalized Lasso based Approximation of Sparse Coding for Visual Recognition

no code implementations NeurIPS 2011 Nobuyuki Morioka, Shin'ichi Satoh

Sparse coding, a method of explaining sensory data with as few dictionary bases as possible, has attracted much attention in computer vision.

Object Recognition

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