Search Results for author: Osamu Yoshie

Found 16 papers, 7 papers with code

BreakGPT: A Large Language Model with Multi-stage Structure for Financial Breakout Detection

1 code implementation12 Feb 2024 Kang Zhang, Osamu Yoshie, Weiran Huang

To address these issues, we introduce BreakGPT, the first large language model for financial breakout detection.

Language Modelling Large Language Model

PillarNeSt: Embracing Backbone Scaling and Pretraining for Pillar-based 3D Object Detection

no code implementations29 Nov 2023 Weixin Mao, Tiancai Wang, Diankun Zhang, Junjie Yan, Osamu Yoshie

Pillar-based methods mainly employ randomly initialized 2D convolution neural network (ConvNet) for feature extraction and fail to enjoy the benefits from the backbone scaling and pretraining in the image domain.

3D Object Detection object-detection

GMM: Delving into Gradient Aware and Model Perceive Depth Mining for Monocular 3D Detection

no code implementations30 Jun 2023 Weixin Mao, Jinrong Yang, Zheng Ge, Lin Song, HongYu Zhou, Tiezheng Mao, Zeming Li, Osamu Yoshie

In light of the success of sample mining techniques in 2D object detection, we propose a simple yet effective mining strategy for improving depth perception in 3D object detection.

3D Object Detection Depth Estimation +3

Vision Learners Meet Web Image-Text Pairs

no code implementations17 Jan 2023 Bingchen Zhao, Quan Cui, Hao Wu, Osamu Yoshie, Cheng Yang, Oisin Mac Aodha

In this work, given the excellent scalability of web data, we consider self-supervised pre-training on noisy web sourced image-text paired data.

Benchmarking Self-Supervised Learning +1

Discriminability-Transferability Trade-Off: An Information-Theoretic Perspective

1 code implementation8 Mar 2022 Quan Cui, Bingchen Zhao, Zhao-Min Chen, Borui Zhao, RenJie Song, Jiajun Liang, Boyan Zhou, Osamu Yoshie

This work simultaneously considers the discriminability and transferability properties of deep representations in the typical supervised learning task, i. e., image classification.

Image Classification Transfer Learning

Contrastive Vision-Language Pre-training with Limited Resources

1 code implementation17 Dec 2021 Quan Cui, Boyan Zhou, Yu Guo, Weidong Yin, Hao Wu, Osamu Yoshie, Yubo Chen

However, these works require a tremendous amount of data and computational resources (e. g., billion-level web data and hundreds of GPUs), which prevent researchers with limited resources from reproduction and further exploration.

Contrastive Learning

PP-YOLOv2: A Practical Object Detector

1 code implementation21 Apr 2021 Xin Huang, Xinxin Wang, Wenyu Lv, Xiaying Bai, Xiang Long, Kaipeng Deng, Qingqing Dang, Shumin Han, Qiwen Liu, Xiaoguang Hu, dianhai yu, Yanjun Ma, Osamu Yoshie

To meet these two concerns, we comprehensively evaluate a collection of existing refinements to improve the performance of PP-YOLO while almost keep the infer time unchanged.

Object Real-Time Object Detection

OTA: Optimal Transport Assignment for Object Detection

2 code implementations CVPR 2021 Zheng Ge, Songtao Liu, Zeming Li, Osamu Yoshie, Jian Sun

Recent advances in label assignment in object detection mainly seek to independently define positive/negative training samples for each ground-truth (gt) object.

Object object-detection +1

A Reinforcement learning method for Optical Thin-Film Design

no code implementations13 Feb 2021 Anqing Jiang, LiangYao Chen, Osamu Yoshie

Machine learning, especially deep learning, is dramatically changing the methods associated with optical thin-film inverse design.

reinforcement-learning Reinforcement Learning (RL)

LLA: Loss-aware Label Assignment for Dense Pedestrian Detection

1 code implementation12 Jan 2021 Zheng Ge, JianFeng Wang, Xin Huang, Songtao Liu, Osamu Yoshie

A joint loss is then defined as the weighted summation of cls and reg losses as the assigning indicator.

object-detection Object Detection +1

ExchNet: A Unified Hashing Network for Large-Scale Fine-Grained Image Retrieval

no code implementations ECCV 2020 Quan Cui, Qing-Yuan Jiang, Xiu-Shen Wei, Wu-Jun Li, Osamu Yoshie

Retrieving content relevant images from a large-scale fine-grained dataset could suffer from intolerably slow query speed and highly redundant storage cost, due to high-dimensional real-valued embeddings which aim to distinguish subtle visual differences of fine-grained objects.

Image Retrieval Retrieval

Delving into the Imbalance of Positive Proposals in Two-stage Object Detection

no code implementations23 May 2020 Zheng Ge, Zequn Jie, Xin Huang, Chengzheng Li, Osamu Yoshie

The first imbalance lies in the large number of low-quality RPN proposals, which makes the R-CNN module (i. e., post-classification layers) become highly biased towards the negative proposals in the early training stage.

object-detection Object Detection

NMS by Representative Region: Towards Crowded Pedestrian Detection by Proposal Pairing

no code implementations CVPR 2020 Xin Huang, Zheng Ge, Zequn Jie, Osamu Yoshie

To acquire the visible parts, a novel Paired-Box Model (PBM) is proposed to simultaneously predict the full and visible boxes of a pedestrian.

Pedestrian Detection

PS-RCNN: Detecting Secondary Human Instances in a Crowd via Primary Object Suppression

no code implementations16 Mar 2020 Zheng Ge, Zequn Jie, Xin Huang, Rong Xu, Osamu Yoshie

PS-RCNN first detects slightly/none occluded objects by an R-CNN module (referred as P-RCNN), and then suppress the detected instances by human-shaped masks so that the features of heavily occluded instances can stand out.

Human Detection Object Detection

A new multilayer optical film optimal method based on deep q-learning

no code implementations7 Dec 2018 Anqing Jiang, Osamu Yoshie, LiangYao Chen

This model can converge the global optimum of the optical thin film structure, this will greatly improve the design efficiency of multi-layer films.

Q-Learning

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