Search Results for author: Pingyu Wu

Found 6 papers, 5 papers with code

BACON: Supercharge Your VLM with Bag-of-Concept Graph to Mitigate Hallucinations

no code implementations3 Jul 2024 Zhantao Yang, Ruili Feng, Keyu Yan, Huangji Wang, Zhicai Wang, Shangwen Zhu, Han Zhang, Jie Xiao, Pingyu Wu, Kai Zhu, Jixuan Chen, Chen-Wei Xie, Chaojie Mao, Yue Yang, Hongyang Zhang, Yu Liu, Fan Cheng

This paper presents Bag-of-Concept Graph (BACON) to gift models with limited linguistic abilities to taste the privilege of Vision Language Models (VLMs) and boost downstream tasks such as detection, visual question answering (VQA), and image generation.

Image Generation Question Answering +1

Background Activation Suppression for Weakly Supervised Object Localization and Semantic Segmentation

2 code implementations22 Sep 2023 Wei Zhai, Pingyu Wu, Kai Zhu, Yang Cao, Feng Wu, Zheng-Jun Zha

In addition, our method also achieves state-of-the-art weakly supervised semantic segmentation performance on the PASCAL VOC 2012 and MS COCO 2014 datasets.

Object Weakly-Supervised Object Localization +2

ChatHaruhi: Reviving Anime Character in Reality via Large Language Model

1 code implementation18 Aug 2023 Cheng Li, Ziang Leng, Chenxi Yan, Junyi Shen, Hao Wang, Weishi MI, Yaying Fei, Xiaoyang Feng, Song Yan, HaoSheng Wang, Linkang Zhan, Yaokai Jia, Pingyu Wu, Haozhen Sun

Role-playing chatbots built on large language models have drawn interest, but better techniques are needed to enable mimicking specific fictional characters.

Language Modelling Large Language Model +2

Spatial-Aware Token for Weakly Supervised Object Localization

1 code implementation ICCV 2023 Pingyu Wu, Wei Zhai, Yang Cao, Jiebo Luo, Zheng-Jun Zha

Specifically, a spatial token is first introduced in the input space to aggregate representations for localization task.

Object Weakly-Supervised Object Localization

Background Activation Suppression for Weakly Supervised Object Localization

2 code implementations CVPR 2022 Pingyu Wu, Wei Zhai, Yang Cao

Existing FPM-based methods use cross-entropy (CE) to evaluate the foreground prediction map and to guide the learning of generator.

Object Weakly-Supervised Object Localization

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