Search Results for author: Peng-Tao Jiang

Found 19 papers, 8 papers with code

LayerCAM: Exploring Hierarchical Class Activation Maps for Localization

3 code implementations IEEE 2021 Peng-Tao Jiang, Chang-Bin Zhang, Qibin Hou, Ming-Ming Cheng, Yunchao Wei

To evaluate the quality of the class activation maps produced by LayerCAM, we apply them to weakly-supervised object localization and semantic segmentation.

Object Semantic Segmentation +1

Delving Deep into Label Smoothing

2 code implementations25 Nov 2020 Chang-Bin Zhang, Peng-Tao Jiang, Qibin Hou, Yunchao Wei, Qi Han, Zhen Li, Ming-Ming Cheng

Experiments demonstrate that based on the same classification models, the proposed approach can effectively improve the classification performance on CIFAR-100, ImageNet, and fine-grained datasets.

Classification General Classification

Integral Object Mining via Online Attention Accumulation

2 code implementations ICCV 2019 Peng-Tao Jiang, Qibin Hou, Yang Cao, Ming-Ming Cheng, Yunchao Wei, Hong-Kai Xiong

In order to accumulate the discovered different object parts, we propose an online attention accumulation (OAA) strategy which maintains a cumulative attention map for each target category in each training image so that the integral object regions can be gradually promoted as the training goes.

General Classification Object +4

L2G: A Simple Local-to-Global Knowledge Transfer Framework for Weakly Supervised Semantic Segmentation

1 code implementation CVPR 2022 Peng-Tao Jiang, YuQi Yang, Qibin Hou, Yunchao Wei

Our framework conducts the global network to learn the captured rich object detail knowledge from a global view and thereby produces high-quality attention maps that can be directly used as pseudo annotations for semantic segmentation networks.

Object Transfer Learning +2

Revisiting Single Image Reflection Removal In the Wild

1 code implementation29 Nov 2023 Yurui Zhu, Xueyang Fu, Peng-Tao Jiang, Hao Zhang, Qibin Sun, Jinwei Chen, Zheng-Jun Zha, Bo Li

This research focuses on the issue of single-image reflection removal (SIRR) in real-world conditions, examining it from two angles: the collection pipeline of real reflection pairs and the perception of real reflection locations.

Reflection Removal

Self-Erasing Network for Integral Object Attention

no code implementations NeurIPS 2018 Qibin Hou, Peng-Tao Jiang, Yunchao Wei, Ming-Ming Cheng

To test the quality of the generated attention maps, we employ the mined object regions as heuristic cues for learning semantic segmentation models.

Object Semantic Segmentation

Deeply Explain CNN via Hierarchical Decomposition

no code implementations23 Jan 2022 Ming-Ming Cheng, Peng-Tao Jiang, Ling-Hao Han, Liang Wang, Philip Torr

The proposed framework can generate a deep hierarchy of strongly associated supporting evidence for the network decision, which provides insight into the decision-making process.

Decision Making

Traffic Scene Parsing through the TSP6K Dataset

no code implementations6 Mar 2023 Peng-Tao Jiang, YuQi Yang, Yang Cao, Qibin Hou, Ming-Ming Cheng, Chunhua Shen

Traffic scene parsing is one of the most important tasks to achieve intelligent cities.

Scene Parsing

Towards Training-free Open-world Segmentation via Image Prompt Foundation Models

no code implementations17 Oct 2023 Lv Tang, Peng-Tao Jiang, Hao-Ke Xiao, Bo Li

The realm of computer vision has witnessed a paradigm shift with the advent of foundational models, mirroring the transformative influence of large language models in the domain of natural language processing.

Segmentation

Decoupling Degradation and Content Processing for Adverse Weather Image Restoration

no code implementations8 Dec 2023 Xi Wang, Xueyang Fu, Peng-Tao Jiang, Jie Huang, Mi Zhou, Bo Li, Zheng-Jun Zha

The former facilitates channel-dependent degradation removal operation, allowing the network to tailor responses to various adverse weather types; the latter, by integrating Fourier's global properties into channel-independent content features, enhances network capacity for consistent global content reconstruction.

Image Restoration

Improving Adversarial Energy-Based Model via Diffusion Process

no code implementations4 Mar 2024 Cong Geng, Tian Han, Peng-Tao Jiang, Hao Zhang, Jinwei Chen, Søren Hauberg, Bo Li

Generative models have shown strong generation ability while efficient likelihood estimation is less explored.

Denoising Density Estimation

Empowering Segmentation Ability to Multi-modal Large Language Models

no code implementations21 Mar 2024 YuQi Yang, Peng-Tao Jiang, Jing Wang, Hao Zhang, Kai Zhao, Jinwei Chen, Bo Li

Multi-modal large language models (MLLMs) can understand image-language prompts and demonstrate impressive reasoning ability.

Dialogue Generation Segmentation +1

Multi-Task Dense Prediction via Mixture of Low-Rank Experts

no code implementations26 Mar 2024 YuQi Yang, Peng-Tao Jiang, Qibin Hou, Hao Zhang, Jinwei Chen, Bo Li

Furthermore, to control the parameters and computational cost brought by the increase in the number of experts, we take inspiration from LoRA and propose to leverage the low-rank format of a vanilla convolution in the expert network.

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