☆ 4.8 Article

Detection-Friendly Dehazing: Object Detection in Real-World Hazy Scenes

IEEE TRANSACTIONS ON PATTERN ANALYSIS AND MACHINE INTELLIGENCE (2023)

Related references

Note: Only part of the references are listed.

Article Computer Science, Information Systems

DCA-CycleGAN: Unsupervised single image dehazing using Dark Channel Attention optimized CycleGAN

Yaozong Mo et al.

Summary: This paper proposes a novel unsupervised Dark Channel Attention optimized CycleGAN (DCA-CycleGAN) method to deal with challenging scenes with uneven and dense haze concentration. The method adopts the dark channel as input and generates attention through a DCA subnetwork to handle nonhomogeneous haze. In addition, the method leverages two local discriminators and a new local adversarial loss calculated strategy to enhance dehazing performance on local dense haze.

JOURNAL OF VISUAL COMMUNICATION AND IMAGE REPRESENTATION (2022)

Add to Collection

Review Computer Science, Software Engineering

Attention mechanisms in computer vision: A survey

Meng-Hao Guo et al.

Summary: Attention mechanisms, inspired by the human visual system, have been successfully applied in various computer vision tasks. This survey provides a comprehensive review of different types of attention mechanisms and suggests future research directions.

COMPUTATIONAL VISUAL MEDIA (2022)

Add to Collection

Proceedings Paper Computer Science, Artificial Intelligence

Exploring Resolution and Degradation Clues as Self-supervised Signal for Low Quality Object Detection

Ziteng Cui et al.

Summary: This paper proposes a novel self-supervised framework for object detection in low resolution degraded images. The framework combines representation learning and object detection, and utilizes downsampling degradation as a transformation for self-supervised signals. Experimental results show that the method achieves superior performance in different degradation situations.

COMPUTER VISION, ECCV 2022, PT IX (2022)

Add to Collection

Proceedings Paper Computer Science, Theory & Methods

ResNeSt: Split-Attention Networks

Hang Zhang et al.

Summary: The research presents a multi-branch architecture to improve representation learning in convolutional neural networks, leading to enhanced performance of deep learning models. Their approach leverages channel-wise attention to combine the strengths of feature-map attention and multi-path representation, resulting in more diverse representations.

2022 IEEE/CVF CONFERENCE ON COMPUTER VISION AND PATTERN RECOGNITION WORKSHOPS, CVPRW 2022 (2022)

Add to Collection

Article Computer Science, Artificial Intelligence

Attack to Fool and Explain Deep Networks

Naveed Akhtar et al.

Summary: This article explores the susceptibility of deep visual models to adversarial perturbations and the human understanding of patterns within these perturbations. The authors propose an attack method that confuses the network and reveals insightful information about the decision boundaries. They also use the perturbations to perform image generation and interactive image manipulation.

IEEE TRANSACTIONS ON PATTERN ANALYSIS AND MACHINE INTELLIGENCE (2022)

Add to Collection

Article Computer Science, Software Engineering

Dirty Pixels: Towards End-to-end Image Processing and Perception

Steven Diamond et al.

Summary: The traditional imaging process involves a series of steps, while advanced processing includes feature extraction, classification, tracking, and fusion. We propose an end-to-end differentiable architecture that performs demosaicking, denoising, deblurring, tone-mapping, and classification, improving perception in low light and challenging conditions.

ACM TRANSACTIONS ON GRAPHICS (2021)

Add to Collection

Article Computer Science, Artificial Intelligence

Gaussian Graphical Model Exploration and Selection in High Dimension Low Sample Size Setting

Thomas Lartigue et al.

Summary: In this paper, two families of Gaussian graphical model (GGM) inference methods, nodewise approach and penalised likelihood maximisation, are compared. The study demonstrates that when the sample size is small, both methods may result in graphs with either too few or too many edges compared to the real one. A composite procedure is proposed to address this issue, which explores a family of graphs with a nodewise numerical scheme and selects a candidate based on an overall likelihood criterion. This selection method yields graphs closer to the truth and corresponding to distributions with better KL divergence compared to the other two methods, particularly when the number of observations is small.

IEEE TRANSACTIONS ON PATTERN ANALYSIS AND MACHINE INTELLIGENCE (2021)

Add to Collection

Proceedings Paper Computer Science, Artificial Intelligence

Attentional Feature Fusion

Yimian Dai et al.

Summary: The study introduces an attentional feature fusion scheme for better integrating features from different layers or branches. Utilizing a multi-scale channel attention module and iterative attentional feature fusion helps address challenges in feature fusion.

2021 IEEE WINTER CONFERENCE ON APPLICATIONS OF COMPUTER VISION WACV 2021 (2021)

Add to Collection

Article Computer Science, Artificial Intelligence

Real-World Image Denoising with Deep Boosting

Chang Chen et al.

IEEE TRANSACTIONS ON PATTERN ANALYSIS AND MACHINE INTELLIGENCE (2020)

Add to Collection

Proceedings Paper Computer Science, Artificial Intelligence

Multi-Scale Boosted Dehazing Network with Dense Feature Fusion

Hang Dong et al.

2020 IEEE/CVF CONFERENCE ON COMPUTER VISION AND PATTERN RECOGNITION (CVPR) (2020)

Add to Collection

Article Computer Science, Artificial Intelligence

Connecting Image Denoising and High-Level Vision Tasks via Deep Learning

Ding Liu et al.

IEEE TRANSACTIONS ON IMAGE PROCESSING (2020)

Add to Collection

Article Computer Science, Artificial Intelligence

Benchmarking Single-Image Dehazing and Beyond

Boyi Li et al.

IEEE TRANSACTIONS ON IMAGE PROCESSING (2019)

Add to Collection

Proceedings Paper Computer Science, Artificial Intelligence

GridDehazeNet: Attention-Based Multi-Scale Network for Image Dehazing

Xiaohong Liu et al.

2019 IEEE/CVF INTERNATIONAL CONFERENCE ON COMPUTER VISION (ICCV 2019) (2019)

Add to Collection

Proceedings Paper Computer Science, Artificial Intelligence

Dual Directed Capsule Network for Very Low Resolution Image Recognition

Maneet Singh et al.

2019 IEEE/CVF INTERNATIONAL CONFERENCE ON COMPUTER VISION (ICCV 2019) (2019)

Add to Collection

Proceedings Paper Computer Science, Artificial Intelligence

Double-DIP : Unsupervised Image Decomposition via Coupled Deep-Image-Priors

Yossi Gandelsman et al.

2019 IEEE/CVF CONFERENCE ON COMPUTER VISION AND PATTERN RECOGNITION (CVPR 2019) (2019)

Add to Collection

Proceedings Paper Computer Science, Artificial Intelligence

Single Image Deraining: A Comprehensive Benchmark Analysis

Siyuan Li et al.

2019 IEEE/CVF CONFERENCE ON COMPUTER VISION AND PATTERN RECOGNITION (CVPR 2019) (2019)

Add to Collection

Proceedings Paper Computer Science, Artificial Intelligence

Gated Fusion Network for Single Image Dehazing

Wenqi Ren et al.

2018 IEEE/CVF CONFERENCE ON COMPUTER VISION AND PATTERN RECOGNITION (CVPR) (2018)

Add to Collection

Proceedings Paper Computer Science, Artificial Intelligence

Cycle-Dehaze: Enhanced CycleGAN for Single Image Dehazing

Deniz Engin et al.

PROCEEDINGS 2018 IEEE/CVF CONFERENCE ON COMPUTER VISION AND PATTERN RECOGNITION WORKSHOPS (CVPRW) (2018)

Add to Collection

Article Engineering, Electrical & Electronic

Single image dehazing using kernel regression model and dark channel prior

Cong-Hua Xie et al.

SIGNAL IMAGE AND VIDEO PROCESSING (2017)

Add to Collection

Article Engineering, Electrical & Electronic

Two-Layer Gaussian Process Regression With Example Selection for Image Dehazing

Xin Fan et al.

IEEE TRANSACTIONS ON CIRCUITS AND SYSTEMS FOR VIDEO TECHNOLOGY (2017)

Add to Collection

Proceedings Paper Computer Science, Artificial Intelligence

AOD-Net: All-in-One Dehazing Network

Boyi Li et al.

2017 IEEE INTERNATIONAL CONFERENCE ON COMPUTER VISION (ICCV) (2017)

Add to Collection

Article Computer Science, Artificial Intelligence

DehazeNet: An End-to-End System for Single Image Haze Removal

Bolun Cai et al.

IEEE TRANSACTIONS ON IMAGE PROCESSING (2016)

Add to Collection

Proceedings Paper Computer Science, Artificial Intelligence

Single Image Dehazing via Multi-scale Convolutional Neural Networks

Wenqi Ren et al.

COMPUTER VISION - ECCV 2016, PT II (2016)

Add to Collection

Article Computer Science, Artificial Intelligence

Spatial Pyramid Pooling in Deep Convolutional Networks for Visual Recognition

Kaiming He et al.

IEEE TRANSACTIONS ON PATTERN ANALYSIS AND MACHINE INTELLIGENCE (2015)

Add to Collection

Proceedings Paper Computer Science, Artificial Intelligence

Fast R-CNN

Ross Girshick

2015 IEEE INTERNATIONAL CONFERENCE ON COMPUTER VISION (ICCV) (2015)

Add to Collection

© Peeref 2019-2024. All rights reserved.