Object Detection in Foggy Scenes by Embedding Depth and Reconstruction into Domain Adaptation

• URL: http://arxiv.org/abs/2211.13409v1
• Date: Thu, 24 Nov 2022 04:27:40 GMT
• Title: Object Detection in Foggy Scenes by Embedding Depth and Reconstruction into Domain Adaptation
• Authors: Xin Yang, Michael Bi Mi, Yuan Yuan, Xin Wang, Robby T. Tan
• Abstract summary: Most existing domain adaptation (DA) methods align the features based on the domain feature distributions. In our DA framework, we retain the depth and background information during the domain feature alignment. We propose an encoder-decoder framework to reconstruct the fog-free background image. Our method significantly outperforms the state-of-the-art method (47.6 mAP against the 44.3 mAP on the Foggy Cityscapes dataset)
• Score: 35.751428021375055
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: Most existing domain adaptation (DA) methods align the features based on the domain feature distributions and ignore aspects related to fog, background and target objects, rendering suboptimal performance. In our DA framework, we retain the depth and background information during the domain feature alignment. A consistency loss between the generated depth and fog transmission map is introduced to strengthen the retention of the depth information in the aligned features. To address false object features potentially generated during the DA process, we propose an encoder-decoder framework to reconstruct the fog-free background image. This reconstruction loss also reinforces the encoder, i.e., our DA backbone, to minimize false object features.Moreover, we involve our target data in training both our DA module and our detection module in a semi-supervised manner, so that our detection module is also exposed to the unlabeled target data, the type of data used in the testing stage. Using these ideas, our method significantly outperforms the state-of-the-art method (47.6 mAP against the 44.3 mAP on the Foggy Cityscapes dataset), and obtains the best performance on multiple real-image public datasets. Code is available at: https://github.com/VIML-CVDL/Object-Detection-in-Foggy-Scenes

Related papers

• MICDrop: Masking Image and Depth Features via Complementary Dropout for Domain-Adaptive Semantic Segmentation [155.0797148367653]
  Unsupervised Domain Adaptation (UDA) is the task of bridging the domain gap between a labeled source domain and an unlabeled target domain. We propose to leverage geometric information, i.e., depth predictions, as depth discontinuities often coincide with segmentation boundaries. We show that our method can be plugged into various recent UDA methods and consistently improve results across standard UDA benchmarks.
  arXiv  Detail & Related papers  (2024-08-29T12:15:10Z)
• PGNeXt: High-Resolution Salient Object Detection via Pyramid Grafting Network [24.54269823691119]
  We present an advanced study on more challenging high-resolution salient object detection (HRSOD) from both dataset and network framework perspectives. To compensate for the lack of HRSOD dataset, we thoughtfully collect a large-scale high resolution salient object detection dataset, called UHRSD. All the images are finely annotated in pixel-level, far exceeding previous low-resolution SOD datasets.
  arXiv  Detail & Related papers  (2024-08-02T09:31:21Z)
• Test-Time Adaptation for Depth Completion [9.304152205375757]
  It is common to observe performance degradation when transferring models trained on some (source) datasets to target testing data due to a domain gap between them. We propose an online test-time adaptation method for depth completion, the task of inferring a dense depth map from a single image and associated sparse depth map, that closes the performance gap in a single pass.
  arXiv  Detail & Related papers  (2024-02-05T18:59:52Z)
• Long Range Object-Level Monocular Depth Estimation for UAVs [0.0]
  We propose several novel extensions to state-of-the-art methods for monocular object detection from images at long range. Firstly, we propose Sigmoid and ReLU-like encodings when modeling depth estimation as a regression task. Secondly, we frame the depth estimation as a classification problem and introduce a Soft-Argmax function in the calculation of the training loss.
  arXiv  Detail & Related papers  (2023-02-17T15:26:04Z)
• Learning Object-level Point Augmentor for Semi-supervised 3D Object Detection [85.170578641966]
  We propose an object-level point augmentor (OPA) that performs local transformations for semi-supervised 3D object detection. In this way, the resultant augmentor is derived to emphasize object instances rather than irrelevant backgrounds. Experiments on the ScanNet and SUN RGB-D datasets show that the proposed OPA performs favorably against the state-of-the-art methods.
  arXiv  Detail & Related papers  (2022-12-19T06:56:14Z)
• AGO-Net: Association-Guided 3D Point Cloud Object Detection Network [86.10213302724085]
  We propose a novel 3D detection framework that associates intact features for objects via domain adaptation. We achieve new state-of-the-art performance on the KITTI 3D detection benchmark in both accuracy and speed.
  arXiv  Detail & Related papers  (2022-08-24T16:54:38Z)
• Instance Relation Graph Guided Source-Free Domain Adaptive Object Detection [79.89082006155135]
  Unsupervised Domain Adaptation (UDA) is an effective approach to tackle the issue of domain shift. UDA methods try to align the source and target representations to improve the generalization on the target domain. The Source-Free Adaptation Domain (SFDA) setting aims to alleviate these concerns by adapting a source-trained model for the target domain without requiring access to the source data.
  arXiv  Detail & Related papers  (2022-03-29T17:50:43Z)
• Fog Simulation on Real LiDAR Point Clouds for 3D Object Detection in Adverse Weather [92.84066576636914]
  This work addresses the challenging task of LiDAR-based 3D object detection in foggy weather. We tackle this problem by simulating physically accurate fog into clear-weather scenes. We are the first to provide strong 3D object detection baselines on the Seeing Through Fog dataset.
  arXiv  Detail & Related papers  (2021-08-11T14:37:54Z)
• Progressive Multi-scale Fusion Network for RGB-D Salient Object Detection [9.099589602551575]
  We discuss about the advantages of the so-called progressive multi-scale fusion method and propose a mask-guided feature aggregation module. The proposed framework can effectively combine the two features of different modalities and alleviate the impact of erroneous depth features. We further introduce a mask-guided refinement module(MGRM) to complement the high-level semantic features and reduce the irrelevant features from multi-scale fusion.
  arXiv  Detail & Related papers  (2021-06-07T20:02:39Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.