Solution for CVPR 2024 UG2+ Challenge Track on All Weather Semantic Segmentation

• URL: http://arxiv.org/abs/2406.05837v1
• Date: Sun, 9 Jun 2024 15:56:35 GMT
• Title: Solution for CVPR 2024 UG2+ Challenge Track on All Weather Semantic Segmentation
• Authors: Jun Yu, Yunxiang Zhang, Fengzhao Sun, Leilei Wang, Renjie Lu,
• Abstract summary: We present our solution for the semantic segmentation in adverse weather, in UG2+ Challenge at CVPR 2024. We initialize the InternImage-H backbone with pre-trained weights from the large-scale joint dataset and enhance it with the state-of-the-art Upernet segmentation method. Our proposed solution demonstrates advanced performance on the test set and achieves 3rd position in this challenge.
• Score: 9.322345758563886
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: In this report, we present our solution for the semantic segmentation in adverse weather, in UG2+ Challenge at CVPR 2024. To achieve robust and accurate segmentation results across various weather conditions, we initialize the InternImage-H backbone with pre-trained weights from the large-scale joint dataset and enhance it with the state-of-the-art Upernet segmentation method. Specifically, we utilize offline and online data augmentation approaches to extend the train set, which helps us to further improve the performance of the segmenter. As a result, our proposed solution demonstrates advanced performance on the test set and achieves 3rd position in this challenge.

Related papers

• Point Transformer V3 Extreme: 1st Place Solution for 2024 Waymo Open Dataset Challenge in Semantic Segmentation [98.11452697097539]
  In this technical report, we detail our first-place solution for the 2024 Open dataset Challenge's semantic segmentation track. We significantly enhanced the performance of Point Transformer V3 on the benchmark by implementing cutting-edge, plug-and-play training and inference technologies. This approach secured us the top position on the Open dataset segmentation leaderboard, markedly outperforming other entries.
  arXiv  Detail & Related papers  (2024-07-21T22:08:52Z)
• A Two-Stage Adverse Weather Semantic Segmentation Method for WeatherProof Challenge CVPR 2024 Workshop UG2+ [10.069192320623031]
  We propose a two-stage deep learning framework for the WeatherProof dataset challenge. In the challenge, our solution achieved a competitive score of 0.43 on the Mean Intersection over Union (mIoU) metric, securing a respectable rank of 4th.
  arXiv  Detail & Related papers  (2024-06-08T16:22:26Z)
• Enhanced Semantic Segmentation Pipeline for WeatherProof Dataset Challenge [2.722639169181398]
  This report describes the winning solution to the WeatherProof dataset challenge. We propose an enhanced semantic segmentation pipeline for this challenge. We introduce a new dataset WeatherProofExtra with wider viewing angle and employ data augmentation methods. Our solution is ranked 1st on the final leaderboard.
  arXiv  Detail & Related papers  (2024-06-06T07:12:50Z)
• Data Augmentation for Traffic Classification [54.92823760790628]
  Data Augmentation (DA) is a technique widely adopted in Computer Vision (CV) and Natural Language Processing (NLP) tasks. DA has struggled to gain traction in networking contexts, particularly in Traffic Classification (TC) tasks.
  arXiv  Detail & Related papers  (2024-01-19T15:25:09Z)
• Semantic Segmentation on VSPW Dataset through Contrastive Loss and Multi-dataset Training Approach [7.112725255953468]
  This paper presents the winning solution of the CVPR2023 workshop for video semantic segmentation. Our approach achieves 65.95% mIoU performance on the VSPW dataset, ranked 1st place on the challenge at CVPR 2023.
  arXiv  Detail & Related papers  (2023-06-06T08:53:53Z)
• 3rd Place Solution for PVUW2023 VSS Track: A Large Model for Semantic Segmentation on VSPW [68.56017675820897]
  In this paper, we introduce 3rd place solution for PVUW2023 VSS track. We have explored various image-level visual backbones and segmentation heads to tackle the problem of video semantic segmentation.
  arXiv  Detail & Related papers  (2023-06-04T07:50:38Z)
• The Second Place Solution for ICCV2021 VIPriors Instance Segmentation Challenge [6.087398773657721]
  The Visual Inductive Priors(VIPriors) for Data-Efficient Computer Vision challenges ask competitors to train models from scratch in a data-deficient setting. We introduce the technical details of our submission to the ICCV 2021 VIPriors instance segmentation challenge. Our approach can achieve 40.2%AP@0.50:0.95 on the test set of ICCV 2021 VIPriors instance segmentation challenge.
  arXiv  Detail & Related papers  (2021-12-02T09:23:02Z)
• InverseForm: A Loss Function for Structured Boundary-Aware Segmentation [80.39674800972182]
  We present a novel boundary-aware loss term for semantic segmentation using an inverse-transformation network. This plug-in loss term complements the cross-entropy loss in capturing boundary transformations. We analyze the quantitative and qualitative effects of our loss function on three indoor and outdoor segmentation benchmarks.
  arXiv  Detail & Related papers  (2021-04-06T18:52:45Z)
• Adversarial Feature Augmentation and Normalization for Visual Recognition [109.6834687220478]
  Recent advances in computer vision take advantage of adversarial data augmentation to ameliorate the generalization ability of classification models. Here, we present an effective and efficient alternative that advocates adversarial augmentation on intermediate feature embeddings. We validate the proposed approach across diverse visual recognition tasks with representative backbone networks.
  arXiv  Detail & Related papers  (2021-03-22T20:36:34Z)
• 1st Place Solutions for OpenImage2019 -- Object Detection and Instance Segmentation [116.25081559037872]
  This article introduces the solutions of the two champion teams, MMfruit' for the detection track and MMfruitSeg' for the segmentation track, in OpenImage Challenge 2019. It is commonly known that for an object detector, the shared feature at the end of the backbone is not appropriate for both classification and regression. We propose the Decoupling Head (DH) to disentangle the object classification and regression via the self-learned optimal feature extraction.
  arXiv  Detail & Related papers  (2020-03-17T06:45:07Z)

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.