FedDrive v2: an Analysis of the Impact of Label Skewness in Federated Semantic Segmentation for Autonomous Driving

• URL: http://arxiv.org/abs/2309.13336v2
• Date: Thu, 12 Oct 2023 10:24:42 GMT
• Title: FedDrive v2: an Analysis of the Impact of Label Skewness in Federated Semantic Segmentation for Autonomous Driving
• Authors: Eros Fan\`i, Marco Ciccone and Barbara Caputo
• Abstract summary: We propose FedDrive v2, an extension of the Federated Learning benchmark for Semantic in Autonomous Driving. While the first version aims at studying the effect of domain shift of the visual features across clients, in this work, we focus on the distribution skewness of the labels. We propose six new scenarios to investigate how label skewness affects the performance of segmentation models and compare it with the effect of domain shift.
• Score: 26.99151955856939
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: We propose FedDrive v2, an extension of the Federated Learning benchmark for Semantic Segmentation in Autonomous Driving. While the first version aims at studying the effect of domain shift of the visual features across clients, in this work, we focus on the distribution skewness of the labels. We propose six new federated scenarios to investigate how label skewness affects the performance of segmentation models and compare it with the effect of domain shift. Finally, we study the impact of using the domain information during testing. Official website: https://feddrive.github.io

Related papers

• DiffVein: A Unified Diffusion Network for Finger Vein Segmentation and Authentication [50.017055360261665]
  We introduce DiffVein, a unified diffusion model-based framework which simultaneously addresses vein segmentation and authentication tasks. For better feature interaction between these two branches, we introduce two specialized modules. In this way, our framework allows for a dynamic interplay between diffusion and segmentation embeddings.
  arXiv  Detail & Related papers  (2024-02-03T06:49:42Z)
• Fake it, Mix it, Segment it: Bridging the Domain Gap Between Lidar Sensors [0.966840768820136]
  Best performing neural networks for lidar segmentation are fine-tuned to specific datasets. switching the lidar sensor without retraining on a big set of annotated data from the new sensor creates a domain shift. We propose a new method for lidar domain adaption, in which we use annotated panoptic lidar datasets and recreate the recorded scenes in the structure of a different lidar sensor.
  arXiv  Detail & Related papers  (2022-12-19T14:57:13Z)
• Influence Functions for Sequence Tagging Models [49.81774968547377]
  We extend influence functions to trace predictions back to the training points that informed them. We show the practical utility of segment influence by using the method to identify systematic annotation errors.
  arXiv  Detail & Related papers  (2022-10-25T17:13:11Z)
• DecoupleNet: Decoupled Network for Domain Adaptive Semantic Segmentation [78.30720731968135]
  Unsupervised domain adaptation in semantic segmentation has been raised to alleviate the reliance on expensive pixel-wise annotations. We propose DecoupleNet that alleviates source domain overfitting and enables the final model to focus more on the segmentation task. We also put forward Self-Discrimination (SD) and introduce an auxiliary classifier to learn more discriminative target domain features with pseudo labels.
  arXiv  Detail & Related papers  (2022-07-20T15:47:34Z)
• FedDrive: Generalizing Federated Learning to Semantic Segmentation in Autonomous Driving [27.781734303644516]
  Federated learning aims to learn a global model while preserving privacy and leveraging data on millions of remote devices. We propose FedDrive, a new benchmark consisting of three settings and two datasets. We benchmark state-of-the-art algorithms from the federated learning literature through an in-depth analysis.
  arXiv  Detail & Related papers  (2022-02-28T10:34:31Z)
• Wiki to Automotive: Understanding the Distribution Shift and its impact on Named Entity Recognition [0.0]
  Transfer learning is often unable to replicate the performance of pre-trained models on text of niche domains like Automotive. We focus on performing the Named Entity Recognition (NER) task as it requires strong lexical, syntactic and semantic understanding by the model. Fine-tuning the language models with automotive domain text did not make significant improvements to the NER performance.
  arXiv  Detail & Related papers  (2021-12-01T05:13:47Z)
• Cross-domain Contrastive Learning for Unsupervised Domain Adaptation [108.63914324182984]
  Unsupervised domain adaptation (UDA) aims to transfer knowledge learned from a fully-labeled source domain to a different unlabeled target domain. We build upon contrastive self-supervised learning to align features so as to reduce the domain discrepancy between training and testing sets.
  arXiv  Detail & Related papers  (2021-06-10T06:32:30Z)
• Cross-Domain Label-Adaptive Stance Detection [32.800766653254634]
  Stance detection concerns the classification of a writer's viewpoint towards a target. In this paper, we perform an in-depth analysis of 16 stance detection datasets. We propose an end-to-end unsupervised framework for out-of-domain prediction of unseen, user-defined labels.
  arXiv  Detail & Related papers  (2021-04-15T14:04:29Z)
• Robust wav2vec 2.0: Analyzing Domain Shift in Self-Supervised Pre-Training [67.71228426496013]
  We show that using target domain data during pre-training leads to large performance improvements across a variety of setups. We find that pre-training on multiple domains improves performance generalization on domains not seen during training.
  arXiv  Detail & Related papers  (2021-04-02T12:53:15Z)
• LiDAR-based Panoptic Segmentation via Dynamic Shifting Network [56.71765153629892]
  LiDAR-based panoptic segmentation aims to parse both objects and scenes in a unified manner. We propose the Dynamic Shifting Network (DS-Net), which serves as an effective panoptic segmentation framework in the point cloud realm. Our proposed DS-Net achieves superior accuracies over current state-of-the-art methods.
  arXiv  Detail & Related papers  (2020-11-24T08:44:46Z)

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.