Adapt, But Don't Forget: Fine-Tuning and Contrastive Routing for Lane Detection under Distribution Shift

• URL: http://arxiv.org/abs/2507.18653v1
• Date: Tue, 22 Jul 2025 18:39:15 GMT
• Title: Adapt, But Don't Forget: Fine-Tuning and Contrastive Routing for Lane Detection under Distribution Shift
• Authors: Mohammed Abdul Hafeez Khan, Parth Ganeriwala, Sarah M. Lehman, Siddhartha Bhattacharyya, Amy Alvarez, Natasha Neogi,
• Abstract summary: Cross-dataset distribution shifts can cause catastrophic forgetting during fine-tuning.<n>Our framework achieves near-optimal F1-scores while using significantly fewer parameters than training separate models for each distribution.
• Score: 3.394257279821418
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: Lane detection models are often evaluated in a closed-world setting, where training and testing occur on the same dataset. We observe that, even within the same domain, cross-dataset distribution shifts can cause severe catastrophic forgetting during fine-tuning. To address this, we first train a base model on a source distribution and then adapt it to each new target distribution by creating separate branches, fine-tuning only selected components while keeping the original source branch fixed. Based on a component-wise analysis, we identify effective fine-tuning strategies for target distributions that enable parameter-efficient adaptation. At inference time, we propose using a supervised contrastive learning model to identify the input distribution and dynamically route it to the corresponding branch. Our framework achieves near-optimal F1-scores while using significantly fewer parameters than training separate models for each distribution.

Related papers

• Distribution Alignment for Fully Test-Time Adaptation with Dynamic Online Data Streams [19.921480334048756]
  Test-Time Adaptation (TTA) enables adaptation and inference in test data streams with domain shifts from the source. We propose a novel Distribution Alignment loss for TTA. We surpass existing methods in non-i.i.d. scenarios and maintain competitive performance under the ideal i.i.d. assumption.
  arXiv  Detail & Related papers  (2024-07-16T19:33:23Z)
• Distributionally Robust Learning for Multi-source Unsupervised Domain Adaptation [9.359714425373616]
  Empirical risk often performs poorly when the distribution of the target domain differs from those of source domains.<n>We develop an unsupervised domain adaptation approach that leverages labeled data from multiple source domains and unlabeled data from the target domain.
  arXiv  Detail & Related papers  (2023-09-05T13:19:40Z)
• Robust Outlier Rejection for 3D Registration with Variational Bayes [70.98659381852787]
  We develop a novel variational non-local network-based outlier rejection framework for robust alignment. We propose a voting-based inlier searching strategy to cluster the high-quality hypothetical inliers for transformation estimation.
  arXiv  Detail & Related papers  (2023-04-04T03:48:56Z)
• Divide and Contrast: Source-free Domain Adaptation via Adaptive Contrastive Learning [122.62311703151215]
  Divide and Contrast (DaC) aims to connect the good ends of both worlds while bypassing their limitations. DaC divides the target data into source-like and target-specific samples, where either group of samples is treated with tailored goals. We further align the source-like domain with the target-specific samples using a memory bank-based Maximum Mean Discrepancy (MMD) loss to reduce the distribution mismatch.
  arXiv  Detail & Related papers  (2022-11-12T09:21:49Z)
• Distributionally Robust Models with Parametric Likelihood Ratios [123.05074253513935]
  Three simple ideas allow us to train models with DRO using a broader class of parametric likelihood ratios. We find that models trained with the resulting parametric adversaries are consistently more robust to subpopulation shifts when compared to other DRO approaches.
  arXiv  Detail & Related papers  (2022-04-13T12:43:12Z)
• Leveraging Unlabeled Data to Predict Out-of-Distribution Performance [63.740181251997306]
  Real-world machine learning deployments are characterized by mismatches between the source (training) and target (test) distributions. In this work, we investigate methods for predicting the target domain accuracy using only labeled source data and unlabeled target data. We propose Average Thresholded Confidence (ATC), a practical method that learns a threshold on the model's confidence, predicting accuracy as the fraction of unlabeled examples.
  arXiv  Detail & Related papers  (2022-01-11T23:01:12Z)
• KL Guided Domain Adaptation [88.19298405363452]
  Domain adaptation is an important problem and often needed for real-world applications. A common approach in the domain adaptation literature is to learn a representation of the input that has the same distributions over the source and the target domain. We show that with a probabilistic representation network, the KL term can be estimated efficiently via minibatch samples.
  arXiv  Detail & Related papers  (2021-06-14T22:24:23Z)
• Examining and Combating Spurious Features under Distribution Shift [94.31956965507085]
  We define and analyze robust and spurious representations using the information-theoretic concept of minimal sufficient statistics. We prove that even when there is only bias of the input distribution, models can still pick up spurious features from their training data. Inspired by our analysis, we demonstrate that group DRO can fail when groups do not directly account for various spurious correlations.
  arXiv  Detail & Related papers  (2021-06-14T05:39:09Z)
• Gradual Domain Adaptation in the Wild:When Intermediate Distributions are Absent [32.906658998929394]
  We focus on the problem of domain adaptation when the goal is shifting the model towards the target distribution. We propose GIFT, a method that creates virtual samples from intermediate distributions by interpolating representations of examples from source and target domains.
  arXiv  Detail & Related papers  (2021-06-10T22:47:06Z)
• Learning Calibrated Uncertainties for Domain Shift: A Distributionally Robust Learning Approach [150.8920602230832]
  We propose a framework for learning calibrated uncertainties under domain shifts. In particular, the density ratio estimation reflects the closeness of a target (test) sample to the source (training) distribution. We show that our proposed method generates calibrated uncertainties that benefit downstream tasks.
  arXiv  Detail & Related papers  (2020-10-08T02:10:54Z)
• Robust Federated Learning: The Case of Affine Distribution Shifts [41.27887358989414]
  We develop a robust federated learning algorithm that achieves satisfactory performance against distribution shifts in users' samples. We show that an affine distribution shift indeed suffices to significantly decrease the performance of the learnt classifier in a new test user.
  arXiv  Detail & Related papers  (2020-06-16T03:43:59Z)

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.