Lightweight Frequency Masker for Cross-Domain Few-Shot Semantic Segmentation

• URL: http://arxiv.org/abs/2410.22135v2
• Date: Fri, 22 Nov 2024 06:41:07 GMT
• Title: Lightweight Frequency Masker for Cross-Domain Few-Shot Semantic Segmentation
• Authors: Jintao Tong, Yixiong Zou, Yuhua Li, Ruixuan Li,
• Abstract summary: Cross-domain few-shot segmentation (CD-FSS) is proposed to first pre-train the model on a large-scale source-domain dataset. We propose a lightweight frequency masker, which further reduces channel correlations by an Amplitude-Phase Masker (APM) module and an Adaptive Channel Phase Attention (ACPA) module.
• Score: 9.365590675168589
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: Cross-domain few-shot segmentation (CD-FSS) is proposed to first pre-train the model on a large-scale source-domain dataset, and then transfer the model to data-scarce target-domain datasets for pixel-level segmentation. The significant domain gap between the source and target datasets leads to a sharp decline in the performance of existing few-shot segmentation (FSS) methods in cross-domain scenarios. In this work, we discover an intriguing phenomenon: simply filtering different frequency components for target domains can lead to a significant performance improvement, sometimes even as high as 14% mIoU. Then, we delve into this phenomenon for an interpretation, and find such improvements stem from the reduced inter-channel correlation in feature maps, which benefits CD-FSS with enhanced robustness against domain gaps and larger activated regions for segmentation. Based on this, we propose a lightweight frequency masker, which further reduces channel correlations by an Amplitude-Phase Masker (APM) module and an Adaptive Channel Phase Attention (ACPA) module. Notably, APM introduces only 0.01% additional parameters but improves the average performance by over 10%, and ACPA imports only 2.5% parameters but further improves the performance by over 1.5%, which significantly surpasses the state-of-the-art CD-FSS methods.

Related papers

• The Devil is in Low-Level Features for Cross-Domain Few-Shot Segmentation [22.443834719018795]
  Cross-Domain Few-Shot (CDFSS) is proposed to transfer the pixel-level segmentation capabilities learned from large-scale source-domain datasets to downstream target-domain datasets. We focus on a well-observed but unresolved phenomenon in CDFSS: for target domains, segmentation performance peaks at the very early epochs, and declines sharply as the source-domain training proceeds. We propose a method that includes two plug-and-play modules: one to flatten the loss landscapes for low-level features during source-domain training as a novel sharpness-aware method, and the other to directly supplement target-
  arXiv  Detail & Related papers  (2025-03-27T04:37:52Z)
• FUSED-Net: Enhancing Few-Shot Traffic Sign Detection with Unfrozen Parameters, Pseudo-Support Sets, Embedding Normalization, and Domain Adaptation [2.111102681327218]
  We present 'FUSED-Net', built-upon Faster RCNN for traffic sign detection. Unlike traditional approaches, we keep all parameters unfrozen during training, enabling FUSED-Net to learn from limited samples. We achieve 2.4x, 2.2x, 1.5x, and 1.3x improvements of mAP in 1-shot, 3-shot, 5-shot, and 10-shot scenarios, respectively.
  arXiv  Detail & Related papers  (2024-09-23T09:34:42Z)
• APSeg: Auto-Prompt Network for Cross-Domain Few-Shot Semantic Segmentation [33.90244697752314]
  We introduce APSeg, a novel auto-prompt network for cross-domain few-shot semantic segmentation (CD-FSS) Our model outperforms the state-of-the-art CD-FSS method by 5.24% and 3.10% in average accuracy on 1-shot and 5-shot settings, respectively.
  arXiv  Detail & Related papers  (2024-06-12T16:20:58Z)
• Diffusion Cross-domain Recommendation [0.0]
  We propose Diffusion Cross-domain Recommendation (DiffCDR) to give high-quality outcomes to cold-start users. We first adopt the theory of DPM and design a Diffusion Module (DIM), which generates user's embedding in target domain. In addition, we consider the label data of the target domain and form the task-oriented loss function, which enables our DiffCDR to adapt to specific tasks.
  arXiv  Detail & Related papers  (2024-02-03T15:14:51Z)
• Cross-Domain Few-Shot Segmentation via Iterative Support-Query Correspondence Mining [81.09446228688559]
  Cross-Domain Few-Shots (CD-FSS) poses the challenge of segmenting novel categories from a distinct domain using only limited exemplars. We propose a novel cross-domain fine-tuning strategy that addresses the challenging CD-FSS tasks.
  arXiv  Detail & Related papers  (2024-01-16T14:45:41Z)
• DARNet: Bridging Domain Gaps in Cross-Domain Few-Shot Segmentation with Dynamic Adaptation [20.979759016826378]
  Few-shot segmentation (FSS) aims to segment novel classes in a query image by using only a small number of supporting images from base classes. In cross-domain FSS, leveraging features from label-rich domains for resource-constrained domains poses challenges due to domain discrepancies. This work presents a Dynamically Adaptive Refine (DARNet) method that aims to balance generalization and specificity for CD-FSS.
  arXiv  Detail & Related papers  (2023-12-08T03:03:22Z)
• Dense Affinity Matching for Few-Shot Segmentation [83.65203917246745]
  Few-Shot (FSS) aims to segment the novel class images with a few samples. We propose a dense affinity matching framework to exploit the support-query interaction. We show that our framework performs very competitively under different settings with only 0.68M parameters.
  arXiv  Detail & Related papers  (2023-07-17T12:27:15Z)
• MS-MT: Multi-Scale Mean Teacher with Contrastive Unpaired Translation for Cross-Modality Vestibular Schwannoma and Cochlea Segmentation [11.100048696665496]
  unsupervised domain adaptation (UDA) methods have achieved promising cross-modality segmentation performance. We propose a multi-scale self-ensembling based UDA framework for automatic segmentation of two key brain structures. Our method demonstrates promising segmentation performance with a mean Dice score of 83.8% and 81.4%.
  arXiv  Detail & Related papers  (2023-03-28T08:55:00Z)
• Amplitude Spectrum Transformation for Open Compound Domain Adaptive Semantic Segmentation [62.68759523116924]
  Open compound domain adaptation (OCDA) has emerged as a practical adaptation setting. We propose a novel feature space Amplitude Spectrum Transformation (AST)
  arXiv  Detail & Related papers  (2022-02-09T05:40:34Z)
• Stagewise Unsupervised Domain Adaptation with Adversarial Self-Training for Road Segmentation of Remote Sensing Images [93.50240389540252]
  Road segmentation from remote sensing images is a challenging task with wide ranges of application potentials. We propose a novel stagewise domain adaptation model called RoadDA to address the domain shift (DS) issue in this field. Experiment results on two benchmarks demonstrate that RoadDA can efficiently reduce the domain gap and outperforms state-of-the-art methods.
  arXiv  Detail & Related papers  (2021-08-28T09:29:14Z)
• Discriminative Cross-Domain Feature Learning for Partial Domain Adaptation [70.45936509510528]
  Partial domain adaptation aims to adapt knowledge from a larger and more diverse source domain to a smaller target domain with less number of classes. Recent practice on domain adaptation manages to extract effective features by incorporating the pseudo labels for the target domain. It is essential to align target data with only a small set of source data.
  arXiv  Detail & Related papers  (2020-08-26T03:18:53Z)
• Towards Fair Cross-Domain Adaptation via Generative Learning [50.76694500782927]
  Domain Adaptation (DA) targets at adapting a model trained over the well-labeled source domain to the unlabeled target domain lying in different distributions. We develop a novel Generative Few-shot Cross-domain Adaptation (GFCA) algorithm for fair cross-domain classification.
  arXiv  Detail & Related papers  (2020-03-04T23:25:09Z)

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.