Overcoming Label Noise for Source-free Unsupervised Video Domain Adaptation - Archive ouverte HAL
Conference Papers Year : 2022

Overcoming Label Noise for Source-free Unsupervised Video Domain Adaptation

Abstract

Despite the progress seen in classification methods, current approaches for handling videos with distribution shifts in source and target domains remain source-dependent as they require access to the source data during the adaptation stage. In this paper, we present a self-training based source-free video domain adaptation approach (without bells and whistles) to address this challenge by bridging the gap between the source and the target domains. We use the source pre-trained model to generate pseudo-labels for the target domain samples, which are inevitably noisy. We treat the problem of source-free video domain adaptation as learning from noisy labels and argue that the samples with correct pseudo-labels can help in the adaptation stage. To this end, we leverage the cross-entropy loss as an indicator of the correctness of pseudo-labels, and use the resulting small-loss samples from the target domain for fine-tuning the model. Extensive experimental evaluations show that our method termed as CleanAdapt achieves ∼ 7% gain over the source-only model and outperforms the state-of-the-art approaches on various open datasets.
Fichier principal
Vignette du fichier
21.pdf (2.96 Mo) Télécharger le fichier
Origin Files produced by the author(s)

Dates and versions

hal-03929619 , version 1 (08-01-2023)

Identifiers

  • HAL Id : hal-03929619 , version 1

Cite

Avijit Dasgupta, C. V. Jawahar, Karteek Alahari. Overcoming Label Noise for Source-free Unsupervised Video Domain Adaptation. ICVGIP 2022 - Indian Conference on Computer Vision, Graphics and Image Processing, Dec 2022, Gandhinagar, India. pp.1-9. ⟨hal-03929619⟩
74 View
304 Download

Share

More