.png){kind=icon}
.png){kind=icon}
Return
Representation Decorrelation Guided Robust Image Retrieval Against Label Noise
.png){kind=icon}
PRE
AI
姜
T
P
L
S
Y
M
DOI：10.1109/tbdata.2026.3689013.png)
.png){kind=icon}
Original request for help.png){kind=icon}
Share.png){kind=icon}
Save
Abstract
En 中文
Content-based image retrieval plays a critical role in diverse applications such as search engines and E-commerce. Nevertheless, a fundamental concern related to label noise within data arises. Label noise is often introduced by imperfect annotation approaches, which mislead retrieval models to memorize spurious patterns and thereby reduce the generalization performance of retrieval models. Firstly, we provide both quantitative and visual evidence that label noise induces dimensional collapse in the learned representation space, manifested as abnormal correlation response. To address this, we propose a robust image retrieval framework <italic xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink">TriTAN</i> to mitigate the negative impact caused by label noise while preserving the efficiency. In detail, <italic xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink">TriTAN</i> follows a two-stage training scheme. The first stage warms up the model with a noise-robust supervised objective. The second stage couples prototype-guided similarity learning with prototype-based relabeling and explicit representation decorrelation regularization. Experimental results on six datasets demonstrate the robust retrieval robustness of <italic xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink">TriTAN</i> compared to state-of-the-art methods under both synthetic and real-world label noise scenarios. We also verify the robust scalability of the proposed framework on diverse vision backbones.
Keywords:
Noisy label learning
weakly supervised learning
image retrieval
representation learning
Journal
I
IF:
5.7
Papers:
834
Citations:
3.0K
Organization
Cited Papers