0

Attention, Please! Revisiting Attentive Probing for Masked Image Modeling

Efficient probing using a multi-query cross-attention mechanism enhances performance in self-supervised learning while reducing parameterization and computational cost compared to traditional methods.

Year
2025
Venue
arXiv 2025
Authors
9
Hosting
Abstract onlyARXIV-DEFAULT

Cite

Notes

Only stored in your browser.

Attribution

Abstract & full text
arxiv.org/abs/2506.10178ARXIV-DEFAULT
TL;DR
Semantic Scholar
Attribution policy →

Abstract

As fine-tuning (FT) becomes increasingly impractical at scale, probing is emerging as the preferred evaluation protocol for self-supervised learning (SSL). Yet, the standard linear probing (LP) fails to adequately reflect the potential of models trained with Masked Image Modeling (MIM), due to the distributed nature of patch tokens. This motivates the need for attentive probing, an alternative that uses attention to selectively aggregate patch-level features. Despite its growing adoption, attentive probing remains under-explored, with existing methods suffering from excessive parameterization and poor computational efficiency. In this work, we revisit attentive probing through the lens of the accuracy-efficiency trade-off. We conduct a systematic study of existing methods, analyzing their mechanisms and benchmarking their performance. We introduce efficient probing (EP), a multi-query cross-attention mechanism that eliminates redundant projections, reduces the number of trainable parameters, and achieves up to a 10$\times$ speed-up over conventional multi-head attention. Despite its simplicity, EP outperforms LP and prior attentive probing approaches across seven benchmarks, generalizes well beyond MIM to diverse pre-training paradigms, produces interpretable attention maps, and achieves strong gains in low-shot and layer-wise settings. Code available at https://github.com/billpsomas/efficient-probing.

Authors

9