Papers › MRL: Learning to Mix with Attention and Convolutions

MRL: Learning to Mix with Attention and Convolutions

30 Aug 2022arXiv:2208.13975archive 2025-07-28

Shlok Mohta, Hisahiro Suganuma, Yoshiki Tanaka

In this paper, we present a new neural architectural block for the vision domain, named Mixing Regionally and Locally (MRL), developed with the aim of effectively and efficiently mixing the provided input features. We bifurcate the input feature mixing task as mixing at a regional and local scale. To achieve an efficient mix, we exploit the domain-wide receptive field provided by self-attention for regional-scale mixing and convolutional kernels restricted to local scale for local-scale mixing. More specifically, our proposed method mixes regional features associated with local features within a defined region, followed by a local-scale features mix augmented by regional features. Experiments show that this hybridization of self-attention and convolution brings improved capacity, generalization (right inductive bias), and efficiency. Under similar network settings, MRL outperforms or is at par with its counterparts in classification, object detection, and segmentation tasks. We also show that our MRL-based network architecture achieves state-of-the-art performance for H&E histology datasets. We achieved DICE of 0.843, 0.855, and 0.892 for Kumar, CoNSep, and CPM-17 datasets, respectively, while highlighting the versatility offered by the MRL framework by incorporating layers like group convolutions to improve dataset-specific generalization.

PaperPDF

Code

No code repository is listed for this paper in the archive or in Syntology's graph.

Code Syntology ran Syntology

Not run by Syntology. Nothing on this page verifies that the listed code works.

Tasks

Histopathological SegmentationInductive BiasMulti-tissue Nucleus SegmentationObject Detectionobject-detection

Results from the paper archive 2025-07-28

TaskDatasetModelMetricValueRank at snapshotLeaderboardReport
Multi-tissue Nucleus Segmentation Kumar GC-MHVN Dice 0.843 #1 of 18 Archive leaderboard report
Multi-tissue Nucleus Segmentation Kumar GC-MHVN Jaccard Index 0.652 #1 of 18 Archive leaderboard report
Multi-tissue Nucleus Segmentation Kumar GC-MHVN PQ 0.625 #1 of 18 Archive leaderboard report

Ranks are positions in the archive's leaderboards as they stood at the 2025-07-28 snapshot. Results published since then are not among these rows, so a rank here is not a current standing.

Methods

Convolution

Report a problem or propose a change · a person checks every report against the paper or source before anything changes; decisions are listed on /corrections