paper-with-me

홈 › Papers

Hierarchical Sparse Attention Framework for Computationally Efficient Classification of Biological Cells

2025-05-12 · Elad Yoshai, Dana Yagoda-Aharoni, Eden Dotan, Natan T. Shaked

We present SparseAttnNet, a new hierarchical attention-driven framework for efficient image classification that adaptively selects and processes only the most informative pixels from images. Traditional convolutional neural networks typically process the entire images regardless of information density, leading to computational inefficiency and potential focus on irrelevant features. Our approach leverages a dynamic selection mechanism that uses coarse attention distilled by fine multi-head attention from the downstream layers of the model, allowing the model to identify and extract the most salient k pixels, where k is adaptively learned during training based on loss convergence trends. Once the top-k pixels are selected, the model processes only these pixels, embedding them as words in a language model to capture their semantics, followed by multi-head attention to incorporate global context. For biological cell images, we demonstrate that SparseAttnNet can process approximately 15% of the pixels instead of the full image. Applied to cell classification tasks using white blood cells images from the following modalities: optical path difference (OPD) images from digital holography for stain-free cells, images from motion-sensitive (event) camera from stain-free cells, and brightfield microscopy images of stained cells, For all three imaging modalities, SparseAttnNet achieves competitive accuracy while drastically reducing computational requirements in terms of both parameters and floating-point operations per second, compared to traditional CNNs and Vision Transformers. Since the model focuses on biologically relevant regions, it also offers improved explainability. The adaptive and lightweight nature of SparseAttnNet makes it ideal for deployment in resource-constrained and high-throughput settings, including imaging flow cytometry.

📄 PDF Abstract BibTeX arXiv:2505.07661

Code (0)

등록된 구현이 없습니다.

Tasks

image-classificationImage Classification

Methods 이 논문이 사용한 방법론

Attention 설명 없음
Softmax The Softmax output function transforms a previous layer's output into a vector of probabilities. It is commonly used for multiclass classification. Given an input vector $x$…
Linear Layer A Linear Layer is a projection $\mathbf{XW + b}$.
Multi-Head Attention 설명 없음
Focus 설명 없음

Similar Papers 제목 키워드 기반

Pruning and Sparsemax Methods for Hierarchical Attention Networks

2020-04-08 · João G. Ribeiro, Frederico S. Felisberto, Isabel C. Neto

This paper introduces and evaluates two novel Hierarchical Attention Network models [Yang et al., 2016] - i) Hierarchical Pruned Attention Networks, which remove the irrelevant words and sentences from the classification…

Document ClassificationGeneral ClassificationSentiment Analysis

Revisiting Transformer-based Models for Long Document Classification

2022-04-14 · Xiang Dai, Ilias Chalkidis, Sune Darkner, Desmond Elliott

The recent literature in text classification is biased towards short text sequences (e.g., sentences or paragraphs). In real-world applications, multi-page multi-paragraph documents are common and they cannot be efficien…

ClassificationDocument Classificationtext-classificationText Classification

ERNIE-SPARSE: Learning Hierarchical Efficient Transformer Through Regularized Self-Attention

2022-03-23 · Yang Liu, Jiaxiang Liu, Li Chen, Yuxiang Lu 외

Sparse Transformer has recently attracted a lot of attention since the ability for reducing the quadratic dependency on the sequence length. We argue that two factors, information bottleneck sensitivity and inconsistency…

Sparse Learningtext-classificationText Classification

ERNIE-SPARSE: Learning Hierarchical Efficient Transformer Through Regularized Self-Attention

2021-11-16 · ACL ARR November 2021 11 · Anonymous

Sparse Transformer has recently attracted a lot of attention since the ability for reducing the quadratic dependency on the sequence length. We argue that two factors, information bottleneck sensitivity and inconsistency…

Sparse Learningtext-classificationText Classification

Revisiting Transformer-based Models for Long Document Classification

2021-11-16 · ACL ARR November 2021 11 · Anonymous

The recent literature in text classification is biased towards short text sequences (e.g., sentences or paragraphs). In real-world applications, multi-page multi-paragraph documents are common and they cannot be efficie…

ClassificationDocument Classificationtext-classificationText Classification