# Spatially Attentive Output Layer for Image Classification

arXiv: https://arxiv.org/abs/2004.07570 · HTML: https://mlsanity.com/paper/2004.07570/

## Key facts

- Cited by 5 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 16 Apr 2020.

## Built on by (most cited first, 5 of 5)

- [A Discriminative Channel Diversification Network for Image Classification](https://mlsanity.com/paper/2112.05861/) (2021)
- [NOAH: Learning Pairwise Object Category Attentions for Image Classification](https://mlsanity.com/paper/2402.02377/) (2024)
- [Self-supervised Spatial Reasoning on Multi-View Line Drawings](https://mlsanity.com/paper/2104.13433/) (2021)
- [Fine-Grained Attention for Weakly Supervised Object Localization](https://mlsanity.com/paper/2104.04952/) (2021)
- [Privacy-Preserving Driver Drowsiness Detection with Spatial Self-Attention and Federated Learning](https://mlsanity.com/paper/2508.00287/) (2025)

## Abstract (arXiv)

Most convolutional neural networks (CNNs) for image classification use a global average pooling (GAP) followed by a fully-connected (FC) layer for output logits. However, this spatial aggregation procedure inherently restricts the utilization of location-specific information at the output layer, although this spatial information can be beneficial for classification. In this paper, we propose a novel spatial output layer on top of the existing convolutional feature maps to explicitly exploit the location-specific output information. In specific, given the spatial feature maps, we replace the previous GAP-FC layer with a spatially attentive output layer (SAOL) by employing a attention mask on spatial logits. The proposed location-specific attention selectively aggregates spatial logits within a target region, which leads to not only the performance improvement but also spatially interpretable outputs. Moreover, the proposed SAOL also permits to fully exploit location-specific self-supervision as well as self-distillation to enhance the generalization ability during training. The proposed SAOL with self-supervision and self-distillation can be easily plugged into existing CNNs. Experimental results on various classification tasks with representative architectures show consistent performance improvements by SAOL at almost the same computational cost.