# Sharpen Focus: Learning with Attention Separability and Consistency

arXiv: https://arxiv.org/abs/1811.07484 · HTML: https://mlsanity.com/paper/1811.07484/

## Key facts

- Cited by 18 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 19 Nov 2018.

## Built on by (most cited first, 18 of 18)

- [Improving Deep Learning Interpretability by Saliency Guided Training](https://mlsanity.com/paper/2111.14338/) (2021)
- [A Peek Into the Reasoning of Neural Networks: Interpreting with Structural Visual Concepts](https://mlsanity.com/paper/2105.00290/) (2021)
- [Learning Hierarchical Attention for Weakly-supervised Chest X-Ray Abnormality Localization and Diagnosis](https://mlsanity.com/paper/2112.12349/) (2021)
- [Consistent Explanations by Contrastive Learning](https://mlsanity.com/paper/2110.00527/) (2021)
- [SMOOT: Saliency Guided Mask Optimized Online Training](https://mlsanity.com/paper/2310.00772/) (2023)
- [Towards To-a-T Spatio-Temporal Focus for Skeleton-Based Action Recognition](https://mlsanity.com/paper/2202.02314/) (2022)
- [Neural Insights for Digital Marketing Content Design](https://mlsanity.com/paper/2302.01416/) (2023)
- [Learning Transferable Conceptual Prototypes for Interpretable Unsupervised Domain Adaptation](https://mlsanity.com/paper/2310.08071/) (2023)
- [Improving Disease Classification Performance and Explainability of Deep Learning Models in Radiology with Heatmap Generators](https://mlsanity.com/paper/2207.00157/) (2022)
- [ATCON: Attention Consistency for Vision Models](https://mlsanity.com/paper/2210.09705/) (2022)
- [MAC: ModAlity Calibration for Object Detection](https://mlsanity.com/paper/2310.09461/) (2023)
- [SCAAT: Improving Neural Network Interpretability via Saliency Constrained Adaptive Adversarial Training](https://mlsanity.com/paper/2311.05143/) (2023)
- [Statistical Attention Localization (SAL): Methodology and Application to Object Classification](https://mlsanity.com/paper/2208.01823/) (2022)
- [Multi-view Action Recognition via Directed Gromov-Wasserstein Discrepancy](https://mlsanity.com/paper/2405.01337/) (2024)
- [Focus-Consistent Multi-Level Aggregation for Compositional Zero-Shot Learning](https://mlsanity.com/paper/2408.17083/) (2024)
- [Adaptive Progressive Attention Graph Neural Network for EEG Emotion Recognition](https://mlsanity.com/paper/2501.14246/) (2025)
- [AI-CNet3D: An Anatomically-Informed Cross-Attention Network with Multi-Task Consistency Fine-tuning for 3D Glaucoma Classification](https://mlsanity.com/paper/2510.00882/) (2025)
- [Inhibited Self-Attention: Sharpening Focus in Vision Transformers](https://mlsanity.com/paper/2607.12881/) (2026)

## Abstract (arXiv)

Recent developments in gradient-based attention modeling have seen attention maps emerge as a powerful tool for interpreting convolutional neural networks. Despite good localization for an individual class of interest, these techniques produce attention maps with substantially overlapping responses among different classes, leading to the problem of visual confusion and the need for discriminative attention. In this paper, we address this problem by means of a new framework that makes class-discriminative attention a principled part of the learning process. Our key innovations include new learning objectives for attention separability and cross-layer consistency, which result in improved attention discriminability and reduced visual confusion. Extensive experiments on image classification benchmarks show the effectiveness of our approach in terms of improved classification accuracy, including CIFAR-100 (+3.33%), Caltech-256 (+1.64%), ILSVRC2012 (+0.92%), CUB-200-2011 (+4.8%) and PASCAL VOC2012 (+5.73%).