# SAGE: Saliency-Guided Contrastive Embeddings

arXiv: https://arxiv.org/abs/2511.12744 · HTML: https://mlsanity.com/paper/2511.12744/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Builds on 24 of its 40 references that are in the map.
- First posted on arXiv 16 Nov 2025.

## Builds on (most cited first, 24 of 24)

- [Swin Transformer: Hierarchical Vision Transformer using Shifted Windows](https://mlsanity.com/paper/2103.14030/) (2021)
- [Distilling the Knowledge in a Neural Network](https://mlsanity.com/paper/1503.02531/) (2015)
- [Densely Connected Convolutional Networks](https://mlsanity.com/paper/1608.06993/) (2016)
- [EfficientNet: Rethinking Model Scaling for Convolutional Neural Networks](https://mlsanity.com/paper/1905.11946/) (2019)
- [FaceNet: A Unified Embedding for Face Recognition and Clustering](https://mlsanity.com/paper/1503.03832/) (2015)
- [Learning Deep Features for Discriminative Localization](https://mlsanity.com/paper/1512.04150/) (2015)
- [Sanity Checks for Saliency Maps](https://mlsanity.com/paper/1810.03292/) (2018)
- [Grad-CAM++: Improved Visual Explanations for Deep Convolutional Networks](https://mlsanity.com/paper/1710.11063/) (2017)
- [RISE: Randomized Input Sampling for Explanation of Black-box Models](https://mlsanity.com/paper/1806.07421/) (2018)
- [Score-CAM: Score-Weighted Visual Explanations for Convolutional Neural Networks](https://mlsanity.com/paper/1910.01279/) (2019)
- [Axiom-based Grad-CAM: Towards Accurate Visualization and Explanation of CNNs](https://mlsanity.com/paper/2008.02312/) (2020)
- [On a generalization of the Jensen-Shannon divergence and the JS-symmetrization of distances relying on abstract means](https://mlsanity.com/paper/1904.04017/) (2019)
- [Creation and Validation of a Chest X-Ray Dataset with Eye-tracking and Report Dictation for AI Development](https://mlsanity.com/paper/2009.07386/) (2020)
- [SS-CAM: Smoothed Score-CAM for Sharper Visual Feature Localization](https://mlsanity.com/paper/2006.14255/) (2020)
- [CYBORG: Blending Human Saliency Into the Loss Improves Deep Learning](https://mlsanity.com/paper/2112.00686/) (2021)
- [Post-mortem Iris Recognition with Deep-Learning-based Image Segmentation](https://mlsanity.com/paper/1901.01708/) (2019)
- [Iris Liveness Detection Competition (LivDet-Iris) -- The 2020 Edition](https://mlsanity.com/paper/2009.00749/) (2020)
- [Human-Aided Saliency Maps Improve Generalization of Deep Learning](https://mlsanity.com/paper/2105.03492/) (2021)
- [GazeGNN: A Gaze-Guided Graph Neural Network for Chest X-ray Classification](https://mlsanity.com/paper/2305.18221/) (2023)
- [Assessment of iris recognition reliability for eyes affected by ocular pathologies](https://mlsanity.com/paper/1809.00206/) (2018)
- [Explain To Me: Salience-Based Explainability for Synthetic Face Detection Models](https://mlsanity.com/paper/2303.11969/) (2023)
- [Gaze-Guided Class Activation Mapping: Leveraging Human Attention for Network Attention in Chest X-rays Classification](https://mlsanity.com/paper/2202.07107/) (2022)
- [Grains of Saliency: Optimizing Saliency-based Training of Biometric Attack Detection Models](https://mlsanity.com/paper/2405.00650/) (2024)
- [Taking Training Seriously: Human Guidance and Management-Based Regulation of Artificial Intelligence](https://mlsanity.com/paper/2402.08466/) (2024)

## Abstract (arXiv)

Integrating human perceptual priors into the training of neural networks has been shown to raise model generalization, serve as an effective regularizer, and align models with human expertise for applications in high-risk domains. Existing approaches to integrate saliency into model training often rely on internal model mechanisms, which recent research suggests may be unreliable. Our insight is that many challenges associated with saliency-guided training stem from the placement of the guidance approaches solely within the image space. Instead, we move away from the image space, use the model's latent space embeddings to steer human guidance during training, and we propose SAGE (Saliency-Guided Contrastive Embeddings): a loss function that integrates human saliency into network training using contrastive embeddings. We apply salient-preserving and saliency-degrading signal augmentations to the input and capture the changes in embeddings and model logits. We guide the model towards salient features and away from non-salient features using a contrastive triplet loss. Additionally, we perform a sanity check on the logit distributions to ensure that the model outputs match the saliency-based augmentations. We demonstrate a boost in classification performance across both open- and closed-set scenarios against SOTA saliency-based methods, showing SAGE's effectiveness across various backbones, and include experiments to suggest its wide generalization across tasks.