# Mutually Causal Semantic Distillation Network for Zero-Shot Learning

arXiv: https://arxiv.org/abs/2603.17412 · HTML: https://mlsanity.com/paper/2603.17412/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Builds on 56 of its 90 references that are in the map.
- First posted on arXiv 18 Mar 2026.

## Builds on (most cited first, 30 of 56)

- [Deep Residual Learning for Image Recognition](https://mlsanity.com/paper/1512.03385/) (2015)
- [Learning Transferable Visual Models From Natural Language Supervision](https://mlsanity.com/paper/2103.00020/) (2021)
- [Distilling the Knowledge in a Neural Network](https://mlsanity.com/paper/1503.02531/) (2015)
- [Learning to Prompt for Vision-Language Models](https://mlsanity.com/paper/2109.01134/) (2021)
- [FitNets: Hints for Thin Deep Nets](https://mlsanity.com/paper/1412.6550/) (2014)
- [Deep Mutual Learning](https://mlsanity.com/paper/1706.00384/) (2017)
- [Unbiased Scene Graph Generation from Biased Training](https://mlsanity.com/paper/2002.11949/) (2020)
- [Feature Generating Networks for Zero-Shot Learning](https://mlsanity.com/paper/1712.00981/) (2017)
- [Zero-Shot Learning -- The Good, the Bad and the Ugly](https://mlsanity.com/paper/1703.04394/) (2017)
- [Generalized Zero- and Few-Shot Learning via Aligned Variational Autoencoders](https://mlsanity.com/paper/1812.01784/) (2018)
- [Actor-Mimic: Deep Multitask and Transfer Reinforcement Learning](https://mlsanity.com/paper/1511.06342/) (2015)
- [Label-Embedding for Image Classification](https://mlsanity.com/paper/1503.08677/) (2015)
- [f-VAEGAN-D2: A Feature Generating Framework for Any-Shot Learning](https://mlsanity.com/paper/1903.10132/) (2019)
- [Attribute Prototype Network for Zero-Shot Learning](https://mlsanity.com/paper/2008.08290/) (2020)
- [A Review of Generalized Zero-Shot Learning Methods](https://mlsanity.com/paper/2011.08641/) (2020)
- [Suppressing Uncertainties for Large-Scale Facial Expression Recognition](https://mlsanity.com/paper/2002.10392/) (2020)
- [Causality Inspired Representation Learning for Domain Generalization](https://mlsanity.com/paper/2203.14237/) (2022)
- [Region Attention Networks for Pose and Occlusion Robust Facial Expression Recognition](https://mlsanity.com/paper/1905.04075/) (2019)
- [Generalized Zero-Shot Learning via Synthesized Examples](https://mlsanity.com/paper/1712.03878/) (2017)
- [Counterfactual Attention Learning for Fine-Grained Visual Categorization and Re-identification](https://mlsanity.com/paper/2108.08728/) (2021)
- [Interventional Few-Shot Learning](https://mlsanity.com/paper/2009.13000/) (2020)
- [Causal Attention for Vision-Language Tasks](https://mlsanity.com/paper/2103.03493/) (2021)
- [Counterfactual Zero-Shot and Open-Set Visual Recognition](https://mlsanity.com/paper/2103.00887/) (2021)
- [Contrastive Embedding for Generalized Zero-Shot Learning](https://mlsanity.com/paper/2103.16173/) (2021)
- [Leveraging the Invariant Side of Generative Zero-Shot Learning](https://mlsanity.com/paper/1904.04092/) (2019)
- [Causal Attention for Unbiased Visual Recognition](https://mlsanity.com/paper/2108.08782/) (2021)
- [Confounding-Robust Policy Improvement](https://mlsanity.com/paper/1805.08593/) (2018)
- [Domain-aware Visual Bias Eliminating for Generalized Zero-Shot Learning](https://mlsanity.com/paper/2003.13261/) (2020)
- [Goal-Oriented Gaze Estimation for Zero-Shot Learning](https://mlsanity.com/paper/2103.03433/) (2021)
- [Zero-Shot Visual Recognition using Semantics-Preserving Adversarial Embedding Networks](https://mlsanity.com/paper/1712.01928/) (2017)

## Abstract (arXiv)

Zero-shot learning (ZSL) aims to recognize the unseen classes in the open-world guided by the side-information (e.g., attributes). Its key task is how to infer the latent semantic knowledge between visual and attribute features on seen classes, and thus conducting a desirable semantic knowledge transfer from seen classes to unseen ones. Prior works simply utilize unidirectional attention within a weakly-supervised manner to learn the spurious and limited latent semantic representations, which fail to effectively discover the intrinsic semantic knowledge (e.g., attribute semantic) between visual and attribute features. To solve the above challenges, we propose a mutually causal semantic distillation network (termed MSDN++) to distill the intrinsic and sufficient semantic representations for ZSL. MSDN++ consists of an attributerightarrowvisual causal attention sub-net that learns attribute-based visual features, and a visualrightarrowattribute causal attention sub-net that learns visual-based attribute features. The causal attentions encourages the two sub-nets to learn causal vision-attribute associations for representing reliable features with causal visual/attribute learning. With the guidance of semantic distillation loss, the two mutual attention sub-nets learn collaboratively and teach each other throughout the training process. Extensive experiments on three widely-used benchmark datasets (e.g., CUB, SUN, AWA2, and FLO) show that our MSDN++ yields significant improvements over the strong baselines, leading to new state-of-the-art performances.