# HAD: Heterogeneity-Aware Distillation for Lifelong Heterogeneous Learning

arXiv: https://arxiv.org/abs/2603.26192 · HTML: https://mlsanity.com/paper/2603.26192/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Builds on 41 of its 62 references that are in the map.
- First posted on arXiv 27 Mar 2026.

## Builds on (most cited first, 30 of 41)

- [Deep Residual Learning for Image Recognition](https://mlsanity.com/paper/1512.03385/) (2015)
- [U-Net: Convolutional Networks for Biomedical Image Segmentation](https://mlsanity.com/paper/1505.04597/) (2015)
- [Overcoming catastrophic forgetting in neural networks](https://mlsanity.com/paper/1612.00796/) (2016)
- [The Cityscapes Dataset for Semantic Urban Scene Understanding](https://mlsanity.com/paper/1604.01685/) (2016)
- [Encoder-Decoder with Atrous Separable Convolution for Semantic Image Segmentation](https://mlsanity.com/paper/1802.02611/) (2018)
- [Learning without Forgetting](https://mlsanity.com/paper/1606.09282/) (2016)
- [iCaRL: Incremental Classifier and Representation Learning](https://mlsanity.com/paper/1611.07725/) (2016)
- [Vision Transformers for Dense Prediction](https://mlsanity.com/paper/2103.13413/) (2021)
- [Depth Anything: Unleashing the Power of Large-Scale Unlabeled Data](https://mlsanity.com/paper/2401.10891/) (2024)
- [Dark Experience for General Continual Learning: a Strong, Simple Baseline](https://mlsanity.com/paper/2004.07211/) (2020)
- [A Comprehensive Survey of Continual Learning: Theory, Method and Application](https://mlsanity.com/paper/2302.00487/) (2023)
- [A Survey on Multi-Task Learning](https://mlsanity.com/paper/1707.08114/) (2017)
- [Taskonomy: Disentangling Task Transfer Learning](https://mlsanity.com/paper/1804.08328/) (2018)
- [Gradient based sample selection for online continual learning](https://mlsanity.com/paper/1903.08671/) (2019)
- [PathNet: Evolution Channels Gradient Descent in Super Neural Networks](https://mlsanity.com/paper/1701.08734/) (2017)
- [Dilated Residual Networks](https://mlsanity.com/paper/1705.09914/) (2017)
- [PLOP: Learning without Forgetting for Continual Semantic Segmentation](https://mlsanity.com/paper/2011.11390/) (2020)
- [Balanced MSE for Imbalanced Visual Regression](https://mlsanity.com/paper/2203.16427/) (2022)
- [FeCAM: Exploiting the Heterogeneity of Class Distributions in Exemplar-Free Continual Learning](https://mlsanity.com/paper/2309.14062/) (2023)
- [What Matters When Repurposing Diffusion Models for General Dense Perception Tasks?](https://mlsanity.com/paper/2403.06090/) (2024)
- [The Edge of Depth: Explicit Constraints between Segmentation and Depth](https://mlsanity.com/paper/2004.00171/) (2020)
- [Flattening Sharpness for Dynamic Gradient Projection Memory Benefits Continual Learning](https://mlsanity.com/paper/2110.04593/) (2021)
- [Depth Any Video with Scalable Synthetic Data](https://mlsanity.com/paper/2410.10815/) (2024)
- [Understanding Imbalanced Semantic Segmentation Through Neural Collapse](https://mlsanity.com/paper/2301.01100/) (2023)
- [Parameter-Level Soft-Masking for Continual Learning](https://mlsanity.com/paper/2306.14775/) (2023)
- [Open-World Multi-Task Control Through Goal-Aware Representation Learning and Adaptive Horizon Prediction](https://mlsanity.com/paper/2301.10034/) (2023)
- [TransFGU: A Top-down Approach to Fine-Grained Unsupervised Semantic Segmentation](https://mlsanity.com/paper/2112.01515/) (2021)
- [Analyzing Overfitting under Class Imbalance in Neural Networks for Image Segmentation](https://mlsanity.com/paper/2102.10365/) (2021)
- [Continual Learning with Scaled Gradient Projection](https://mlsanity.com/paper/2302.01386/) (2023)
- [Universal Few-shot Learning of Dense Prediction Tasks with Visual Token Matching](https://mlsanity.com/paper/2303.14969/) (2023)

## Abstract (arXiv)

Lifelong learning aims to preserve knowledge acquired from previous tasks while incorporating knowledge from a sequence of new tasks. However, most prior work explores only streams of homogeneous tasks (textite.g., only classification tasks) and neglects the scenario of learning across heterogeneous tasks that possess different structures of outputs. In this work, we formalize this broader setting as lifelong heterogeneous learning (LHL). Departing from conventional lifelong learning, the task sequence of LHL spans different task types, and the learner needs to retain heterogeneous knowledge for different output space structures. To instantiate the LHL, we focus on LHL in the context of dense prediction (LHL4DP), a realistic and challenging scenario. To this end, we propose the Heterogeneity-Aware Distillation (HAD) method, an exemplar-free approach that preserves previously gained heterogeneous knowledge by self-distillation in each training phase. The proposed HAD comprises two complementary components, including a distribution-balanced heterogeneity-aware distillation loss to alleviate the global imbalance of prediction distribution and a salience-guided heterogeneity-aware distillation loss that concentrates learning on informative edge pixels extracted with the Sobel operator. Extensive experiments demonstrate that the proposed HAD method significantly outperforms existing methods in this new scenario.