# UniTAC: Universal Task-Aware Compression via Weighted Distortion Measures

arXiv: https://arxiv.org/abs/2608.16696 · HTML: https://mlsanity.com/paper/2608.16696/

## Key facts

- Cited by 1 papers in the map (data through 14 Oct 2026).
- Builds on 26 of its 35 references that are in the map.
- First posted on arXiv 17 Aug 2026.

## Builds on (most cited first, 26 of 26)

- [Deep Residual Learning for Image Recognition](https://mlsanity.com/paper/1512.03385/) (2015)
- [An Image is Worth 16x16 Words: Transformers for Image Recognition at Scale](https://mlsanity.com/paper/2010.11929/) (2020)
- [Grad-CAM: Visual Explanations from Deep Networks via Gradient-based Localization](https://mlsanity.com/paper/1610.02391/) (2016)
- [Deep Learning Face Attributes in the Wild](https://mlsanity.com/paper/1411.7766/) (2014)
- [Axiomatic Attribution for Deep Networks](https://mlsanity.com/paper/1703.01365/) (2017)
- [SmoothGrad: removing noise by adding noise](https://mlsanity.com/paper/1706.03825/) (2017)
- [Variational image compression with a scale hyperprior](https://mlsanity.com/paper/1802.01436/) (2018)
- [Deep Variational Information Bottleneck](https://mlsanity.com/paper/1612.00410/) (2016)
- [End-to-end Optimized Image Compression](https://mlsanity.com/paper/1611.01704/) (2016)
- [Interpretable Explanations of Black Boxes by Meaningful Perturbation](https://mlsanity.com/paper/1704.03296/) (2017)
- [AffectNet: A Database for Facial Expression, Valence, and Arousal Computing in the Wild](https://mlsanity.com/paper/1708.03985/) (2017)
- [A Survey of Embodied AI: From Simulators to Research Tasks](https://mlsanity.com/paper/2103.04918/) (2021)
- [Beyond Transmitting Bits: Context, Semantics, and Task-Oriented Communications](https://mlsanity.com/paper/2207.09353/) (2022)
- [6G Networks: Beyond Shannon Towards Semantic and Goal-Oriented Communications](https://mlsanity.com/paper/2011.14844/) (2020)
- [Video Coding for Machines: A Paradigm of Collaborative Compression and Intelligent Analytics](https://mlsanity.com/paper/2001.03569/) (2020)
- [Scalable Image Coding for Humans and Machines](https://mlsanity.com/paper/2107.08373/) (2021)
- [Image coding for machines: an end-to-end learned approach](https://mlsanity.com/paper/2108.09993/) (2021)
- [DeepWiVe: Deep-Learning-Aided Wireless Video Transmission](https://mlsanity.com/paper/2111.13034/) (2021)
- [End-to-end Learning of Compressible Features](https://mlsanity.com/paper/2007.11797/) (2020)
- [Improving performance of deep learning models with axiomatic attribution priors and expected gradients](https://mlsanity.com/paper/1906.10670/) (2019)
- [All-in-One Image Coding for Joint Human-Machine Vision with Multi-Path Aggregation](https://mlsanity.com/paper/2409.19660/) (2024)
- [TexShape: Information Theoretic Sentence Embedding for Language Models](https://mlsanity.com/paper/2402.05132/) (2024)
- [Prompt-ICM: A Unified Framework towards Image Coding for Machines with Task-driven Prompts](https://mlsanity.com/paper/2305.02578/) (2023)
- [An Overview of the JPEG AI Learning-Based Image Coding Standard](https://mlsanity.com/paper/2510.13867/) (2025)
- [Multi-level Reliability Interface for Semantic Communications over Wireless Networks](https://mlsanity.com/paper/2407.05487/) (2024)
- [Towards Robust Semantic Video Transmission over Block Erasure Channels](https://mlsanity.com/paper/2607.07823/) (2026)

## Built on by (most cited first, 1 of 1)

- [On Task Scope and Information Retention in Source Coding](https://mlsanity.com/paper/2609.37575/) (2026)

## Abstract (arXiv)

Lossy compression is conventionally driven by a task-agnostic distortion (e.g., MSE or MS-SSIM), yet in many emerging applications the receiver cares not about uniform fidelity but about a downstream task whose relevant content varies across the signal and evolves over time. We formulate task-aware compression as a weighted rate-distortion problem, in which a single codec is driven by a separable, per-component weighted distortion whose weights encode task importance and may depend on the source. We introduce task consistency, i.e., that minimizing the weighted distortion also minimizes the true task loss, and characterize when it holds: for linear tasks, the task loss admits a weighted-MSE form with signal-independent weights under suitable cross-term conditions, while for nonlinear tasks, an integrated-gradients analysis motivates separable task-aware weights. We show how task symmetry and irrelevance further constrain the admissible weights. Guided by this theory, we realize the weight-conditioned code in a single learned Vision Transformer (ViT) codec whose token-level attention natively consumes a per-component importance vector, so one fixed backbone is re-targeted at runtime, from universal (task-agnostic) to task-specialized operation, purely by swapping the injected weights, without retraining, while producing a single human-viewable reconstruction steered to the active task. On downstream face-analysis tasks, a single model reaches 91.4% accuracy at 0.034 bpp on a localized task, within 1.9% of a task-specific codec (93.3%) and well above a universal codec (76.9%). Such task-adaptive compression suits bandwidth-constrained perception systems, e.g., in Physical AI, where the active task drifts and per-task retraining is infeasible.