# Reinforced Bit Allocation under Task-Driven Semantic Distortion Metrics

arXiv: https://arxiv.org/abs/1910.07392 · HTML: https://mlsanity.com/paper/1910.07392/

## Key facts

- Cited by 6 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 16 Oct 2019.

## Built on by (most cited first, 6 of 6)

- [Visual Analysis Motivated Rate-Distortion Model for Image Coding](https://mlsanity.com/paper/2104.10315/) (2021)
- [Perceptual Video Coding for Machines via Satisfied Machine Ratio Modeling](https://mlsanity.com/paper/2211.06797/) (2022)
- [A Dual-Critic Reinforcement Learning Framework for Frame-level Bit Allocation in HEVC/H.265](https://mlsanity.com/paper/2104.01735/) (2021)
- [RL-RC-DoT: A Block-level RL agent for Task-Aware Video Compression](https://mlsanity.com/paper/2501.12216/) (2025)
- [End-to-End Image Compression with Probabilistic Decoding](https://mlsanity.com/paper/2109.14837/) (2021)
- [Diagnosis-oriented Medical Image Compression with Efficient Transfer Learning](https://mlsanity.com/paper/2310.13250/) (2023)

## Abstract (arXiv)

Rapid growing intelligent applications require optimized bit allocation in image/video coding to support specific task-driven scenarios such as detection, classification, segmentation, etc. Some learning-based frameworks have been proposed for this purpose due to their inherent end-to-end optimization mechanisms. However, it is still quite challenging to integrate these task-driven metrics seamlessly into traditional hybrid coding framework. To the best of our knowledge, this paper is the first work trying to solve this challenge based on reinforcement learning (RL) approach. Specifically, we formulate the bit allocation problem as a Markovian Decision Process (MDP) and train RL agents to automatically decide the quantization parameter (QP) of each coding tree unit (CTU) for HEVC intra coding, according to the task-driven semantic distortion metrics. This bit allocation scheme can maximize the semantic level fidelity of the task, such as classification accuracy, while minimizing the bit-rate. We also employ gradient class activation map (Grad-CAM) and Mask R-CNN tools to extract task-related importance maps to help the agents make decisions. Extensive experimental results demonstrate the superior performance of our approach by achieving 43.1% to 73.2% bit-rate saving over the anchor of HEVC under the equivalent task-related distortions.