# Aggregation Cross-Entropy for Sequence Recognition

arXiv: https://arxiv.org/abs/1904.08364 · HTML: https://mlsanity.com/paper/1904.08364/

## Key facts

- Cited by 22 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 17 Apr 2019.

## Built on by (most cited first, 22 of 22)

- [From Two to One: A New Scene Text Recognizer with Visual Language Modeling Network](https://mlsanity.com/paper/2108.09661/) (2021)
- [PIMNet: A Parallel, Iterative and Mimicking Network for Scene Text Recognition](https://mlsanity.com/paper/2109.04145/) (2021)
- [MMOCR: A Comprehensive Toolbox for Text Detection, Recognition and Understanding](https://mlsanity.com/paper/2108.06543/) (2021)
- [When Counting Meets HMER: Counting-Aware Network for Handwritten Mathematical Expression Recognition](https://mlsanity.com/paper/2207.11463/) (2022)
- [Context Perception Parallel Decoder for Scene Text Recognition](https://mlsanity.com/paper/2307.12270/) (2023)
- [Recognition of Handwritten Chinese Text by Segmentation: A Segment-annotation-free Approach](https://mlsanity.com/paper/2207.14801/) (2022)
- [Towards Open-Set Text Recognition via Label-to-Prototype Learning](https://mlsanity.com/paper/2203.05179/) (2022)
- [SGBANet: Semantic GAN and Balanced Attention Network for Arbitrarily Oriented Scene Text Recognition](https://mlsanity.com/paper/2207.10256/) (2022)
- [Open-set Text Recognition via Character-Context Decoupling](https://mlsanity.com/paper/2204.05535/) (2022)
- [PageNet: Towards End-to-End Weakly Supervised Page-Level Handwritten Chinese Text Recognition](https://mlsanity.com/paper/2207.14807/) (2022)
- [Self-distillation Regularized Connectionist Temporal Classification Loss for Text Recognition: A Simple Yet Effective Approach](https://mlsanity.com/paper/2308.08806/) (2023)
- [InstructOCR: Instruction Boosting Scene Text Spotting](https://mlsanity.com/paper/2412.15523/) (2024)
- [Reciprocal Feature Learning via Explicit and Implicit Tasks in Scene Text Recognition](https://mlsanity.com/paper/2105.06229/) (2021)
- [I2C2W: Image-to-Character-to-Word Transformers for Accurate Scene Text Recognition](https://mlsanity.com/paper/2105.08383/) (2021)
- [Implicit Feature Alignment: Learn to Convert Text Recognizer to Text Spotter](https://mlsanity.com/paper/2106.05920/) (2021)
- [Parallel Scale-wise Attention Network for Effective Scene Text Recognition](https://mlsanity.com/paper/2104.12076/) (2021)
- [Masked and Permuted Implicit Context Learning for Scene Text Recognition](https://mlsanity.com/paper/2305.16172/) (2023)
- [Decoupling Visual-Semantic Feature Learning for Robust Scene Text Recognition](https://mlsanity.com/paper/2111.12351/) (2021)
- [An End-to-End Neural Network for Image-to-Audio Transformation](https://mlsanity.com/paper/2303.06078/) (2023)
- [Hippocampus-heuristic Character Recognition Network for Zero-shot Learning](https://mlsanity.com/paper/2104.02236/) (2021)
- [Geometric Perception based Efficient Text Recognition](https://mlsanity.com/paper/2302.03873/) (2023)
- [Augmented Transformers with Adaptive n-grams Embedding for Multilingual Scene Text Recognition](https://mlsanity.com/paper/2302.14261/) (2023)

## Abstract (arXiv)

In this paper, we propose a novel method, aggregation cross-entropy (ACE), for sequence recognition from a brand new perspective. The ACE loss function exhibits competitive performance to CTC and the attention mechanism, with much quicker implementation (as it involves only four fundamental formulas), faster inferenceback-propagation (approximately O(1) in parallel), less storage requirement (no parameter and negligible runtime memory), and convenient employment (by replacing CTC with ACE). Furthermore, the proposed ACE loss function exhibits two noteworthy properties: (1) it can be directly applied for 2D prediction by flattening the 2D prediction into 1D prediction as the input and (2) it requires only characters and their numbers in the sequence annotation for supervision, which allows it to advance beyond sequence recognition, e.g., counting problem. The code is publicly available at https://github.com/summerlvsong/Aggregation-Cross-Entropy.