Image coding for machines (ICM) aims to compress images for machine analysis
using recognition models rather than human vision. Hence, in ICM, it is
important for the encoder to recognize and compress the information necessary
for the machine recognition task. There are two main approaches in learned ICM;
optimization of the compression model based on task loss, and Region of
Interest (ROI) based bit allocation. These approaches provide the encoder with
the recognition capability. However, optimization with task loss becomes
difficult when the recognition model is deep, and ROI-based methods often
involve extra overhead during evaluation. In this study, we propose a novel
training method for learned ICM models that applies auxiliary loss to the
encoder to improve its recognition capability and rate-distortion performance.
Our method achieves Bjontegaard Delta rate improvements of 27.7% and 20.3% in
object detection and semantic segmentation tasks, compared to the conventional
training method.

通过辅助损失训练编码器以提升其识别能力和速率失真性能的一种新型学习图像编码方法，相较于传统训练方法，在物体检测和语义分割任务中分别实现了 27.7% 和 20.3% 的 Bjontegaard Delta 速率改进。

通过辅助损失优化编码器提高机器图像编码

Improving Image Coding for Machines through Optimizing Encoder via  Auxiliary Loss

Beyond the text detection and recognition tasks in image text spotting, video
text spotting presents an augmented challenge with the inclusion of tracking.
While advanced end-to-end trainable methods have shown commendable performance,
the pursuit of multi-task optimization may pose the risk of producing
sub-optimal outcomes for individual tasks. In this paper, we highlight a main
bottleneck in the state-of-the-art video text spotter: the limited recognition
capability. In response to this issue, we propose to efficiently turn an
off-the-shelf query-based image text spotter into a specialist on video and
present a simple baseline termed GoMatching, which focuses the training efforts
on tracking while maintaining strong recognition performance. To adapt the
image text spotter to video datasets, we add a rescoring head to rescore each
detected instance's confidence via efficient tuning, leading to a better
tracking candidate pool. Additionally, we design a long-short term matching
module, termed LST-Matcher, to enhance the spotter's tracking capability by
integrating both long- and short-term matching results via Transformer. Based
on the above simple designs, GoMatching achieves impressive performance on two
public benchmarks, e.g., setting a new record on the ICDAR15-video dataset, and
one novel test set with arbitrary-shaped text, while saving considerable
training budgets. The code will be released at
this https URL

在本文中，我们提出了一种名为 GoMatching 的简单基线方法，通过在跟踪任务中集中训练的努力来提高视频文本识别的性能，同时在图像文本识别任务上保持强大的性能表现。通过添加重新评分头和设计长短期匹配模块，GoMatching 在两个公共基准测试集上取得了令人印象深刻的性能。