返回
Learning-Based Image Compression With Parameter-Adaptive Rate-Constrained Loss
DOI:10.1109/LSP.2024.3383801.png)
摘要
En 中文
In recent years, the crucial task of image compression has been addressed by end-to-end neural network methods. However, achieving fine-grained rate control in this new paradigm has presented challenges. In our previous work, we explored mismatches in rate estimation during target-rate-oriented training and proposed heuristics involving costly parameter searches as a solution. This work proposes a lightweight approach, which dynamically adapts loss parameters to mitigate rate estimation issues, ensuring precise target rate attainment. Inspired by Reinforcement Learning, our method exhibits performance comparable to preceding approaches on the Kodak dataset in terms of PSNR. Additionally, it reduces computational training costs.
Keyword:
Convolutional neural network
learning-based image compression
rate control
variational autoencoder
期刊
IF:
9.6
论文数:
1.1W
被引数:
1.7W
机构
引用论文
Nonacog Alfa for Prophylaxis and Treatment of Bleeding Episodes in Previously Treated Patients with Moderately Severe or Severe Hemophilia B in India非阿考α用于印度既往经治的中重度或重度B型血友病患者出血事件的预防及治疗
Spontaneous Epidural Hematoma in a Child With Inherited Factor XIII Deficiency一名先天性因子XIII缺乏症患儿自发性硬膜外血肿
Long‐term high dose factor VIII treatment of 3 haemophiliacs with factor VIII inhibitor3例合并因子VIII抑制物的血友病患者接受长期大剂量因子VIII治疗
Management of Musculoskeletal Complications in Patients with Hemophilia:
Literature Review and Expert Recommendations血友病患者肌骨并发症的管理:文献综述与专家建议
Diagnosis, clinical manifestations and management of rare bleeding disorders in Iran罕见出血性疾病的诊断、临床表现与管理:伊朗经验
Hematology
IF0
Once-weekly prophylaxis regimen of nonacog alfa in patients with hemophilia B: an analysis of timing of bleeding event onset非阿卡哥α每周一次预防方案在B型血友病患者中的应用:出血事件发生时间的分析

