EUVIMEDEUVIMED entdecken
Crossref

Transform-Free Feature Coding via Entropy-Constrained Vector Quantization

Qiaoxi Chen, Changsheng Gao, Li Li, Dong Liu

Proceedings of the AAAI Conference on Artificial Intelligence · 14.03.2026 · 40 (17) · 14565-14573

DOI: 10.1609/aaai.v40i17.38474 ↗

Kurz gefasst

Fachartikel in der Zeitschrift Proceedings of the AAAI Conference on Artificial Intelligence, online erschienen am 14.03.2026. Verfasst von Qiaoxi Chen und 3 weiteren Autor:innen. Die Arbeit wurde bisher 1-mal zitiert (Crossref).

AbstractBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

Feature coding has recently emerged as a key technique for efficient transmission of intermediate representations in distributed AI systems. Existing approaches largely follow a transform-based pipeline inherited from image and video coding, where the transform module is used to remove spatial structural redundancies in visual signals. However, our analysis indicates that such redundancies have already been largely removed during feature extraction, which reduces the necessity of the transform module. Building on this insight, we propose a new transform-free pipeline that directly encodes the extracted features via a vector quantization module and an entropy model. The proposed transform‑free framework jointly learns the quantization codebook and entropy model, enabling end‑to‑end optimization tailored to the inherent feature characteristics. Furthermore, the proposed method inherently avoids the computational complexity of the transform module. Experiments on features from diverse architectures and tasks demonstrate that our method achieves superior rate-distortion performance compared to transform-based baselines, while significantly reducing the encoding and decoding complexity.

Zitieren

APA

Chen, Q., Gao, C., Li, L., & Liu, D. (2026). Transform-Free Feature Coding via Entropy-Constrained Vector Quantization. Proceedings of the AAAI Conference on Artificial Intelligence, 40(17), 14565-14573. https://doi.org/10.1609/aaai.v40i17.38474

Vancouver

Chen Q, Gao C, Li L, Liu D. Transform-Free Feature Coding via Entropy-Constrained Vector Quantization. Proceedings of the AAAI Conference on Artificial Intelligence. 2026;40(17):14565-14573. doi:10.1609/aaai.v40i17.38474

BibTeX
@article{Chen2026,
  author = {Chen, Qiaoxi and Gao, Changsheng and Li, Li and Liu, Dong},
  title = {Transform-Free Feature Coding via Entropy-Constrained Vector Quantization},
  journal = {Proceedings of the AAAI Conference on Artificial Intelligence},
  year = {2026},
  volume = {40},
  number = {17},
  pages = {14565--14573},
  doi = {10.1609/aaai.v40i17.38474}
}
Kostenlos starten →