paper-with-me

Papers

Dec-Adapter: Exploring Efficient Decoder-Side Adapter for Bridging Screen Content and Natural Image Compression

2023-01-01 · ICCV 2023 1 · Sheng Shen, Huanjing Yue, Jingyu Yang

Natural image compression has been greatly improved in the deep learning era. However, the compression performance will be heavily degraded if the pretrained encoder is directly applied on screen content image compression. Meanwhile, we observe that parameter-efficient trans-fer learning (PETL) methods have shown great adaptation ability in high-level vision tasks. Therefore, we propose a Dec-Adapter, a pioneering entropy-efficient transfer learning module for the decoder to bridge natural image and screen content compression. The adapter's parameters are learned during encoding and transmitted to the decoder for image-adaptive decoding. Our Dec-Adapter is lightweight, domain-transferable, and architecture-agnostic with generalized performance in bridging the two domains. Experiments demonstrate that our method outperforms all existing methods by a large margin in terms of BD-rate performance on screen content image compression. Specifically, our method achieves over 2 dB gain compared with the baseline when transferred to screen content image com-pression.

📄 PDF Abstract BibTeX

Code (0)

등록된 구현이 없습니다.

Tasks

DecoderImage CompressionTransfer Learning

Similar Papers 제목 키워드 기반

Universal Activation Verbalizer: A Unified Framework for Cross-Model Activation Explanation

2026-05-25 · Haiyan Zhao, Zirui He, Guanchu Wang, Ali Payani 외 arxiv

Activation verbalization explains hidden representations in natural language, but existing methods are mostly limited to self-explanation, where each model explains only its own activations. We introduce Universal Activa…

Prompting and Adapter Tuning for Self-supervised Encoder-Decoder Speech Model

2023-10-04 · Kai-Wei Chang, Ming-Hsin Chen, Yun-Ping Lin, Jing Neng Hsu 외

Prompting and adapter tuning have emerged as efficient alternatives to fine-tuning (FT) methods. However, existing studies on speech prompting focused on classification tasks and failed on more complex sequence generatio…

Cross-Lingual ASRDecoderslot-fillingSlot Filling

Representation Discrepancy Bridging Method for Remote Sensing Image-Text Retrieval

2025-05-22 · Hailong Ning, Siying Wang, Tao Lei, Xiaopeng Cao 외

Remote Sensing Image-Text Retrieval (RSITR) plays a critical role in geographic information interpretation, disaster monitoring, and urban planning by establishing semantic associations between image and textual descript…

cross-modal alignmentImage-text Retrievalparameter-efficient fine-tuningRetrieval+1

Domain Adaptation for Learned Image Compression with Supervised Adapters

2024-04-24 · Alberto Presta, Gabriele Spadaro, Enzo Tartaglione, Attilio Fiandrotti 외

In Learned Image Compression (LIC), a model is trained at encoding and decoding images sampled from a source domain, often outperforming traditional codecs on natural images; yet its performance may be far from optimal o…

DecoderDomain AdaptationImage Compression

Exploring Efficient-tuning Methods in Self-supervised Speech Models

2022-10-10 · Zih-Ching Chen, Chin-Lun Fu, Chih-Ying Liu, Shang-Wen Li 외

In this study, we aim to explore efficient tuning methods for speech self-supervised learning. Recent studies show that self-supervised learning (SSL) can learn powerful representations for different speech tasks. Howeve…

Self-Supervised Learning