paper-with-me

홈 › Papers

Efficient Masked Image Compression with Position-Indexed Self-Attention

2025-04-17 · Chengjie Dai, Tiantian Song, Hui Tang, Fangdong Chen, Bowei Yang, Guanghua Song

In recent years, image compression for high-level vision tasks has attracted considerable attention from researchers. Given that object information in images plays a far more crucial role in downstream tasks than background information, some studies have proposed semantically structuring the bitstream to selectively transmit and reconstruct only the information required by these tasks. However, such methods structure the bitstream after encoding, meaning that the coding process still relies on the entire image, even though much of the encoded information will not be transmitted. This leads to redundant computations. Traditional image compression methods require a two-dimensional image as input, and even if the unimportant regions of the image are set to zero by applying a semantic mask, these regions still participate in subsequent computations as part of the image. To address such limitations, we propose an image compression method based on a position-indexed self-attention mechanism that encodes and decodes only the visible parts of the masked image. Compared to existing semantic-structured compression methods, our approach can significantly reduce computational costs.

📄 PDF Abstract BibTeX arXiv:2504.12923

Code (0)

등록된 구현이 없습니다.

Tasks

Image CompressionPosition

Methods 이 논문이 사용한 방법론

Softmax The Softmax output function transforms a previous layer's output into a vector of probabilities. It is commonly used for multiclass classification. Given an input vector $x$…
Attention 설명 없음
SET Dynamic Sparse Training method where weight mask is updated randomly periodically

Similar Papers 제목 키워드 기반

Masked Surfel Prediction for Self-Supervised Point Cloud Learning

2022-07-07 · Yabin Zhang, Jiehong Lin, Chenhang He, Yongwei Chen 외

Masked auto-encoding is a popular and effective self-supervised learning approach to point cloud learning. However, most of the existing methods reconstruct only the masked points and overlook the local geometry informat…

DecoderPoint cloud reconstructionSelf-Supervised Learning

A Fast Palette Reordering Technique Based on GPU-Optimized Genetic Algorithms

2018-09-08 · IEEE International Conference on Image Processing (ICIP) 2018 9 · Oliver Giudice, Dario Allegra, Filippo Stanco, Giorgio Grasso 외

Color re-indexing is one of main approaches for improving the loss-less compression of color indexed images. Zero-order entropy reduction of indexes matrix is the key to obtain high compression ratio. However, obtaining …

ClusteringGPU

Label Ranker: Self-Aware Preference for Classification Label Position in Visual Masked Self-Supervised Pre-Trained Model

2025-03-03 · Preprints.org 2025 3 · Peihao Xiang, Kaida Wu, Ou Bai

This paper investigates the impact of randomly initialized unique encoding of classification label position on the visual masked self-supervised pre-trained model when fine-tuning downstream classification tasks. Our fin…

ClassificationDimensionality ReductionHuman Activity RecognitionImage Classification+3

Image Compression with Product Quantized Masked Image Modeling

2022-12-14 · Alaaeldin El-Nouby, Matthew J. Muckley, Karen Ullrich, Ivan Laptev 외

Recent neural compression methods have been based on the popular hyperprior framework. It relies on Scalar Quantization and offers a very strong compression performance. This contrasts from recent advances in image gener…

Image CompressionImage GenerationQuantizationRepresentation Learning+1

SemanticMIM: Marring Masked Image Modeling with Semantics Compression for General Visual Representation

2024-06-15 · Yike Yuan, Huanzhang Dou, Fengjun Guo, Xi Li

This paper represents a neat yet effective framework, named SemanticMIM, to integrate the advantages of masked image modeling (MIM) and contrastive learning (CL) for general visual representation. We conduct a thorough c…

Contrastive Learning