From the 1 of 4 linked papers with an AI index.
5 papers
Context Adaptive Extended Chain Coding for Semantic Map Compression
Runyu Yang, Junqi Liao, Hyomin Choi +2
The paper proposes a lossless compression method for semantic maps that uses an extended chain coding scheme with context‑adaptive entropy coding and a skip‑coding mechanism to red…
Feature Compression for Machines with Range-Based Channel Truncation and Frame Packing
Juan Merlos, Fabien Racapé, Hyomin Choi +2
This paper proposes a method that enhances the compression performance of the current model under development for the upcoming MPEG standard on Feature Coding for Machines (FCM). T…
Efficient Feature Compression for Machines with Global Statistics Preservation
Md Eimran Hossain Eimon, Hyomin Choi, Fabien Racapé +4
The split-inference paradigm divides an artificial intelligence (AI) model into two parts. This necessitates the transfer of intermediate feature data between the two halves. Here,…
How Universal Are SAM2 Features?
Masoud Khairi Atani, Alon Harell, Hyomin Choi +3
The trade-off between general-purpose foundation vision models and their specialized counterparts is critical for efficient feature coding design and is not yet fully understood. W…
Variable-Rate Learned Image Compression with Multi-Objective Optimization and Quantization-Reconstruction Offsets
Fatih Kamisli, Fabien Racape, Hyomin Choi
Achieving successful variable bitrate compression with computationally simple algorithms from a single end-to-end learned image or video compression model remains a challenge. Many…