Improving Image Coding for Machines through Optimizing Encoder via Auxiliary Loss

[2402.08267] Improving Image Coding for Machines through Optimizing Encoder via Auxiliary Loss Skip to main content Search Submit Donate Log in Search arXiv Press Enter to search · Advanced search Computer Science > Computer Vision and Pattern Recognition arXiv:2402.08267 (cs) [Submitted on 13 Feb 2024 ( v1 ), last revised 9 Apr 2026 (this version, v3)] Title: Improving Image Coding for Machines through Optimizing Encoder via Auxiliary Loss Authors: Kei Iino , Shunsuke Akamatsu , Hiroshi Watanabe , Shohei Enomoto , Akira Sakamoto , Takeharu Eda View a PDF of the paper titled Improving Image Coding for Machines through Optimizing Encoder via Auxiliary Loss, by Kei Iino and 5 other authors View PDF Abstract: Image coding for machines (ICM) aims to compress images for machine analysis using recognition models rather than human vision. Hence, in ICM, it is important for the encoder to recognize and compress the information necessary for the machine recognition task. There are two main approaches in learned ICM; optimization of the compression model based on task loss, and Region of Interest (ROI) based bit allocation. These approaches provide the encoder with the recognition capability. However, optimization with task loss becomes difficult when the recognition model is deep, and ROI-based methods often involve extra overhead during evaluation. In this study, we propose a novel training method for learned ICM models that applies auxiliary loss to the encoder to improve its recognition capability and rate-distortion performance. Our method achieves Bjontegaard Delta rate improvements of 27.7% and 20.3% in object detection and semantic segmentation tasks, compared to the conventional training method. Comments: Accepted at ICIP 2024 Subjects: Computer Vision and Pattern Recognition (cs.CV) ; Artificial Intelligence (cs.AI) Cite as: arXiv:2402.08267 [cs.CV] (or arXiv:2402.08267v3 [cs.CV] for this version) https://doi.org/10.48550/arXiv.2402.08267 Focus to learn more arXiv-issued DOI via DataCite Related DOI : https://doi.org/10.1109/ICIP51287.2024.10647577 Focus to learn more DOI(s) linking to related resources Submission history From: Kei Iino [ view email ] [v1] Tue, 13 Feb 2024 07:45:25 UTC (853 KB) (withdrawn) [v2] Sat, 28 Sep 2024 14:05:27 UTC (853 KB) [v3] Thu, 9 Apr 2026 07:58:39 UTC (853 KB) Full-text links: Access Paper: View a PDF of the paper titled Improving Image Coding for Machines through Optimizing Encoder via Auxiliary Loss, by Kei Iino and 5 other authors View PDF view license Current browse context: cs.CV < prev | next > new | recent | 2024-02 Change to browse by: cs cs.AI References & Citations NASA ADS Google Scholar Semantic Scholar export BibTeX citation Loading... BibTeX formatted citation × loading... Data provided by: Bookmark Bibliographic Tools Bibliographic and Citation Tools Bibliographic Explorer Toggle Bibliographic Explorer ( What is the Explorer? ) Connected Papers Toggle Connected Papers ( What is Connected Papers? ) Litmaps Toggle Litmaps ( What is Litmaps? ) scite.ai Toggle scite Smart Citations ( What are Smart Citations? ) Code, Data, Media Code, Data and Media Associated with this Article alphaXiv Toggle alphaXiv ( What is alphaXiv? ) Links to Code Toggle CatalyzeX Code Finder for Papers ( What is CatalyzeX? ) DagsHub Toggle DagsHub ( What is DagsHub? ) GotitPub Toggle Gotit.pub ( What is GotitPub? ) Huggingface Toggle Hugging Face ( What is Huggingface? ) ScienceCast Toggle ScienceCast ( What is ScienceCast? ) Demos Demos Replicate Toggle Replicate ( What is Replicate? ) Spaces Toggle Hugging Face Spaces ( What is Spaces? ) Spaces Toggle TXYZ.AI ( What is TXYZ.AI? ) Related Papers Recommenders and Search Tools Link to Influence Flower Influence Flower ( What are Influence Flowers? ) Core recommender toggle CORE Recommender ( What is CORE? ) Author Venue Institution Topic About arXivLabs arXivLabs: experimental projects with community collaborators arXivLabs is a framework that allows collaborators to develop and share new arXiv features directly on our website. Both individuals and organizations that work with arXivLabs have embraced and accepted our values of openness, community, excellence, and user data privacy. arXiv is committed to these values and only works with partners that adhere to them. Have an idea for a project that will add value for arXiv's community? Learn more about arXivLabs . Which authors of this paper are endorsers? | Disable MathJax ( What is MathJax? ) We gratefully acknowledge support from our major funders , member institutions , , and all contributors. About · Help · Contact · Subscribe · Copyright · Privacy · Accessibility · Operational Status (opens in new tab) Major funding support from

Related documents

• UnionSparse: An Index-Efficient Sparsity Framework for Low-Bit Sparse LLM Inference on Edge#441749
• Contextual Utility of Quantization Moves in Extreme Low-Bit LLMs#996683
• rapidcodeR: Fast, Easy, and Affordable Data Coding with LLMs#393497
• Tuna-2: Pixel Embeddings Beat Vision Encoders for Multimodal Understanding and Generation#141780
• SignRoundV2: Closing the Performance Gap in Extremely Low-Bit Post-Training Quantization for LLMs#149328