Feature Compression

Description from the archive archive 2025-07-28.

Benchmarks archive 2025-07-28

No benchmark for this task in the archive.

Libraries

Not in the archive: the export carries no per-task library table, so there is nothing to show at snapshot 2025-07-28.

Datasets archive 2025-07-28

No dataset record in the archive lists this task.

Subtasks archive 2025-07-28

No subtask under this task in the archive's task tree.

Parent tasks archive 2025-07-28

Most implemented papers archive 2025-07-28

28 shown of 28 papers with code (96 tagged with this task in all), ordered by repositories listed in the archive, not by stars (the archive holds no stars, so PwC's “Social” and “Latest” sorts cannot be reproduced). Papers without a page here are shown as plain text.

• Flexible Variable-Rate Image Feature Compression for Edge-Cloud Systems
  30 Mar 2024 2 repositories listed
  By compressing different intermediate features of a pre-trained vision task model, the proposed method can scale the encoding complexity without changing the overall size of the model.
• EMIFF: Enhanced Multi-scale Image Feature Fusion for Vehicle-Infrastructure Cooperative 3D Object Detection
  23 Feb 2024 2 repositories listed
  In autonomous driving, cooperative perception makes use of multi-view cameras from both vehicles and infrastructure, providing a global vantage point with rich semantic context of road conditions beyond a single vehicle…
• VIMI: Vehicle-Infrastructure Multi-view Intermediate Fusion for Camera-based 3D Object Detection
  20 Mar 2023 2 repositories listed Syntology ran 0 of 2 samples · 2 unverified
  In autonomous driving, Vehicle-Infrastructure Cooperative 3D Object Detection (VIC3D) makes use of multi-view cameras from both vehicles and traffic infrastructure, providing a global vantage point with rich semantic…
• Supervised Compression for Resource-Constrained Edge Computing Systems
  21 Aug 2021 2 repositories listed Syntology ran 1 of 17 samples · 16 unverified · 1 pointer-only (licence)
  There has been much interest in deploying deep learning algorithms on low-powered devices, including smartphones, drones, and medical sensors.
• TransVFC: A Transformable Video Feature Compression Framework for Machines
  31 Mar 2025 1 repository listed
  Then, the codec implements perception-guided conditional coding to minimize spatial redundancy and help the reconstructed features align with downstream machine perception.
• LLaVA-ST: A Multimodal Large Language Model for Fine-Grained Spatial-Temporal Understanding
  14 Jan 2025 1 repository listed Syntology ran 3 of 7 samples · 4 unverified
  Furthermore, we propose ST-Align dataset with 4.
• Meissonic: Revitalizing Masked Generative Transformers for Efficient High-Resolution Text-to-Image Synthesis
  10 Oct 2024 1 repository listed Syntology ran 4 of 12 samples · 8 unverified
  We present Meissonic, which elevates non-autoregressive masked image modeling (MIM) text-to-image to a level comparable with state-of-the-art diffusion models like SDXL.
• Entropy Loss: An Interpretability Amplifier of 3D Object Detection Network for Intelligent Driving
  1 Sep 2024 1 repository listed
  Entropy Loss is formulated based on the functionality of feature compression networks within the perception model.
• I²VC: A Unified Framework for Intra- & Inter-frame Video Compression
  23 May 2024 1 repository listed
  Previous neural video compression methods necessitate distinct codecs for three types of frames (I-frame, P-frame and B-frame), which hinders a unified approach and generalization across different video contexts.
• Vector Quantization for Recommender Systems: A Review and Outlook
  6 May 2024 1 repository listed
  Finally, the survey analyzes the remaining challenges and anticipates future trends in VQ4Rec, including the challenges associated with the training of vector quantization, the opportunities presented by large language…
• FOOL: Addressing the Downlink Bottleneck in Satellite Computing with Neural Feature Compression
  25 Mar 2024 1 repository listed
  Further, it embeds context and leverages inter-tile dependencies to lower transfer costs with negligible overhead.
• Effective Communication with Dynamic Feature Compression
  29 Jan 2024 1 repository listed
  The remote wireless control of industrial systems is one of the major use cases for 5G and beyond systems: in these cases, the massive amounts of sensory information that need to be shared over the wireless medium may…
• Learning to Manipulate Artistic Images
  25 Jan 2024 1 repository listed Syntology ran 1 of 2 samples · 1 unverified
  Recent advancement in computer vision has significantly lowered the barriers to artistic creation.
• WidthFormer: Toward Efficient Transformer-based BEV View Transformation
  8 Jan 2024 1 repository listed
  We present WidthFormer, a novel transformer-based module to compute Bird's-Eye-View (BEV) representations from multi-view cameras for real-time autonomous-driving applications.
• Understanding Deep Representation Learning via Layerwise Feature Compression and Discrimination
  6 Nov 2023 1 repository listed Syntology ran 11 of 17 samples · 6 unverified · 17 pointer-only (licence)
  To the best of our knowledge, this is the first quantitative characterization of feature evolution in hierarchical representations of deep linear networks.
• End-to-end Feature Selection Approach for Learning Skinny Trees
  28 Oct 2023 1 repository listed
  Our optimization-based approach learns an ensemble of differentiable trees, and simultaneously performs feature selection using a grouped ℓ₀-regularizer.
• FrankenSplit: Efficient Neural Feature Compression with Shallow Variational Bottleneck Injection for Mobile Edge Computing
  21 Feb 2023 1 repository listed
  The rise of mobile AI accelerators allows latency-sensitive applications to execute lightweight Deep Neural Networks (DNNs) on the client side.
• SGCN: Exploiting Compressed-Sparse Features in Deep Graph Convolutional Network Accelerators
  25 Jan 2023 1 repository listed
  A GCN takes as input an arbitrarily structured graph and executes a series of layers which exploit the graph's structure to calculate their output features.
• Supervised Feature Compression based on Counterfactual Analysis
  17 Nov 2022 1 repository listed
  Counterfactual Explanations are becoming a de-facto standard in post-hoc interpretable machine learning.
• Efficient Feature Compression for Edge-Cloud Systems
  17 Nov 2022 1 repository listed
  Optimizing computation in an edge-cloud system is an important yet challenging problem.
• Video in 10 Bits: Few-Bit VideoQA for Efficiency and Privacy
  15 Oct 2022 1 repository listed
  Specifically, we insert a lightweight Feature Compression Module (FeatComp) into a VideoQA model which learns to extract task-specific tiny features as little as 10 bits, which are optimal for answering certain types of…
• Compressing Features for Learning with Noisy Labels
  27 Jun 2022 1 repository listed
  This decomposition provides three insights: (i) it shows that over-fitting is indeed an issue for learning with noisy labels; (ii) through an information bottleneck formulation, it explains why the proposed feature…
• Multi-Agent Collaborative Inference via DNN Decoupling: Intermediate Feature Compression and Edge Learning
  24 May 2022 1 repository listed
  In this paper, we study the multi-agent collaborative inference scenario, where a single edge server coordinates the inference of multiple UEs.
• SC2 Benchmark: Supervised Compression for Split Computing
  16 Mar 2022 1 repository listed
  With the increasing demand for deep learning models on mobile devices, splitting neural network computation between the device and a more powerful edge server has become an attractive solution.
• Context-Aware Compilation of DNN Training Pipelines across Edge and Cloud
  30 Dec 2021 1 repository listed
  Experimental results show that our system not only adapts well to, but also draws on the varying contexts, delivering a practical and efficient solution to edge-cloud model training.
• Lossy Compression for Lossless Prediction
  21 Jun 2021 1 repository listed Syntology ran 2 of 11 samples · 9 unverified
  Most data is automatically collected and only ever "seen" by algorithms.
• BottleNet++: An End-to-End Approach for Feature Compression in Device-Edge Co-Inference Systems
  31 Oct 2019 1 repository listed
  By exploiting the strong sparsity and the fault-tolerant property of the intermediate feature in a deep neural network (DNN), BottleNet++ achieves a much higher compression ratio than existing methods.
• Context-aware Deep Feature Compression for High-speed Visual Tracking
  28 Mar 2018 1 repository listed
  We propose a new context-aware correlation filter based tracking framework to achieve both high computational speed and state-of-the-art performance among real-time trackers.

Syntology lines on 7 of the papers shown; no Syntology record for the others (a paper without an arXiv id cannot be joined to the graph, and absence from the graph layer is not a recorded non-run). “Ran” means the sample executed on a synthesized fixture, not that the paper's result was reproduced. Read from the graph 2026-09-24.