Browse State-of-the-Art › Feature Compression
Feature Compression
28 papers with code · 0 benchmarks · 0 datasets archive 2025-07-28
Compress data for machine interpretability to perform downstream tasks, rather than for human perception.
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
Papers archive 2025-07-28
archive papers tagged: 96 · with a code link: 28 · where Syntology ran a sample: 7 (6 with a run with no instrument failure, 1 where every run was a failure of Syntology's instrument) Syntology
Show: all tagged papersonly where code ran (7 of 96 tagged: 6 with a run with no instrument failure, 1 where every run was a failure of Syntology's instrument)
Page 1 of 1: papers 1 to 96 of 96, in archive order: by repositories listed in the archive (most first), then newest first, not by stars (the archive holds no stars, so PwC's “Social” and “Latest” sorts cannot be reproduced). Papers that list no repository come after every paper that lists one.
Papers without a page here are shown as plain text. A Syntology line reads “N ran (of which C constructed an object rather than computing a result; K with no instrument failure: H honoured, V violated, P with no contract checked; I where Syntology's instrument failed) · U unverified”; the figure “where Syntology's instrument failed” counts failures of Syntology's instrument, not of the code. When the archive marks a repository official for the paper, the line starts with that repository's state (the archive's flag, not a verdict on who wrote the code); hover it for the repositories the samples that ran came from. The first sentence of the abstract is shown for the first 30 papers; every abstract is on its paper's page.
-
30 Mar 2024 2 repositories listedBy 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.
-
23 Feb 2024 2 repositories listedIn 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…
-
20 Mar 2023 2 repositories listed Syntology official (archive's flag): 2 ran · 2 ran (of which 0 constructed an object rather than computing a result; 2 with no instrument failure: 0 honoured, 0 violated, 2 with no contract checked; 0 where Syntology's instrument failed) · 0 unverified (of 2 harvested samples)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…
-
21 Aug 2021 2 repositories listed Syntology official (archive's flag): 2 ran · 11 ran (of which 0 constructed an object rather than computing a result; 10 with no instrument failure: 0 honoured, 0 violated, 10 with no contract checked; 1 where Syntology's instrument failed) · 6 unverified (of 17 harvested samples) · 1 pointer-only (licence)There has been much interest in deploying deep learning algorithms on low-powered devices, including smartphones, drones, and medical sensors.
-
31 Mar 2025 1 repository listedThen, the codec implements perception-guided conditional coding to minimize spatial redundancy and help the reconstructed features align with downstream machine perception.
-
14 Jan 2025 1 repository listed Syntology official (archive's flag): 3 ran · 3 ran (of which 2 constructed an object rather than computing a result; 2 with no instrument failure: 0 honoured, 0 violated, 2 with no contract checked; 1 where Syntology's instrument failed) · 4 unverified (of 7 harvested samples)Furthermore, we propose ST-Align dataset with 4.
-
10 Oct 2024 1 repository listed Syntology official (archive's flag): 4 ran · 4 ran (of which 1 constructed an object rather than computing a result; 1 with no instrument failure: 0 honoured, 0 violated, 1 with no contract checked; 3 where Syntology's instrument failed) · 8 unverified (of 12 harvested samples)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.
-
1 Sep 2024 1 repository listedEntropy Loss is formulated based on the functionality of feature compression networks within the perception model.
-
23 May 2024 1 repository listedPrevious 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.
-
6 May 2024 1 repository listedFinally, 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…
-
25 Mar 2024 1 repository listedFurther, it embeds context and leverages inter-tile dependencies to lower transfer costs with negligible overhead.
-
29 Jan 2024 1 repository listedThe 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…
-
25 Jan 2024 1 repository listed Syntology official (archive's flag): 1 ran · 1 ran (of which 0 constructed an object rather than computing a result; 0 with no instrument failure: 0 honoured, 0 violated, 0 with no contract checked; 1 where Syntology's instrument failed) · 1 unverified (of 2 harvested samples)Recent advancement in computer vision has significantly lowered the barriers to artistic creation.
-
8 Jan 2024 1 repository listedWe 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.
-
6 Nov 2023 1 repository listed Syntology official (archive's flag): 11 ran · 11 ran (of which 0 constructed an object rather than computing a result; 11 with no instrument failure: 0 honoured, 0 violated, 11 with no contract checked; 0 where Syntology's instrument failed) · 6 unverified (of 17 harvested samples) · 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.
-
28 Oct 2023 1 repository listedOur optimization-based approach learns an ensemble of differentiable trees, and simultaneously performs feature selection using a grouped ℓ₀-regularizer.
-
21 Feb 2023 1 repository listedThe rise of mobile AI accelerators allows latency-sensitive applications to execute lightweight Deep Neural Networks (DNNs) on the client side.
-
25 Jan 2023 1 repository listedA 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.
-
17 Nov 2022 1 repository listedOptimizing computation in an edge-cloud system is an important yet challenging problem.
-
17 Nov 2022 1 repository listedCounterfactual Explanations are becoming a de-facto standard in post-hoc interpretable machine learning.
-
15 Oct 2022 1 repository listedSpecifically, 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…
-
27 Jun 2022 1 repository listedThis 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…
-
24 May 2022 1 repository listedIn this paper, we study the multi-agent collaborative inference scenario, where a single edge server coordinates the inference of multiple UEs.
-
16 Mar 2022 1 repository listedWith 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.
-
30 Dec 2021 1 repository listedExperimental 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.
-
21 Jun 2021 1 repository listed Syntology official (archive's flag): 9 ran · 9 ran (of which 0 constructed an object rather than computing a result; 8 with no instrument failure: 1 honoured, 0 violated, 7 with no contract checked; 1 where Syntology's instrument failed) · 2 unverified (of 11 harvested samples)Most data is automatically collected and only ever "seen" by algorithms.
-
31 Oct 2019 1 repository listedBy 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.
-
28 Mar 2018 1 repository listedWe 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.
-
Cross-architecture universal feature coding via distribution alignment15 Jun 2025 0 repositories listedFeature coding has become increasingly important in scenarios where semantic representations rather than raw pixels are transmitted and stored.
-
Enhancing Drug Discovery: Autoencoder-Based Latent Space Augmentation for Improved Molecular Solubility Prediction using LatMixSol30 May 2025 0 repositories listedAccurate prediction of molecular solubility is a cornerstone of early-stage drug discovery, yet conventional machine learning models face significant challenges due to limited labeled data and the high-dimensional…
-
SEMFED: Semantic-Aware Resource-Efficient Federated Learning for Heterogeneous NLP Tasks26 May 2025 0 repositories listed
-
UCS: A Universal Model for Curvilinear Structure Segmentation5 Apr 2025 0 repositories listed
-
Selective Complementary Feature Fusion and Modal Feature Compression Interaction for Brain Tumor Segmentation20 Mar 2025 0 repositories listed
-
Task-Oriented Feature Compression for Multimodal Understanding via Device-Edge Co-Inference17 Mar 2025 0 repositories listed
-
Dual-Domain Homogeneous Fusion with Cross-Modal Mamba and Progressive Decoder for 3D Object Detection12 Mar 2025 0 repositories listed
-
Hierarchical Semantic Compression for Consistent Image Semantic Restoration24 Feb 2025 0 repositories listed
-
Stereo Image Coding for Machines with Joint Visual Feature Compression20 Feb 2025 0 repositories listed
-
An Efficient Large Recommendation Model: Towards a Resource-Optimal Scaling Law14 Feb 2025 0 repositories listed
-
MotionBench: Benchmarking and Improving Fine-grained Video Motion Understanding for Vision Language Models6 Jan 2025 0 repositories listed
-
Generative Map Priors for Collaborative BEV Semantic Segmentation1 Jan 2025 0 repositories listed
-
Privacy-Aware Multi-Device Cooperative Edge Inference with Distributed Resource Bidding30 Dec 2024 0 repositories listed
-
Structurally Consistent MRI Colorization using Cross-modal Fusion Learning12 Dec 2024 0 repositories listed
-
SpikeBottleNet: Spike-Driven Feature Compression Architecture for Edge-Cloud Co-Inference11 Oct 2024 0 repositories listed
-
Toward Scalable Image Feature Compression: A Content-Adaptive and Diffusion-Based Approach8 Oct 2024 0 repositories listed
-
Distilling Channels for Efficient Deep Tracking18 Sep 2024 0 repositories listed
-
Feature Compression for Cloud-Edge Multimodal 3D Object Detection6 Sep 2024 0 repositories listed
-
Towards unlocking the mystery of adversarial fragility of neural networks23 Jun 2024 0 repositories listed
-
Texture-guided Coding for Deep Features30 May 2024 0 repositories listed
-
JointRF: End-to-End Joint Optimization for Dynamic Neural Radiance Field Representation and Compression23 May 2024 0 repositories listed
-
Compressive Feature Selection for Remote Visual Multi-Task Inference15 May 2024 0 repositories listed
-
DMOFC: Discrimination Metric-Optimized Feature Compression7 May 2024 0 repositories listed
-
Distributed and Rate-Adaptive Feature Compression2 Apr 2024 0 repositories listed
-
NeRFCodec: Neural Feature Compression Meets Neural Radiance Fields for Memory-Efficient Scene Representation2 Apr 2024 0 repositories listed
-
The Geometric Structure of Topic Models6 Mar 2024 0 repositories listed
-
Dynamic Semantic Compression for CNN Inference in Multi-access Edge Computing: A Graph Reinforcement Learning-based Autoencoder19 Jan 2024 0 repositories listed
-
Vertical Federated Image Segmentation15 Jan 2024 0 repositories listed
-
The Road to On-board Change Detection: A Lightweight Patch-Level Change Detection Network via Exploring the Potential of Pruning and Pooling16 Oct 2023 0 repositories listed
-
DeepAdaIn-Net: Deep Adaptive Device-Edge Collaborative Inference for Augmented Reality22 Sep 2023 0 repositories listed
-
In Defense of Clip-based Video Relation Detection18 Jul 2023 0 repositories listed
-
End-to-End Learnable Multi-Scale Feature Compression for VCM29 Jun 2023 0 repositories listed
-
Adversarial Examples Detection with Enhanced Image Difference Features based on Local Histogram Equalization8 May 2023 0 repositories listed
-
Semantic and Effective Communication for Remote Control Tasks with Dynamic Feature Compression14 Jan 2023 0 repositories listed
-
Attention-based Feature Compression for CNN Inference Offloading in Edge Computing24 Nov 2022 0 repositories listed
-
Cross Modal Compression: Towards Human-comprehensible Semantic Compression6 Sep 2022 0 repositories listed
-
6 Jul 2022 0 repositories listed
-
Feature Compression for Rate Constrained Object Detection on the Edge15 Apr 2022 0 repositories listed
-
Source Feature Compression for Object Classification in Vision-Based Underwater Robotics28 Dec 2021 0 repositories listed
-
Reconstructing Pruned Filters using Cheap Spatial Transformations25 Oct 2021 0 repositories listed
-
Video Coding for Machine: Compact Visual Representation Compression for Intelligent Collaborative Analytics18 Oct 2021 0 repositories listed
-
Memory-Efficient CNN Accelerator Based on Interlayer Feature Map Compression12 Oct 2021 0 repositories listed
-
Haar Wavelet Feature Compression for Quantized Graph Convolutional Networks10 Oct 2021 0 repositories listed
-
Communication-Computation Efficient Device-Edge Co-Inference via AutoML30 Aug 2021 0 repositories listed
-
Deep Reinforcement Learning for Wireless Resource Allocation Using Buffer State Information27 Aug 2021 0 repositories listed
-
Fusion: Towards Automated ICD Coding via Feature Compression1 Aug 2021 0 repositories listed
-
Connecting Compression Spaces with Transformer for Approximate Nearest Neighbor Search30 Jul 2021 0 repositories listed
-
Mitigating severe over-parameterization in deep convolutional neural networks through forced feature abstraction and compression with an entropy-based heuristic27 Jun 2021 0 repositories listed
-
Revisit Visual Representation in Analytics Taxonomy: A Compression Perspective16 Jun 2021 0 repositories listed
-
Selective Feature Compression for Efficient Activity Recognition Inference1 Apr 2021 0 repositories listed
-
Large Scale Autonomous Driving Scenarios Clustering with Self-supervised Feature Extraction30 Mar 2021 0 repositories listed
-
Collaborative Intelligence: Challenges and Opportunities13 Feb 2021 0 repositories listed
-
Dynamic Submodular Maximization1 Dec 2020 0 repositories listed
-
PIDNet: An Efficient Network for Dynamic Pedestrian Intrusion Detection1 Sep 2020 0 repositories listed
-
Derivation of Information-Theoretically Optimal Adversarial Attacks with Applications to Robust Machine Learning28 Jul 2020 0 repositories listed
-
Chromatic Learning for Sparse Datasets6 Jun 2020 0 repositories listed
-
Joint Device-Edge Inference over Wireless Links with Pruning4 Mar 2020 0 repositories listed
-
End-to-End Facial Deep Learning Feature Compression with Teacher-Student Enhancement10 Feb 2020 0 repositories listed
-
Video Coding for Machines: A Paradigm of Collaborative Compression and Intelligent Analytics10 Jan 2020 0 repositories listed
-
An Emerging Coding Paradigm VCM: A Scalable Coding Approach Beyond Feature and Signal9 Jan 2020 0 repositories listed
-
Trust but Verify: An Information-Theoretic Explanation for the Adversarial Fragility of Machine Learning Systems, and a General Defense against Adversarial Attacks25 May 2019 0 repositories listed
-
Categorical Feature Compression via Submodular Optimization30 Apr 2019 0 repositories listed
-
Comparing of Term Clustering Frameworks for Modular Ontology Learning25 Jan 2019 0 repositories listed
-
Intermediate Deep Feature Compression: the Next Battlefield of Intelligent Sensing17 Sep 2018 0 repositories listed
-
Near-Lossless Deep Feature Compression for Collaborative Intelligence26 Apr 2018 0 repositories listed
-
Deep feature compression for collaborative object detection12 Feb 2018 0 repositories listed
-
17 Aug 2017 0 repositories listed
-
Compact Representation for Image Classification: To Choose or to Compress?1 Jun 2014 0 repositories listed
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; each line links to that paper's sample list. Syntology's record for this page last changed ; when this build read Syntology's graph is in the build record. For agents: get_harvested_code_for_paper(arxiv_id) lists each paper's samples; how to connect.
Report a problem or propose a change · a person checks every report against the paper or source before anything changes; decisions are listed on /corrections