SOTAVerified

Feature Compression

Compress data for machine interpretability to perform downstream tasks, rather than for human perception.

Papers

Recently AddedMost HypedMost ActiveNeeds VerificationMost Verified

Showing 51–96 of 96 papers

TitleStatusHype
Selective Feature Compression for Efficient Activity Recognition Inference—0
Semantic and Effective Communication for Remote Control Tasks with Dynamic Feature Compression—0
SEMFED: Semantic-Aware Resource-Efficient Federated Learning for Heterogeneous NLP Tasks—0
Source Feature Compression for Object Classification in Vision-Based Underwater Robotics—0
SpikeBottleNet: Spike-Driven Feature Compression Architecture for Edge-Cloud Co-Inference—0
Stereo Image Coding for Machines with Joint Visual Feature Compression—0
Structurally Consistent MRI Colorization using Cross-modal Fusion Learning—0
Task-Oriented Feature Compression for Multimodal Understanding via Device-Edge Co-Inference—0
Texture-guided Coding for Deep Features—0
The Geometric Structure of Topic Models—0
Trust but Verify: An Information-Theoretic Explanation for the Adversarial Fragility of Machine Learning Systems, and a General Defense against Adversarial Attacks—0
Toward Scalable Image Feature Compression: A Content-Adaptive and Diffusion-Based Approach—0
Towards unlocking the mystery of adversarial fragility of neural networks—0
UCS: A Universal Model for Curvilinear Structure Segmentation—0
Vertical Federated Image Segmentation—0
Video Coding for Machine: Compact Visual Representation Compression for Intelligent Collaborative Analytics—0
Video Coding for Machines: A Paradigm of Collaborative Compression and Intelligent Analytics—0
The Road to On-board Change Detection: A Lightweight Patch-Level Change Detection Network via Exploring the Potential of Pruning and Pooling—0
Adversarial Examples Detection with Enhanced Image Difference Features based on Local Histogram Equalization—0
An Efficient Large Recommendation Model: Towards a Resource-Optimal Scaling Law—0
An Emerging Coding Paradigm VCM: A Scalable Coding Approach Beyond Feature and Signal—0
Attention-based Feature Compression for CNN Inference Offloading in Edge Computing—0
Categorical Feature Compression via Submodular Optimization—0
Chromatic Learning for Sparse Datasets—0
Collaborative Intelligence: Challenges and Opportunities—0
Communication-Computation Efficient Device-Edge Co-Inference via AutoML—0
Compact Representation for Image Classification: To Choose or to Compress?—0
Comparing of Term Clustering Frameworks for Modular Ontology Learning—0
Complementary Bi-directional Feature Compression for Indoor 360° Semantic Segmentation with Self-distillation—0
Compressive Feature Selection for Remote Visual Multi-Task Inference—0
Cross-architecture universal feature coding via distribution alignment—0
Cross Modal Compression: Towards Human-comprehensible Semantic Compression—0
DeepAdaIn-Net: Deep Adaptive Device-Edge Collaborative Inference for Augmented Reality—0
Deep feature compression for collaborative object detection—0
Joint Device-Edge Inference over Wireless Links with Pruning—0
Deep Reinforcement Learning for Wireless Resource Allocation Using Buffer State Information—0
Derivation of Information-Theoretically Optimal Adversarial Attacks with Applications to Robust Machine Learning—0
Distilling Channels for Efficient Deep Tracking—0
Distributed and Rate-Adaptive Feature Compression—0
DMOFC: Discrimination Metric-Optimized Feature Compression—0
Dual-Domain Homogeneous Fusion with Cross-Modal Mamba and Progressive Decoder for 3D Object Detection—0
Dynamic Semantic Compression for CNN Inference in Multi-access Edge Computing: A Graph Reinforcement Learning-based Autoencoder—0
Dynamic Submodular Maximization—0
End-to-End Facial Deep Learning Feature Compression with Teacher-Student Enhancement—0
End-to-End Learnable Multi-Scale Feature Compression for VCM—0
Enhancing Drug Discovery: Autoencoder-Based Latent Space Augmentation for Improved Molecular Solubility Prediction using LatMixSol—0
Show:102550
← PrevPage 2 of 2Next →

No leaderboard results yet.