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 51–75 of 96 papers

TitleStatusHype
Semantic and Effective Communication for Remote Control Tasks with Dynamic Feature Compression—0
Attention-based Feature Compression for CNN Inference Offloading in Edge Computing—0
Supervised Feature Compression based on Counterfactual AnalysisCode0
Efficient Feature Compression for Edge-Cloud SystemsCode0
Video in 10 Bits: Few-Bit VideoQA for Efficiency and PrivacyCode2
Cross Modal Compression: Towards Human-comprehensible Semantic Compression—0
Complementary Bi-directional Feature Compression for Indoor 360° Semantic Segmentation with Self-distillation—0
Compressing Features for Learning with Noisy LabelsCode1
Multi-Agent Collaborative Inference via DNN Decoupling: Intermediate Feature Compression and Edge LearningCode1
Feature Compression for Rate Constrained Object Detection on the Edge—0
SC2 Benchmark: Supervised Compression for Split ComputingCode0
Context-Aware Compilation of DNN Training Pipelines across Edge and CloudCode0
Source Feature Compression for Object Classification in Vision-Based Underwater Robotics—0
Reconstructing Pruned Filters using Cheap Spatial Transformations—0
Video Coding for Machine: Compact Visual Representation Compression for Intelligent Collaborative Analytics—0
Memory-Efficient CNN Accelerator Based on Interlayer Feature Map Compression—0
Haar Wavelet Feature Compression for Quantized Graph Convolutional Networks—0
Communication-Computation Efficient Device-Edge Co-Inference via AutoML—0
Deep Reinforcement Learning for Wireless Resource Allocation Using Buffer State Information—0
Supervised Compression for Resource-Constrained Edge Computing SystemsCode1
Fusion: Towards Automated ICD Coding via Feature Compression—0
Connecting Compression Spaces with Transformer for Approximate Nearest Neighbor Search—0
Mitigating severe over-parameterization in deep convolutional neural networks through forced feature abstraction and compression with an entropy-based heuristic—0
Lossy Compression for Lossless PredictionCode1
Revisit Visual Representation in Analytics Taxonomy: A Compression Perspective—0
Show:102550
← PrevPage 3 of 4Next →

No leaderboard results yet.