SOTAVerified

Feature Compression

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

Papers

Showing 150 of 96 papers

TitleStatusHype
Meissonic: Revitalizing Masked Generative Transformers for Efficient High-Resolution Text-to-Image SynthesisCode3
Video in 10 Bits: Few-Bit VideoQA for Efficiency and PrivacyCode2
LLaVA-ST: A Multimodal Large Language Model for Fine-Grained Spatial-Temporal UnderstandingCode2
EMIFF: Enhanced Multi-scale Image Feature Fusion for Vehicle-Infrastructure Cooperative 3D Object DetectionCode2
WidthFormer: Toward Efficient Transformer-based BEV View TransformationCode2
I^2VC: A Unified Framework for Intra- & Inter-frame Video CompressionCode1
VIMI: Vehicle-Infrastructure Multi-view Intermediate Fusion for Camera-based 3D Object DetectionCode1
Compressing Features for Learning with Noisy LabelsCode1
Vector Quantization for Recommender Systems: A Review and OutlookCode1
Lossy Compression for Lossless PredictionCode1
Learning to Manipulate Artistic ImagesCode1
FOOL: Addressing the Downlink Bottleneck in Satellite Computing with Neural Feature CompressionCode1
FrankenSplit: Efficient Neural Feature Compression with Shallow Variational Bottleneck Injection for Mobile Edge ComputingCode1
Supervised Compression for Resource-Constrained Edge Computing SystemsCode1
Multi-Agent Collaborative Inference via DNN Decoupling: Intermediate Feature Compression and Edge LearningCode1
DeepAdaIn-Net: Deep Adaptive Device-Edge Collaborative Inference for Augmented Reality0
Deep feature compression for collaborative object detection0
Joint Device-Edge Inference over Wireless Links with Pruning0
Deep Reinforcement Learning for Wireless Resource Allocation Using Buffer State Information0
Derivation of Information-Theoretically Optimal Adversarial Attacks with Applications to Robust Machine Learning0
Distilling Channels for Efficient Deep Tracking0
Distributed and Rate-Adaptive Feature Compression0
DMOFC: Discrimination Metric-Optimized Feature Compression0
Dual-Domain Homogeneous Fusion with Cross-Modal Mamba and Progressive Decoder for 3D Object Detection0
Dynamic Semantic Compression for CNN Inference in Multi-access Edge Computing: A Graph Reinforcement Learning-based Autoencoder0
Dynamic Submodular Maximization0
End-to-End Facial Deep Learning Feature Compression with Teacher-Student Enhancement0
End-to-End Learnable Multi-Scale Feature Compression for VCM0
Enhancing Drug Discovery: Autoencoder-Based Latent Space Augmentation for Improved Molecular Solubility Prediction using LatMixSol0
Feature Compression for Cloud-Edge Multimodal 3D Object Detection0
Feature Compression for Rate Constrained Object Detection on the Edge0
Fusion: Towards Automated ICD Coding via Feature Compression0
Generative Map Priors for Collaborative BEV Semantic Segmentation0
Haar Wavelet Feature Compression for Quantized Graph Convolutional Networks0
Hierarchical Semantic Compression for Consistent Image Semantic Restoration0
In Defense of Clip-based Video Relation Detection0
Intermediate Deep Feature Compression: the Next Battlefield of Intelligent Sensing0
JointRF: End-to-End Joint Optimization for Dynamic Neural Radiance Field Representation and Compression0
Large Scale Autonomous Driving Scenarios Clustering with Self-supervised Feature Extraction0
Connecting Compression Spaces with Transformer for Approximate Nearest Neighbor Search0
The Road to On-board Change Detection: A Lightweight Patch-Level Change Detection Network via Exploring the Potential of Pruning and Pooling0
Adversarial Examples Detection with Enhanced Image Difference Features based on Local Histogram Equalization0
An Efficient Large Recommendation Model: Towards a Resource-Optimal Scaling Law0
An Emerging Coding Paradigm VCM: A Scalable Coding Approach Beyond Feature and Signal0
Attention-based Feature Compression for CNN Inference Offloading in Edge Computing0
Categorical Feature Compression via Submodular Optimization0
Chromatic Learning for Sparse Datasets0
Collaborative Intelligence: Challenges and Opportunities0
Communication-Computation Efficient Device-Edge Co-Inference via AutoML0
Compact Representation for Image Classification: To Choose or to Compress?0
Show:102550
← PrevPage 1 of 2Next →

No leaderboard results yet.