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 1–50 of 96 papers

TitleStatusHype
Meissonic: Revitalizing Masked Generative Transformers for Efficient High-Resolution Text-to-Image SynthesisCode3
LLaVA-ST: A Multimodal Large Language Model for Fine-Grained Spatial-Temporal UnderstandingCode2
WidthFormer: Toward Efficient Transformer-based BEV View TransformationCode2
Video in 10 Bits: Few-Bit VideoQA for Efficiency and PrivacyCode2
EMIFF: Enhanced Multi-scale Image Feature Fusion for Vehicle-Infrastructure Cooperative 3D Object DetectionCode2
I^2VC: A Unified Framework for Intra- & Inter-frame Video CompressionCode1
Compressing Features for Learning with Noisy LabelsCode1
Learning to Manipulate Artistic ImagesCode1
Lossy Compression for Lossless PredictionCode1
Supervised Compression for Resource-Constrained Edge Computing SystemsCode1
FOOL: Addressing the Downlink Bottleneck in Satellite Computing with Neural Feature CompressionCode1
Multi-Agent Collaborative Inference via DNN Decoupling: Intermediate Feature Compression and Edge LearningCode1
FrankenSplit: Efficient Neural Feature Compression with Shallow Variational Bottleneck Injection for Mobile Edge ComputingCode1
Vector Quantization for Recommender Systems: A Review and OutlookCode1
VIMI: Vehicle-Infrastructure Multi-view Intermediate Fusion for Camera-based 3D Object DetectionCode1
Flexible Variable-Rate Image Feature Compression for Edge-Cloud SystemsCode0
BottleNet++: An End-to-End Approach for Feature Compression in Device-Edge Co-Inference SystemsCode0
End-to-end Feature Selection Approach for Learning Skinny TreesCode0
SC2 Benchmark: Supervised Compression for Split ComputingCode0
TransVFC: A Transformable Video Feature Compression Framework for MachinesCode0
Efficient Feature Compression for Edge-Cloud SystemsCode0
SGCN: Exploiting Compressed-Sparse Features in Deep Graph Convolutional Network AcceleratorsCode0
Effective Communication with Dynamic Feature CompressionCode0
Understanding Deep Representation Learning via Layerwise Feature Compression and DiscriminationCode0
Entropy Loss: An Interpretability Amplifier of 3D Object Detection Network for Intelligent DrivingCode0
Context-Aware Compilation of DNN Training Pipelines across Edge and CloudCode0
Selective Complementary Feature Fusion and Modal Feature Compression Interaction for Brain Tumor SegmentationCode0
Context-aware Deep Feature Compression for High-speed Visual TrackingCode0
Supervised Feature Compression based on Counterfactual AnalysisCode0
Feature Compression for Cloud-Edge Multimodal 3D Object Detection—0
Feature Compression for Rate Constrained Object Detection on the Edge—0
Fusion: Towards Automated ICD Coding via Feature Compression—0
Generative Map Priors for Collaborative BEV Semantic Segmentation—0
Haar Wavelet Feature Compression for Quantized Graph Convolutional Networks—0
Hierarchical Semantic Compression for Consistent Image Semantic Restoration—0
In Defense of Clip-based Video Relation Detection—0
Intermediate Deep Feature Compression: the Next Battlefield of Intelligent Sensing—0
JointRF: End-to-End Joint Optimization for Dynamic Neural Radiance Field Representation and Compression—0
Large Scale Autonomous Driving Scenarios Clustering with Self-supervised Feature Extraction—0
Connecting Compression Spaces with Transformer for Approximate Nearest Neighbor Search—0
Memory-Efficient CNN Accelerator Based on Interlayer Feature Map Compression—0
Mitigating severe over-parameterization in deep convolutional neural networks through forced feature abstraction and compression with an entropy-based heuristic—0
MotionBench: Benchmarking and Improving Fine-grained Video Motion Understanding for Vision Language Models—0
Near-Lossless Deep Feature Compression for Collaborative Intelligence—0
NeRFCodec: Neural Feature Compression Meets Neural Radiance Fields for Memory-Efficient Scene Representation—0
Reconstructing Pruned Filters using Cheap Spatial Transformations—0
PIDNet: An Efficient Network for Dynamic Pedestrian Intrusion Detection—0
Pixel-Level Matching for Video Object Segmentation using Convolutional Neural Networks—0
Privacy-Aware Multi-Device Cooperative Edge Inference with Distributed Resource Bidding—0
Revisit Visual Representation in Analytics Taxonomy: A Compression Perspective—0
Show:102550
← PrevPage 1 of 2Next →

No leaderboard results yet.