Papers with Code 아카이브
Feature Compression
태스크의 하위 분류와 논문·코드·평가·기법·데이터셋을 탐색하세요.
- 하위 태스크
- 0
- 평가표
- 0
- 보존된 평가 기록
- 0
Compress data for machine interpretability to perform downstream tasks, rather than for human perception.
논문
이 태스크와 하위 분야의 관련 논문입니다. 실제 성능 비교는 평가 결과에서 확인하세요.
Enhancing Drug Discovery: Autoencoder-Based Latent Space Augmentation for Improved Molecular Solubility Prediction using LatMixSol
SEMFED: Semantic-Aware Resource-Efficient Federated Learning for Heterogeneous NLP Tasks
UCS: A Universal Model for Curvilinear Structure Segmentation
TransVFC: A Transformable Video Feature Compression Framework for Machines
Selective Complementary Feature Fusion and Modal Feature Compression Interaction for Brain Tumor Segmentation
Task-Oriented Feature Compression for Multimodal Understanding via Device-Edge Co-Inference
Dual-Domain Homogeneous Fusion with Cross-Modal Mamba and Progressive Decoder for 3D Object Detection
Hierarchical Semantic Compression for Consistent Image Semantic Restoration
Stereo Image Coding for Machines with Joint Visual Feature Compression
An Efficient Large Recommendation Model: Towards a Resource-Optimal Scaling Law
LLaVA-ST: A Multimodal Large Language Model for Fine-Grained Spatial-Temporal Understanding
MotionBench: Benchmarking and Improving Fine-grained Video Motion Understanding for Vision Language Models
Privacy-Aware Multi-Device Cooperative Edge Inference with Distributed Resource Bidding
Structurally Consistent MRI Colorization using Cross-modal Fusion Learning
SpikeBottleNet: Spike-Driven Feature Compression Architecture for Edge-Cloud Co-Inference
Meissonic: Revitalizing Masked Generative Transformers for Efficient High-Resolution Text-to-Image Synthesis
Toward Scalable Image Feature Compression: A Content-Adaptive and Diffusion-Based Approach
Distilling Channels for Efficient Deep Tracking
Feature Compression for Cloud-Edge Multimodal 3D Object Detection
Entropy Loss: An Interpretability Amplifier of 3D Object Detection Network for Intelligent Driving
Towards unlocking the mystery of adversarial fragility of neural networks
Texture-guided Coding for Deep Features
I$^2$VC: A Unified Framework for Intra- & Inter-frame Video Compression
JointRF: End-to-End Joint Optimization for Dynamic Neural Radiance Field Representation and Compression
Compressive Feature Selection for Remote Visual Multi-Task Inference
DMOFC: Discrimination Metric-Optimized Feature Compression
Vector Quantization for Recommender Systems: A Review and Outlook
Distributed and Rate-Adaptive Feature Compression
NeRFCodec: Neural Feature Compression Meets Neural Radiance Fields for Memory-Efficient Scene Representation
Flexible Variable-Rate Image Feature Compression for Edge-Cloud Systems
FOOL: Addressing the Downlink Bottleneck in Satellite Computing with Neural Feature Compression
The Geometric Structure of Topic Models
EMIFF: Enhanced Multi-scale Image Feature Fusion for Vehicle-Infrastructure Cooperative 3D Object Detection
Effective Communication with Dynamic Feature Compression
Learning to Manipulate Artistic Images
출처: Papers with Code · CC BY-SA 4.0. 아카이브 자료와 새로 수집한 논문은 별도로 관리합니다.