Papers Feature Compression
“Feature Compression” 태그가 달린 논문 96편 · 필터 해제
Cross-architecture universal feature coding via distribution alignment
Feature coding has become increasingly important in scenarios where semantic representations rather than raw pixels are transmitted and stored. However, most existing methods are architecture-specific, targeting either C…
Feature Compressionimage-classificationImage ClassificationEnhancing Drug Discovery: Autoencoder-Based Latent Space Augmentation for Improved Molecular Solubility Prediction using LatMixSol
Accurate prediction of molecular solubility is a cornerstone of early-stage drug discovery, yet conventional machine learning models face significant challenges due to limited labeled data and the high-dimensional nature…
Drug DiscoveryFeature CompressionSEMFED: Semantic-Aware Resource-Efficient Federated Learning for Heterogeneous NLP Tasks
Background: Federated Learning (FL) has emerged as a promising paradigm for training machine learning models while preserving data privacy. However, applying FL to Natural Language Processing (NLP) tasks presents unique …
Feature CompressionFederated LearningUCS: A Universal Model for Curvilinear Structure Segmentation
Curvilinear structure segmentation (CSS) is vital in various domains, including medical imaging, landscape analysis, industrial surface inspection, and plant analysis. While existing methods achieve high performance with…
Feature CompressionSegmentationSemantic SegmentationTransVFC: A Transformable Video Feature Compression Framework for Machines
Nowadays, more and more video transmissions primarily aim at downstream machine vision tasks rather than humans. While widely deployed Human Visual System (HVS) oriented video coding standards like H.265/HEVC and H.264/A…
Feature CompressionSelective Complementary Feature Fusion and Modal Feature Compression Interaction for Brain Tumor Segmentation
Efficient modal feature fusion strategy is the key to achieve accurate segmentation of brain glioma. However, due to the specificity of different MRI modes, it is difficult to carry out cross-modal fusion with large diff…
Brain Tumor SegmentationFeature CompressionSpecificityTumor SegmentationTask-Oriented Feature Compression for Multimodal Understanding via Device-Edge Co-Inference
With the rapid development of large multimodal models (LMMs), multimodal understanding applications are emerging. As most LMM inference requests originate from edge devices with limited computational capabilities, the pr…
Feature CompressionImage CompressionQuestion AnsweringVisual Question AnsweringDual-Domain Homogeneous Fusion with Cross-Modal Mamba and Progressive Decoder for 3D Object Detection
Fusing LiDAR point cloud features and image features in a homogeneous BEV space has been widely adopted for 3D object detection in autonomous driving. However, such methods are limited by the excessive compression of mul…
3D Object DetectionAutonomous DrivingDecoderFeature Compression+3Hierarchical Semantic Compression for Consistent Image Semantic Restoration
The emerging semantic compression has been receiving increasing research efforts most recently, capable of achieving high fidelity restoration during compression, even at extremely low bitrates. However, existing semanti…
Feature CompressionSemantic CompressionVideo CompressionStereo Image Coding for Machines with Joint Visual Feature Compression
2D image coding for machines (ICM) has achieved great success in coding efficiency, while less effort has been devoted to stereo image fields. To promote the efficiency of stereo image compression (SIC) and intelligent a…
Feature CompressionImage CompressionAn Efficient Large Recommendation Model: Towards a Resource-Optimal Scaling Law
The pursuit of scaling up recommendation models confronts intrinsic tensions between expanding model capacity and preserving computational tractability. While prior studies have explored scaling laws for recommendation s…
Feature CompressionGPURecommendation SystemsLLaVA-ST: A Multimodal Large Language Model for Fine-Grained Spatial-Temporal Understanding
Recent advancements in multimodal large language models (MLLMs) have shown promising results, yet existing approaches struggle to effectively handle both temporal and spatial localization simultaneously. This challenge s…
Feature CompressionLanguage ModelingLanguage ModellingLarge Language Model+3MotionBench: Benchmarking and Improving Fine-grained Video Motion Understanding for Vision Language Models
In recent years, vision language models (VLMs) have made significant advancements in video understanding. However, a crucial capability - fine-grained motion comprehension - remains under-explored in current benchmarks. …
BenchmarkingFeature CompressionVideo UnderstandingGenerative Map Priors for Collaborative BEV Semantic Segmentation
Collaborative perception aims to address the constraint of single-agent perception by exchanging information among multiple agents. Previous works primarily focus on collaborative object detection, exploring compress…
Feature Compressionobject-detectionObject DetectionSemantic SegmentationPrivacy-Aware Multi-Device Cooperative Edge Inference with Distributed Resource Bidding
Mobile edge computing (MEC) has empowered mobile devices (MDs) in supporting artificial intelligence (AI) applications through collaborative efforts with proximal MEC servers. Unfortunately, despite the great promise of …
Edge-computingFeature CompressionPrivacy PreservingStructurally Consistent MRI Colorization using Cross-modal Fusion Learning
Medical image colorization can greatly enhance the interpretability of the underlying imaging modality and provide insights into human anatomy. The objective of medical image colorization is to transfer a diverse spectru…
AnatomyColorizationFeature CompressionImage ColorizationSpikeBottleNet: Spike-Driven Feature Compression Architecture for Edge-Cloud Co-Inference
Edge-cloud co-inference enables efficient deep neural network (DNN) deployment by splitting the architecture between an edge device and cloud server, crucial for resource-constraint edge devices. This approach requires b…
DecoderFeature CompressionMeissonic: Revitalizing Masked Generative Transformers for Efficient High-Resolution Text-to-Image Synthesis
We present Meissonic, which elevates non-autoregressive masked image modeling (MIM) text-to-image to a level comparable with state-of-the-art diffusion models like SDXL. By incorporating a comprehensive suite of architec…
Feature CompressionImage GenerationToward Scalable Image Feature Compression: A Content-Adaptive and Diffusion-Based Approach
Traditional image codecs emphasize signal fidelity and human perception, often at the expense of machine vision tasks. Deep learning methods have demonstrated promising coding performance by utilizing rich semantic embed…
Data CompressionFacial Landmark DetectionFeature CompressionImage Compression+4Distilling Channels for Efficient Deep Tracking
Deep trackers have proven success in visual tracking. Typically, these trackers employ optimally pre-trained deep networks to represent all diverse objects with multi-channel features from some fixed layers. The deep net…
Feature CompressionVisual Tracking