Papers Feature Compression
“Feature Compression” 태그가 달린 논문 96편 · 필터 해제
Understanding Deep Representation Learning via Layerwise Feature Compression and Discrimination
Over the past decade, deep learning has proven to be a highly effective tool for learning meaningful features from raw data. However, it remains an open question how deep networks perform hierarchical feature learning ac…
Feature CompressionMulti-class ClassificationRepresentation LearningTransfer LearningEnd-to-end Feature Selection Approach for Learning Skinny Trees
We propose a new optimization-based approach for feature selection in tree ensembles, an important problem in statistics and machine learning. Popular tree ensemble toolkits e.g., Gradient Boosted Trees and Random Forest…
Ensemble LearningFeature CompressionFeature Importancefeature selection+1The Road to On-board Change Detection: A Lightweight Patch-Level Change Detection Network via Exploring the Potential of Pruning and Pooling
Existing satellite remote sensing change detection (CD) methods often crop original large-scale bi-temporal image pairs into small patch pairs and then use pixel-level CD methods to fairly process all the patch pairs. Ho…
Change DetectionFeature CompressionDeepAdaIn-Net: Deep Adaptive Device-Edge Collaborative Inference for Augmented Reality
The object inference for augmented reality (AR) requires a precise object localization within user's physical environment and the adaptability to dynamic communication conditions. Deep learning (DL) is advantageous in ca…
Collaborative InferenceFeature CompressionObjectObject LocalizationIn Defense of Clip-based Video Relation Detection
Video Visual Relation Detection (VidVRD) aims to detect visual relationship triplets in videos using spatial bounding boxes and temporal boundaries. Existing VidVRD methods can be broadly categorized into bottom-up and t…
Feature CompressionObject TrackingRelationVideo Visual Relation DetectionEnd-to-End Learnable Multi-Scale Feature Compression for VCM
The proliferation of deep learning-based machine vision applications has given rise to a new type of compression, so called video coding for machine (VCM). VCM differs from traditional video coding in that it is optimize…
Feature Compressionobject-detectionObject DetectionAdversarial Examples Detection with Enhanced Image Difference Features based on Local Histogram Equalization
Deep Neural Networks (DNNs) have recently made significant progress in many fields. However, studies have shown that DNNs are vulnerable to adversarial examples, where imperceptible perturbations can greatly mislead DNNs…
Feature CompressionVIMI: Vehicle-Infrastructure Multi-view Intermediate Fusion for Camera-based 3D Object Detection
In autonomous driving, Vehicle-Infrastructure Cooperative 3D Object Detection (VIC3D) makes use of multi-view cameras from both vehicles and traffic infrastructure, providing a global vantage point with rich semantic con…
3D Object DetectionAutonomous DrivingFeature Compressionobject-detection+1FrankenSplit: Efficient Neural Feature Compression with Shallow Variational Bottleneck Injection for Mobile Edge Computing
The rise of mobile AI accelerators allows latency-sensitive applications to execute lightweight Deep Neural Networks (DNNs) on the client side. However, critical applications require powerful models that edge devices can…
Data CompressionEdge-computingFeature CompressionImage Classification+3SGCN: Exploiting Compressed-Sparse Features in Deep Graph Convolutional Network Accelerators
Graph convolutional networks (GCNs) are becoming increasingly popular as they overcome the limited applicability of prior neural networks. A GCN takes as input an arbitrarily structured graph and executes a series of lay…
Feature CompressionSemantic and Effective Communication for Remote Control Tasks with Dynamic Feature Compression
The coordination of robotic swarms and the remote wireless control of industrial systems are among the major use cases for 5G and beyond systems: in these cases, the massive amounts of sensory information that needs to b…
Deep Reinforcement LearningFeature CompressionQuantizationAttention-based Feature Compression for CNN Inference Offloading in Edge Computing
This paper studies the computational offloading of CNN inference in device-edge co-inference systems. Inspired by the emerging paradigm semantic communication, we propose a novel autoencoder-based CNN architecture (AECNN…
DecoderEdge-computingFeature CompressionSemantic CommunicationSupervised Feature Compression based on Counterfactual Analysis
Counterfactual Explanations are becoming a de-facto standard in post-hoc interpretable machine learning. For a given classifier and an instance classified in an undesired class, its counterfactual explanation corresponds…
counterfactualCounterfactual ExplanationFeature CompressionInterpretable Machine LearningEfficient Feature Compression for Edge-Cloud Systems
Optimizing computation in an edge-cloud system is an important yet challenging problem. In this paper, we consider a three-way trade-off between bit rate, classification accuracy, and encoding complexity in an edge-cloud…
ClassificationFeature Compressionimage-classificationImage ClassificationVideo in 10 Bits: Few-Bit VideoQA for Efficiency and Privacy
In Video Question Answering (VideoQA), answering general questions about a video requires its visual information. Yet, video often contains redundant information irrelevant to the VideoQA task. For example, if the task i…
Feature CompressionQuestion AnsweringVideo Question AnsweringCross Modal Compression: Towards Human-comprehensible Semantic Compression
Traditional image/video compression aims to reduce the transmission/storage cost with signal fidelity as high as possible. However, with the increasing demand for machine analysis and semantic monitoring in recent years,…
Feature CompressionSemantic CompressionVideo CompressionComplementary Bi-directional Feature Compression for Indoor 360° Semantic Segmentation with Self-distillation
Recently, horizontal representation-based panoramic semantic segmentation approaches outperform projection-based solutions, because the distortions can be effectively removed by compressing the spherical data in the vert…
Feature CompressionSemantic SegmentationCompressing Features for Learning with Noisy Labels
Supervised learning can be viewed as distilling relevant information from input data into feature representations. This process becomes difficult when supervision is noisy as the distilled information might not be releva…
Feature CompressionFeature ImportanceImage ClassificationInductive Bias+1Multi-Agent Collaborative Inference via DNN Decoupling: Intermediate Feature Compression and Edge Learning
Recently, deploying deep neural network (DNN) models via collaborative inference, which splits a pre-trained model into two parts and executes them on user equipment (UE) and edge server respectively, becomes attractive.…
Collaborative InferenceCPUFeature CompressionFeature Compression for Rate Constrained Object Detection on the Edge
Recent advances in computer vision has led to a growth of interest in deploying visual analytics model on mobile devices. However, most mobile devices have limited computing power, which prohibits them from running large…
CPUFeature CompressionImage Compressionobject-detection+1