Papers Feature Compression

SC2 Benchmark: Supervised Compression for Split Computing

With the increasing demand for deep learning models on mobile devices, splitting neural network computation between the device and a more powerful edge server has become an attractive solution. However, existing split co…

Context-Aware Compilation of DNN Training Pipelines across Edge and Cloud

Empowered by machine learning, edge devices including smartphones, wearable, and IoT devices have become growingly intelligent, raising conflicts with the limited resource. On-device model personalization is particularly…

Source Feature Compression for Object Classification in Vision-Based Underwater Robotics

New efficient source feature compression solutions are proposed based on a two-stage Walsh-Hadamard Transform (WHT) for Convolutional Neural Network (CNN)-based object classification in underwater robotics. The object im…

Reconstructing Pruned Filters using Cheap Spatial Transformations

We present an efficient alternative to the convolutional layer using cheap spatial transformations. This construction exploits an inherent spatial redundancy of the learned convolutional filters to enable a much greater …

Video Coding for Machine: Compact Visual Representation Compression for Intelligent Collaborative Analytics

Video Coding for Machines (VCM) is committed to bridging to an extent separate research tracks of video/image compression and feature compression, and attempts to optimize compactness and efficiency jointly from a unifie…

Memory-Efficient CNN Accelerator Based on Interlayer Feature Map Compression

Existing deep convolutional neural networks (CNNs) generate massive interlayer feature data during network inference. To maintain real-time processing in embedded systems, large on-chip memory is required to buffer the i…

Haar Wavelet Feature Compression for Quantized Graph Convolutional Networks

Graph Convolutional Networks (GCNs) are widely used in a variety of applications, and can be seen as an unstructured version of standard Convolutional Neural Networks (CNNs). As in CNNs, the computational cost of GCNs fo…

Communication-Computation Efficient Device-Edge Co-Inference via AutoML

Device-edge co-inference, which partitions a deep neural network between a resource-constrained mobile device and an edge server, recently emerges as a promising paradigm to support intelligent mobile applications. To ac…

Deep Reinforcement Learning for Wireless Resource Allocation Using Buffer State Information

As the number of user equipments (UEs) with various data rate and latency requirements increases in wireless networks, the resource allocation problem for orthogonal frequency-division multiple access (OFDMA) becomes cha…

Supervised Compression for Resource-Constrained Edge Computing Systems

There has been much interest in deploying deep learning algorithms on low-powered devices, including smartphones, drones, and medical sensors. However, full-scale deep neural networks are often too resource-intensive in …

Fusion: Towards Automated ICD Coding via Feature Compression

Connecting Compression Spaces with Transformer for Approximate Nearest Neighbor Search

We propose a generic feature compression method for Approximate Nearest Neighbor Search (ANNS) problems, which speeds up existing ANNS methods in a plug-and-play manner. Specifically, based on transformer, we propose a n…

Mitigating severe over-parameterization in deep convolutional neural networks through forced feature abstraction and compression with an entropy-based heuristic

Convolutional Neural Networks (CNNs) such as ResNet-50, DenseNet-40 and ResNeXt-56 are severely over-parameterized, necessitating a consequent increase in the computational resources required for model training which sca…

Lossy Compression for Lossless Prediction

Most data is automatically collected and only ever "seen" by algorithms. Yet, data compressors preserve perceptual fidelity rather than just the information needed by algorithms performing downstream tasks. In this paper…

Revisit Visual Representation in Analytics Taxonomy: A Compression Perspective

Visual analytics have played an increasingly critical role in the Internet of Things, where massive visual signals have to be compressed and fed into machines. But facing such big data and constrained bandwidth capacity,…

Selective Feature Compression for Efficient Activity Recognition Inference

Most action recognition solutions rely on dense sampling to precisely cover the informative temporal clip. Extensively searching temporal region is expensive for a real-world application. In this work, we focus on improv…

Large Scale Autonomous Driving Scenarios Clustering with Self-supervised Feature Extraction

The clustering of autonomous driving scenario data can substantially benefit the autonomous driving validation and simulation systems by improving the simulation tests' completeness and fidelity. This article proposes a …

Collaborative Intelligence: Challenges and Opportunities

This paper presents an overview of the emerging area of collaborative intelligence (CI). Our goal is to raise awareness in the signal processing community of the challenges and opportunities in this area of growing impor…

Dynamic Submodular Maximization

One of the basic primitives in the class of submodular optimization problems is the submodular maximization under a cardinality constraint. Here we are given a ground set $V$ that is endowed with a monotone submodular fu…

PIDNet: An Efficient Network for Dynamic Pedestrian Intrusion Detection

Vision-based dynamic pedestrian intrusion detection (PID), judging whether pedestrians intrude an area-of-interest (AoI) by a moving camera, is an important task in mobile surveillance. The dynamically changing AoIs and …