Feature Compression

19 papers with code • 0 benchmarks • 0 datasets

Compress data for machine interpretability to perform downstream tasks, rather than for human perception.

Most implemented papers

Supervised Feature Compression based on Counterfactual Analysis

ceciliasalvatore/sfcca 17 Nov 2022

Counterfactual Explanations are becoming a de-facto standard in post-hoc interpretable machine learning.

Efficient Feature Compression for Edge-Cloud Systems

duanzhiihao/edge-cloud-rac 17 Nov 2022

Optimizing computation in an edge-cloud system is an important yet challenging problem.

SGCN: Exploiting Compressed-Sparse Features in Deep Graph Convolutional Network Accelerators

2023-MindSpore-1/ms-code-218 25 Jan 2023

A GCN takes as input an arbitrarily structured graph and executes a series of layers which exploit the graph's structure to calculate their output features.

FrankenSplit: Efficient Neural Feature Compression with Shallow Variational Bottleneck Injection for Mobile Edge Computing

rezafuru/frankensplit 21 Feb 2023

The rise of mobile AI accelerators allows latency-sensitive applications to execute lightweight Deep Neural Networks (DNNs) on the client side.

Understanding Deep Representation Learning via Layerwise Feature Compression and Discrimination

heimine/pnc_dln 6 Nov 2023

To the best of our knowledge, this is the first quantitative characterization of feature evolution in hierarchical representations of deep linear networks.

WidthFormer: Toward Efficient Transformer-based BEV View Transformation

chenhongyiyang/widthformer 8 Jan 2024

In this work, we present WidthFormer, a novel transformer-based Bird's-Eye-View (BEV) 3D detection method tailored for real-time autonomous-driving applications.

Learning to Manipulate Artistic Images

snailforce/sim-net 25 Jan 2024

Recent advancement in computer vision has significantly lowered the barriers to artistic creation.

Effective Communication with Dynamic Feature Compression

pietro-talli/tmlcn_code 29 Jan 2024

The remote wireless control of industrial systems is one of the major use cases for 5G and beyond systems: in these cases, the massive amounts of sensory information that need to be shared over the wireless medium may overload even high-capacity connections.

EMIFF: Enhanced Multi-scale Image Feature Fusion for Vehicle-Infrastructure Cooperative 3D Object Detection

bosszhe/emiff 23 Feb 2024

In autonomous driving, cooperative perception makes use of multi-view cameras from both vehicles and infrastructure, providing a global vantage point with rich semantic context of road conditions beyond a single vehicle viewpoint.

FOOL: Addressing the Downlink Bottleneck in Satellite Computing with Neural Feature Compression

no code yet • 25 Mar 2024

Further, it embeds context and leverages inter-tile dependencies to lower transfer costs with negligible overhead.