Related papers: TACTIC: Joint Rate-Distortion-Accuracy Optimisatio…
Despite demonstrating superior rate-distortion (RD) performance, learning-based image compression (LIC) algorithms have been found to be vulnerable to malicious perturbations in recent studies. However, the adversarial attacks considered in…
With the emergence of diverse and massive data in the upcoming sixth-generation (6G) networks, the task-agnostic semantic communication system is regarded to provide robust intelligent services. In this paper, we propose a task-agnostic…
Image compression is a fundamental research field and many well-known compression standards have been developed for many decades. Recently, learned compression methods exhibit a fast development trend with promising results. However, there…
Semantic communications are expected to accomplish various semantic tasks with relatively less spectrum resource by exploiting the semantic feature of source data. To simultaneously serve both the data transmission and semantic tasks, joint…
This paper introduces ROI-Packing, an efficient image compression method tailored specifically for machine vision. By prioritizing regions of interest (ROI) critical to end-task accuracy and packing them efficiently while discarding less…
Token compression aims to speed up large-scale vision transformers (e.g. ViTs) by pruning (dropping) or merging tokens. It is an important but challenging task. Although recent advanced approaches achieved great success, they need to…
Network traffic analysis increasingly relies on feature-based representations to support monitoring and security in the presence of pervasive encryption. Although features are more compact than raw packet traces, their storage has become a…
While recent neural codecs achieve strong performance at low bitrates when optimized for perceptual quality, their effectiveness deteriorates significantly under ultra-low bitrate conditions. To mitigate this, generative compression methods…
Accurate and efficient discrete video tokenization is essential for long video sequences processing. Yet, the inherent complexity and variable information density of videos present a significant bottleneck for current tokenizers, which…
This paper studies the computational offloading of video action recognition in edge computing. To achieve effective semantic information extraction and compression, following semantic communication we propose a novel spatiotemporal…
In many learning situations, resources at inference time are significantly more constrained than resources at training time. This paper studies a general paradigm, called Differentiable ARchitecture Compression (DARC), that combines model…
Point cloud compression methods jointly optimize bitrates and reconstruction distortion. However, balancing compression ratio and reconstruction quality is difficult because low-frequency and high-frequency components contribute differently…
Adapting large pretrained models to diverse tasks is now routine, yet the two dominant strategies of parameter-efficient fine-tuning (PEFT) and low-rank compression are typically composed in sequence. This decoupled practice first…
Neural audio codecs, leveraging quantization algorithms, have significantly impacted various speech/audio tasks. While high-fidelity reconstruction is paramount for human perception, audio coding for machines (ACoM) prioritizes efficient…
With the help of powerful generative models, Semantic Image Compression (SIC) has achieved impressive performance at ultra-low bitrate. However, due to coarse-grained visual-semantic alignment and inherent randomness, the reliability of SIC…
In this paper, we propose the problem of collaborative perception, where robots can combine their local observations with those of neighboring agents in a learnable way to improve accuracy on a perception task. Unlike existing work in…
Autoencoder-based image codecs achieve state-of-the-art compression performance but often incur high computational complexity, particularly at decoding time. This work introduces a low-complexity learned image compression framework based on…
Recent advancements in deep learning-based image compression are notable. However, prevalent schemes that employ a serial context-adaptive entropy model to enhance rate-distortion (R-D) performance are markedly slow. Furthermore, the…
Decoding remote sensing images to achieve high perceptual quality, particularly at low bitrates, remains a significant challenge. To address this problem, we propose the invertible neural network-based remote sensing image compression…
Data efficiency, despite being an attractive characteristic, is often challenging to measure and optimize for in task-oriented semantic parsing; unlike exact match, it can require both model- and domain-specific setups, which have,…