92 citations · 155 across the 20 of their papers we have counts for
21 papers
Flexible Mixed Precision Quantization for Learned Image Compression
Md Adnan Faisal Hossain, Zhihao Duan, Fengqing Zhu
Despite its improvements in coding performance compared to traditional codecs, Learned Image Compression (LIC) suffers from large computational costs for storage and deployment. Mo…
CL-LoRA: Continual Low-Rank Adaptation for Rehearsal-Free Class-Incremental Learning
Jiangpeng He, Zhihao Duan, Fengqing Zhu
Class-Incremental Learning (CIL) aims to learn new classes sequentially while retaining the knowledge of previously learned classes. Recently, pre-trained models (PTMs) combined wi…
Low-Rank Adaptation of Pre-trained Vision Backbones for Energy-Efficient Image Coding for Machine
Yichi Zhang, Zhihao Duan, Yuning Huang +1
Image Coding for Machines (ICM) focuses on optimizing image compression for AI-driven analysis rather than human perception. Existing ICM frameworks often rely on separate codecs f…
Accelerating Learned Image Compression Through Modeling Neural Training Dynamics
Yichi Zhang, Zhihao Duan, Yuning Huang +1
As learned image compression (LIC) methods become increasingly computationally demanding, enhancing their training efficiency is crucial. This paper takes a step forward in acceler…
Balanced Rate-Distortion Optimization in Learned Image Compression
Yichi Zhang, Zhihao Duan, Yuning Huang +1
Learned image compression (LIC) using deep learning architectures has seen significant advancements, yet standard rate-distortion (R-D) optimization often encounters imbalanced upd…
High-Efficiency Neural Video Compression via Hierarchical Predictive Learning
Ming Lu, Zhihao Duan, Wuyang Cong +3
The enhanced Deep Hierarchical Video Compression-DHVC 2.0-has been introduced. This single-model neural video codec operates across a broad range of bitrates, delivering not only s…
On Efficient Neural Network Architectures for Image Compression
Yichi Zhang, Zhihao Duan, Fengqing Zhu
Recent advances in learning-based image compression typically come at the cost of high complexity. Designing computationally efficient architectures remains an open challenge. In t…
Learning to Classify New Foods Incrementally Via Compressed Exemplars
Justin Yang, Zhihao Duan, Jiangpeng He +1
Food image classification systems play a crucial role in health monitoring and diet tracking through image-based dietary assessment techniques. However, existing food recognition s…
Flexible Variable-Rate Image Feature Compression for Edge-Cloud Systems
Md Adnan Faisal Hossain, Zhihao Duan, Yuning Huang +1
Feature compression is a promising direction for coding for machines. Existing methods have made substantial progress, but they require designing and training separate neural netwo…
Theoretical Bound-Guided Hierarchical VAE for Neural Image Codecs
Yichi Zhang, Zhihao Duan, Yuning Huang +1
Recent studies reveal a significant theoretical link between variational autoencoders (VAEs) and rate-distortion theory, notably in utilizing VAEs to estimate the theoretical upper…
Probing Image Compression For Class-Incremental Learning
Justin Yang, Zhihao Duan, Andrew Peng +3
Image compression emerges as a pivotal tool in the efficient handling and transmission of digital images. Its ability to substantially reduce file size not only facilitates enhance…
Towards Backward-Compatible Continual Learning of Image Compression
Zhihao Duan, Ming Lu, Justin Yang +3
This paper explores the possibility of extending the capability of pre-trained neural image compressors (e.g., adapting to new data or target bitrates) without breaking backward co…
Another Way to the Top: Exploit Contextual Clustering in Learned Image Coding
Yichi Zhang, Zhihao Duan, Ming Lu +3
While convolution and self-attention are extensively used in learned image compression (LIC) for transform coding, this paper proposes an alternative called Contextual Clustering b…
Deep Hierarchical Video Compression
Ming Lu, Zhihao Duan, Fengqing Zhu +1
Recently, probabilistic predictive coding that directly models the conditional distribution of latent features across successive frames for temporal redundancy removal has yielded…
Complexity Evaluation of Parallel Execution of the RAPiD Deep-Learning Algorithm on Intel CPU
Dominic Konrad, Zhihao Duan, Mertcan Cokbas +1
Knowing how many and where are people in various indoor spaces is critical for reducing HVAC energy waste, space management, spatial analytics and in emergency scenarios. While a r…
An Improved Upper Bound on the Rate-Distortion Function of Images
Zhihao Duan, Jack Ma, Jiangpeng He +1
Recent work has shown that Variational Autoencoders (VAEs) can be used to upper-bound the information rate-distortion (R-D) function of images, i.e., the fundamental limit of lossy…
QARV: Quantization-Aware ResNet VAE for Lossy Image Compression
Zhihao Duan, Ming Lu, Jack Ma +3
This paper addresses the problem of lossy image compression, a fundamental problem in image processing and information theory that is involved in many real-world applications. We s…
Efficient Feature Compression for Edge-Cloud Systems
Zhihao Duan, Fengqing Zhu
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,…
Lossy Image Compression with Quantized Hierarchical VAEs
Zhihao Duan, Ming Lu, Zhan Ma +1
Recent research has shown a strong theoretical connection between variational autoencoders (VAEs) and the rate-distortion theory. Motivated by this, we consider the problem of loss…
Opening the Black Box of Learned Image Coders
Zhihao Duan, Ming Lu, Zhan Ma +1
End-to-end learned lossy image coders (LICs), as opposed to hand-crafted image codecs, have shown increasing superiority in terms of the rate-distortion performance. However, they…
RAPiD: Rotation-Aware People Detection in Overhead Fisheye Images
Zhihao Duan, M. Ozan Tezcan, Hayato Nakamura +2
Recent methods for people detection in overhead, fisheye images either use radially-aligned bounding boxes to represent people, assuming people always appear along image radius or…