Related papers: Balanced Rate-Distortion Optimization in Learned I…

The joint optimization of the reconstruction and classification error is a hard non convex problem, especially when a non linear mapping is utilized. In order to overcome this obstacle, a novel optimization strategy is proposed, in which a…

In this work we propose a method for optimizing the lossy compression for a network of diverse reconstruction systems. We focus on adapting a standard image compression method to a set of candidate displays, presenting the decompressed…

Neural video compression (NVC) has demonstrated superior compression efficiency, yet effective rate control remains a significant challenge due to complex temporal dependencies. Existing rate control schemes typically leverage frame content…

Learned Image Compression (LIC) gradually became more and more famous in these years. The hyperprior-module-based LIC models have achieved remarkable rate-distortion performance. However, the memory cost of these LIC models is too large to…

Learning-to-optimize (L2O) is an emerging research area in large-scale optimization with applications in data science. Recently, researchers have proposed a novel L2O framework called learned mirror descent (LMD), based on the classical…

Neural Video Compression (NVC) has achieved remarkable performance in recent years. However, precise rate control remains a challenge due to the inherent limitations of learning-based codecs. To solve this issue, we propose a dynamic video…

We develop a Learning Direct Optimization (LiDO) method for the refinement of a latent variable model that describes input image x. Our goal is to explain a single image x with an interpretable 3D computer graphics model having scene graph…

We study first-order optimization algorithms under the constraint that the descent direction is quantized using a pre-specified budget of $R$-bits per dimension, where $R \in (0 ,\infty)$. We propose computationally efficient optimization…

Data-parallel SGD is the de facto algorithm for distributed optimization, especially for large scale machine learning. Despite its merits, communication bottleneck is one of its persistent issues. Most compression schemes to alleviate this…

In rate-distortion (RD) problems one seeks reduced representations of a source that meet a target distortion constraint. Such optimal representations undergo topological transitions at some critical rate values, when their cardinality or…

Existing learning methods for LiDAR-based applications use 3D points scanned under a pre-determined beam configuration, e.g., the elevation angles of beams are often evenly distributed. Those fixed configurations are task-agnostic, so…

A rekindled the interest in auto-encoder algorithms has been spurred by recent work on deep learning. Current efforts have been directed towards effective training of auto-encoder architectures with a large number of coding units. Here, we…

Learned image compression codecs have recently achieved impressive compression performances surpassing the most efficient image coding architectures. However, most approaches are trained to minimize rate and distortion which often leads to…

In the past years, learned image compression (LIC) has achieved remarkable performance. The recent LIC methods outperform VVC in both PSNR and MS-SSIM. However, the low bit-rate reconstructions of LIC suffer from artifacts such as blurring,…

Due to the substantial computational cost, training state-of-the-art deep neural networks for large-scale datasets often requires distributed training using multiple computation workers. However, by nature, workers need to frequently…

Decentralized optimization and communication compression have exhibited their great potential in accelerating distributed machine learning by mitigating the communication bottleneck in practice. While existing decentralized algorithms with…

Recently, learned image compression schemes have achieved remarkable improvements in image fidelity (e.g., PSNR and MS-SSIM) compared to conventional hybrid image coding ones due to their high-efficiency non-linear transform, end-to-end…

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…

Learning-enabled control systems increasingly rely on multiple sensing modalities (e.g., vision, audio, language, etc.) for perception and decision support. A key challenge is that multi-modal sensor training dynamics are often imbalanced:…

Many information systems employ lossy compression as a crucial intermediate stage among other processing components. While the important distortion is defined by the system's input and output signals, the compression usually ignores the…