Related papers: TLIC: Learned Image Compression with ROI-Weighted …
Post-training Neural Network (NN) model compression is an attractive approach for deploying large, memory-consuming models on devices with limited memory resources. In this study, we investigate the rate-distortion tradeoff for NN model…
Recent advances in computer vision has led to a growth of interest in deploying visual analytics model on mobile devices. However, most mobile devices have limited computing power, which prohibits them from running large scale visual…
Relative attribute (RA), referring to the preference over two images on the strength of a specific attribute, can enable fine-grained image-to-image translation due to its rich semantic information. Existing work based on RAs however failed…
Video compression plays a significant role in IoT devices for the efficient transport of visual data while satisfying all underlying bandwidth constraints. Deep learning-based video compression methods are rapidly replacing traditional…
The ability to find short representations, i.e. to compress data, is crucial for many intelligent systems. We present a theory of incremental compression showing that arbitrary data strings, that can be described by a set of features, can…
Image coding for machines (ICM) aims to compress images for machine analysis using recognition models rather than human vision. Hence, in ICM, it is important for the encoder to recognize and compress the information necessary for the…
Recently, DNN models for lossless image coding have surpassed their traditional counterparts in compression performance, reducing the previous lossless bit rate by about ten percent for natural color images. But even with these advances,…
Low resolution image enhancement is a classical computer vision problem. Selecting the best method to reconstruct an image to a higher resolution with the limited data available in the low-resolution image is quite a challenge. A major…
Recently, learned image compression has attracted considerable attention due to its superior performance over traditional methods. However, most existing approaches employ a single entropy model to estimate the probability distribution of…
The learned image compression (LIC) methods have already surpassed traditional techniques in compressing natural scene (NS) images. However, directly applying these methods to screen content (SC) images, which possess distinct…
Segmenting multiple objects (e.g., organs) in medical images often requires an understanding of their topology, which simultaneously quantifies the shape of the objects and their positions relative to each other. This understanding is…
Adversarial imitation learning (AIL) is a popular method that has recently achieved much success. However, the performance of AIL is still unsatisfactory on the more challenging tasks. We find that one of the major reasons is due to the low…
Autonomous vehicles are a promising solution to traffic congestion, air pollution, accidents, and wasted time and resources. However, remote driver intervention may be necessary for extreme situations to ensure safe roadside parking or…
This paper addresses the challenge of learning a local visual pattern of an object from one image, and generating images depicting objects with that pattern. Learning a localized concept and placing it on an object in a target image is a…
Masked Image Modeling (MIM) is a powerful self-supervised strategy for visual pre-training without the use of labels. MIM applies random crops to input images, processes them with an encoder, and then recovers the masked inputs with a…
We propose Deep Lossless Image Coding (DLIC), a full resolution learned lossless image compression algorithm. Our algorithm is based on a neural network combined with an entropy encoder. The neural network performs a density estimation on…
Conventional multi-view re-ranking methods usually perform asymmetrical matching between the region of interest (ROI) in the query image and the whole target image for similarity computation. Due to the inconsistency in the visual…
Computed tomography for region-of-interest (ROI) reconstruction has advantages of reducing X-ray radiation dose and using a small detector. However, standard analytic reconstruction methods suffer from severe cupping artifacts, and existing…
By optimizing the rate-distortion-realism trade-off, generative image compression approaches produce detailed, realistic images instead of the only sharp-looking reconstructions produced by rate-distortion-optimized models. In this paper,…
We extensively study how to combine Generative Adversarial Networks and learned compression to obtain a state-of-the-art generative lossy compression system. In particular, we investigate normalization layers, generator and discriminator…