Related papers: Task-driven Compression for Collision Encoding bas…

A new trend uses LLMs as dense text encoders via contrastive learning. However, since LLM embeddings predict the probability distribution of the next token, they are inherently generative and distributive, conflicting with contrastive…

Autonomous vehicles and Advanced Driving Assistance Systems (ADAS) have the potential to radically change the way we travel. Many such vehicles currently rely on segmentation and object detection algorithms to detect and track objects…

This work investigates three methods for calculating loss for autoencoder-based pretraining of image encoders: The commonly used reconstruction loss, the more recently introduced deep perceptual similarity loss, and a feature prediction…

Compression is a standard procedure for making convolutional neural networks (CNNs) adhere to some specific computing resource constraints. However, searching for a compressed architecture typically involves a series of time-consuming…

Deep learning methods have achieved impressive performance for multi-class medical image segmentation. However, they are limited in their ability to encode topological interactions among different classes (e.g., containment and exclusion).…

Split computing ($\neq$ split learning) is a promising approach to deep learning models for resource-constrained edge computing systems, where weak sensor (mobile) devices are wirelessly connected to stronger edge servers through channels…

We present a novel learning-based collision avoidance algorithm, CrowdSteer, for mobile robots operating in dense and crowded environments. Our approach is end-to-end and uses multiple perception sensors such as a 2-D lidar along with a…

Standard lossy image compression algorithms aim to preserve an image's appearance, while minimizing the number of bits needed to transmit it. However, the amount of information actually needed by a user for downstream tasks -- e.g.,…

This paper presents an autoencoder-based neural network architecture to compress histopathological images while retaining the denser and more meaningful representation of the original images. Current research into improving compression…

Compressive Sensing, which offers exact reconstruction of sparse signal from a small number of measurements, has tremendous potential for trajectory compression. In order to optimize the compression, trajectory compression algorithms need…

A novel algorithm for tunable compression to within the precision of reproduction targets, or storage, is proposed. The new algorithm is termed the `Perceptron Algorithm', which utilises simple existing concepts in a novel way, has multiple…

Learned image compression methods have attracted great research interest and exhibited superior rate-distortion performance to the best classical image compression standards of the present. The entropy model plays a key role in learned…

Face recognition technology has advanced rapidly and has been widely used in various applications. Due to the extremely huge amount of data of face images and the large computing resources required correspondingly in large-scale face…

Multi-task learning of dense prediction tasks, by sharing both the encoder and decoder, as opposed to sharing only the encoder, provides an attractive front to increase both accuracy and computational efficiency. When the tasks are similar,…

Efficient navigation in dynamic environments is crucial for autonomous robots interacting with moving agents and static obstacles. We present a novel deep reinforcement learning approach that improves robot navigation and interaction with…

This paper explores learned image compression based on traditional and learned discrete wavelet transform (DWT) architectures and learned entropy models for coding DWT subband coefficients. A learned DWT is obtained through the lifting…

Intrinsic image decomposition is the classical task of mapping image to albedo. The WHDR dataset allows methods to be evaluated by comparing predictions to human judgements ("lighter", "same as", "darker"). The best modern intrinsic image…

Well-calibrated traffic flow models are fundamental to understanding traffic phenomena and designing control strategies. Traditional calibration has been developed base on optimization methods. In this paper, we propose a novel…

Learning-based image compression was shown to achieve a competitive performance with state-of-the-art transform-based codecs. This motivated the development of new learning-based visual compression standards such as JPEG-AI. Of particular…

Soft compression is a lossless image compression method, which is committed to eliminating coding redundancy and spatial redundancy at the same time by adopting locations and shapes of codebook to encode an image from the perspective of…