Related papers: JOCA: Task-Driven Joint Optimisation of Camera Har…
Vision-centric autonomous driving has demonstrated excellent performance with economical sensors. As the fundamental step, 3D perception aims to infer 3D information from 2D images based on 3D-2D projection. This makes driving perception…
Recently, the joint design of optical systems and downstream algorithms is showing significant potential. However, existing rays-described methods are limited to optimizing geometric degradation, making it difficult to fully represent the…
We present a novel approach to perform the unsupervised domain adaptation for object detection through forward-backward cyclic (FBC) training. Recent adversarial training based domain adaptation methods have shown their effectiveness on…
Recent advances in end-to-end video compression have shown promising results owing to their unified end-to-end learning optimization. However, such generalized frameworks often lack content-specific adaptation, leading to suboptimal…
Multi-task learning solves multiple correlated tasks. However, conflicts may exist between them. In such circumstances, a single solution can rarely optimize all the tasks, leading to performance trade-offs. To arrive at a set of optimized…
Gradient-based methods are well-suited for derivative-free optimization (DFO), where finite-difference (FD) estimates are commonly used as gradient surrogates. Traditional stochastic approximation methods, such as Kiefer-Wolfowitz (KW) and…
In low-light environments, the performance of computer vision algorithms often deteriorates significantly, adversely affecting key vision tasks such as segmentation, detection, and classification. With the rapid advancement of deep…
In recent years, there has been a growing interest in combining learnable modules with numerical optimization to solve low-level vision tasks. However, most existing approaches focus on designing specialized schemes to generate…
Following the introduction of Adam, several novel adaptive optimizers for deep learning have been proposed. These optimizers typically excel in some tasks but may not outperform Adam uniformly across all tasks. In this work, we introduce…
Enhancing low-light images while maintaining natural colors is a challenging problem due to camera processing variations and limited access to photos with ground-truth lighting conditions. The latter is a crucial factor for supervised…
Active perception in vision-based robotic manipulation aims to move the camera toward more informative observation viewpoints, thereby providing high-quality perceptual inputs for downstream tasks. Most existing active perception methods…
Domain adaptive detection aims to improve the generalization of detectors on target domain. To reduce discrepancy in feature distributions between two domains, recent approaches achieve domain adaption through feature alignment in different…
We introduce a diffusion-based cross-domain image translator in the absence of paired training data. Unlike GAN-based methods, our approach integrates diffusion models to learn the image translation process, allowing for more coverable…
The goal of this thesis is to provide a framework for the use of task-based metrics of image quality to aid in the design, implementation, and evaluation of CT image reconstruction algorithms and CT systems in general. We support the view…
This paper introduces an interacting-particle optimization method tailored to possibly non-convex composite optimization problems, which arise widely in signal processing. The proposed method, \emph{ProxiCBO}, integrates consensus-based…
Reconstructing the 3D shape of a deformable environment from the information captured by a moving depth camera is highly relevant to surgery. The underlying challenge is the fact that simultaneously estimating camera motion and tissue…
State-of-the-art object detection models are frequently trained offline using available datasets, such as ImageNet: large and overly diverse data that are unbalanced and hard to cluster semantically. This kind of training drops the object…
Large-scale image-text pre-trained models enable zero-shot classification and provide consistent accuracy across various data distributions. Nonetheless, optimizing these models in downstream tasks typically requires fine-tuning, which…
Differentiable rendering methods promise the ability to optimize various parameters of 3d scenes to achieve a desired result. However, lighting design has so far received little attention in this field. In this paper, we introduce a method…
In this work, we explore combining automatic hyperparameter tuning and optimization for federated learning (FL) in an online, one-shot procedure. We apply a principled approach on a method for adaptive client learning rate, number of local…