Self-supervised method estimates depth from monocular endoscopy videos.
problem Depth estimation from monocular endoscopy data without manual labeling.
method Convolutional neural networks trained with sparse supervision from stereo methods.
result Submillimeter mean residual error in cross-patient CT scans comparison.
New method improves reliability of depth estimation models.
problem Uncertainty quantification in large-scale vision models.
method Parameter-efficient Bayesian neural networks with PEFT methods.
result Combining PEFT methods with Bayesian inference enhances predictive performance.
We present a generalization of the Cauchy/Lorentzian, Geman-McClure, Welsch/Leclerc, generalized Charbonnier, Charbonnier/pseudo-Huber/L1-L2, and L2 loss functions. By introducing robustness as a continuous parameter, our loss function allows algorithms built around robust loss minimization to be generalized, which imp…
This paper explores the capabilities of convolutional neural networks to deal with a task that is easily manageable for humans: perceiving 3D pose of a human body from varying angles. However, in our approach, we are restricted to using a monocular vision system. For this purpose, we apply a convolutional neural networ…
Self-supervised method estimates distances on fisheye cameras for autonomous driving.
problem Accurate Euclidean distance estimation on fisheye cameras for autonomous driving.
method Self-supervised scale-aware framework for monocular fisheye videos.
result State-of-the-art results on KITTI dataset, comparable to other methods.
Generates coherent 3D scenes from monocular videos without supervision.
problem Lack of 3D scene modeling in video generation models.
method Trains a model to generate 3D scenes with moving objects and a background from monocular videos.
result Trained model generates coherent 3D scenes with multiple moving objects and a background.
Per-pixel ground-truth depth data is challenging to acquire at scale. To overcome this limitation, self-supervised learning has emerged as a promising alternative for training models to perform monocular depth estimation. In this paper, we propose a set of improvements, which together result in both quantitatively and …
Enhances SSL methods with depth cues for better image understanding.
problem Lack of depth cues in 2D image pixel maps limits SSL performance.
method Integrates depth signals from a pretrained monocular RGB-to-depth model into contrastive learning frameworks.
result Improves SSL methods' robustness and generalization with depth signals.
This paper improves 3D pose recovery from 2D images using non-convex regularization.
problem 3D object pose recovery from 2D images.
method Proposes non-convex regularization with leaky capped ℓ1-norm (LCNR) and multi-stage optimization.
result Theoretical analysis shows estimation error decreases with optimization stages.
Regression Prior Networks improve ensemble performance on regression tasks.
problem Improving ensemble performance on regression tasks.
method Extending Prior Networks and Ensemble Distribution Distillation (EnD2) to regression tasks using the Normal-Wishart distribution. result Regression Prior Networks yield performance competitive with ensemble approaches on regression tasks.
Hybrid RL combines simulated and real data for robust autonomous flight.
problem Challenges in training deep RL models for real-world robotic tasks.
method Combines real-world and simulated data to improve generalization.
result Quadrotor avoids collisions using only a monocular camera.
Y-GAN uses multi-camera data to estimate depth maps without expensive hardware.
problem Depth perception for autonomous systems requires accurate 3D spatial information.
method Proposes Y-GAN, a deep convolutional generative adversarial network.
result Y-GAN estimates depth maps from multi-camera stereo images without ground truth data.
In the last decade, supervised deep learning approaches have been extensively employed in visual odometry (VO) applications, which is not feasible in environments where labelled data is not abundant. On the other hand, unsupervised deep learning approaches for localization and mapping in unknown environments from unlab…
Proposes a new metric to evaluate uncertainty in deep learning predictions.
problem Evaluating the reliability of deep learning predictions, especially uncertainty.
method Develops a novel metric for evaluating relative uncertainty in regression tasks with deep neural networks.
result Validates the new metric on a toy dataset and applies it to monocular depth estimation.
Learning based methods have shown very promising results for the task of depth estimation in single images. However, most existing approaches treat depth prediction as a supervised regression problem and as a result, require vast quantities of corresponding ground truth depth data for training. Just recording quality d…
Paper tackles depth estimation and optic disc-cup segmentation from color fundus images.
problem Depth estimation and optic disc-cup segmentation from color fundus images.
method Uses fully convolutional networks for monocular retinal depth estimation and optic disc-cup segmentation.
result Demonstrates improved accuracy in depth estimation and optic disc-cup segmentation.
Proposes a new method for robust uncertainty quantification in regression tasks.
problem Robust uncertainty estimation for deep neural networks in regression tasks.
method Generalized Auxiliary Uncertainty Estimator (AuxUE) scheme, considering both aleatoric and epistemic uncertainties.
result DIDO method provides robust uncertainty estimates in noisy inputs, scalable to image-level and pixel-wise tasks.
We present NAVREN-RL, an approach to NAVigate an unmanned aerial vehicle in an indoor Real ENvironment via end-to-end reinforcement learning RL. A suitable reward function is designed keeping in mind the cost and weight constraints for micro drone with minimum number of sensing modalities. Collection of small number of…
We demonstrate the first application of deep reinforcement learning to autonomous driving. From randomly initialised parameters, our model is able to learn a policy for lane following in a handful of training episodes using a single monocular image as input. We provide a general and easy to obtain reward: the distance …
Sparsity inducing regularization is an important part for learning over-complete visual representations. Despite the popularity of ℓ1 regularization, in this paper, we investigate the usage of non-convex regularizations in this problem. Our contribution consists of three parts. First, we propose the leaky capped …
Sparse Vision MoE matches dense networks in image recognition while using less compute.
problem Scaling vision models efficiently in computer vision.
method Vision MoE (V-MoE) - a sparse version of Vision Transformer.
result V-MoE matches state-of-the-art dense networks in image recognition with half the compute.
Robust CLIP improves vision models' resistance to attacks.
problem Vulnerability of vision models to adversarial attacks.
method Unsupervised adversarial fine-tuning of CLIP.
result Robust CLIP prevents stealth attacks on vision models.
Learning from demonstration (LfD) is useful in settings where hand-coding behaviour or a reward function is impractical. It has succeeded in a wide range of problems but typically relies on manually generated demonstrations or specially deployed sensors and has not generally been able to leverage the copious demonstrat…
Top 8 robotic vision systems tackled lifelong object recognition challenges.
problem Lifelong learning in robotic vision for varied, dynamic environments.
method Design of a dataset with diverse conditions and rules for evaluation.
result Robotic vision systems improved over time with dynamic object appearances.
We propose a method to generate multiple diverse and valid human pose hypotheses in 3D all consistent with the 2D detection of joints in a monocular RGB image. We use a novel generative model uniform (unbiased) in the space of anatomically plausible 3D poses. Our model is compositional (produces a pose by combining par…
Computer vision SSL methods show effectiveness on time series data.
problem Evaluate if computer vision SSL frameworks are effective on time series data.
method Evaluated on UCR and UEA archives, proposed a new method improving VICReg.
result Computer vision SSL frameworks can be effective on time series data.
Quantum hybrid vision transformers improve event classification in high energy physics.
problem Excessive computational resources for training and deploying vision transformer models.
method Constructed quantum hybrid vision transformers for high energy physics event classification.
result Quantum hybrid models achieve comparable performance to classical models with fewer parameters.
New dataset and benchmarks for lifelong robotic vision tasks.
problem Challenges in applying computer vision to robots, especially lifelong learning.
method Provided a new lifelong robotic vision dataset and benchmarks.
result Demonstrated the complexity and bottlenecks in lifelong object recognition.
Survey on deep neural networks for vision and speech.
problem Improving intelligent vision and speech systems.
method Review of deep learning models and challenges.
result Emerging technologies show promise for future systems.
Mobile V-MoEs scale down ViTs for resource-constrained vision tasks.
problem Scaling down Vision Transformers for resource-constrained applications.
method Sparse Mixture-of-Experts (MoEs) applied to entire images, with a stable training procedure.
result Mobile V-MoEs achieve better performance-efficiency trade-offs than dense ViTs.
We consider the task of semantic robotic grasping, in which a robot picks up an object of a user-specified class using only monocular images. Inspired by the two-stream hypothesis of visual reasoning, we present a semantic grasping framework that learns object detection, classification, and grasp planning in an end-to-…
The NIPS 2018 Adversarial Vision Challenge is a competition to facilitate measurable progress towards robust machine vision models and more generally applicable adversarial attacks. This document is an updated version of our competition proposal that was accepted in the competition track of 32nd Conference on Neural In…
GSA-Nets apply group equivariance to self-attention for vision tasks.
problem Improving self-attention networks for vision tasks.
method Define group-equivariant positional encodings.
result GSA-Nets outperform non-equivariant self-attention networks on vision benchmarks.
3DB framework tests and debugs computer vision models using photorealistic simulation.
problem Discovering vulnerabilities and understanding model decision-making in computer vision systems.
method Unified framework using photorealistic simulation to test and debug vision models.
result Insights generated by 3DB transfer to the physical world, enabling robustness analysis.
CViT learns complex physical systems using vision transformer techniques.
problem Learning maps between infinite-dimensional function spaces in scientific machine learning.
method Combines vision transformer encoder, grid-based coordinate embedding, and cross-attention mechanism.
result Achieves state-of-the-art performance on multiple benchmarks, often surpassing larger models.
Vision and language tasks often fail to test AI comprehensively.
problem Current vision and language tasks are flawed due to dataset and evaluation issues.
method Review of current state and proposal for improvement.
result State-of-the-art systems perform well due to dataset and evaluation flaws.
Computer vision models are unstable due to task symmetries and labelling issues.
problem Instability of computer vision models in classification tasks.
method Analysis of symmetries, categorical nature, and labelling issues.
result Instability is a necessary result of current computer vision formulation.
Machine learning models are vulnerable to adversarial examples: small changes to images can cause computer vision models to make mistakes such as identifying a school bus as an ostrich. However, it is still an open question whether humans are prone to similar mistakes. Here, we address this question by leveraging recen…
ViWi dataset framework tackles wireless communication problems with visual data.
problem Leveraging visual sensory information in wireless communications.
method Developed a parametric, systematic, and scalable data generation framework using 3D modeling and ray-tracing.
result Offers a way to generate training and testing datasets for assessing machine learning solutions.
Computer vision is hard because of a large variability in lighting, shape, and texture; in addition the image signal is non-additive due to occlusion. Generative models promised to account for this variability by accurately modelling the image formation process as a function of latent variables with prior beliefs. Baye…
ViLT is a faster vision-and-language model without convolution or region supervision.
problem Efficiency and expressive power limitations in current VLP models.
method A convolution-free Vision-and-Language Transformer (ViLT) that processes visual inputs similarly to textual inputs.
result ViLT is up to tens of times faster with competitive or better performance.
Framework simplifies vision-based control and goal discovery.
problem Learning proportional control from visual data.
method Introduces NewtonianVAE for proportional control and goal discovery.
result Dramatic simplification and acceleration of vision-based controllers.
New framework segments 3D scenes using neural algorithms and sub-Riemannian geometry.
problem Effective scene segmentation in 3D vision.
method Neurogeometric sub-Riemannian model, harmonic analysis, neural-based stereo correspondence.
result Sub-Riemannian metric is central to effective scene segmentation.
Real-time uncertainty estimation for computer vision tasks.
problem Real-time inference of uncertainty in deep learning models.
method Uncertainty-Aware Distribution Distillation method for fast inference.
result Significantly reduced inference time with improved uncertainty and predictive performance.
3D good continuation model explains stereo vision using neurogeometry.
problem Understanding how the brain processes 3D visual correspondence.
method Developed a neurogeometric model involving spatial and orientation disparities.
result Provides insight into neural organization and correspondence problem.
Meta Omnium benchmarks few-shot learning across diverse vision tasks.
problem Evaluating generalization of few-shot learning across multiple vision tasks.
method Introduction of Meta Omnium dataset and evaluation of meta-learning algorithms.
result Meta-learning algorithms can generalize across diverse vision tasks.
This work characterizes benign overfitting in Vision Transformers.
problem Understanding generalization of Vision Transformers when trained to overfit.
method Gradient descent on a data distribution model, focusing on self-attention layer and softmax.
result Established a condition to distinguish between small and large test errors based on signal-to-noise ratio.
Detects anomalies in autonomous mobile robots using vision.
problem Anomaly detection for autonomous mobile robots.
method Unsupervised deep learning methods and a novel dataset.
result State-of-the-art approach tested on a new dataset.