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.
On-device research index
arXiv research
A locally-built, LLM-digested index of recent arXiv papers in quant finance, geometry/topology, and statistical ML — keyword search served straight from SQLite on this machine.
168,786 papers · 148 categories
Trend · papers per month
48 results for “vision systems”
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.
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.
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.
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…
A new network controls task execution in a single vision system.
problem Executing multiple tasks accurately and efficiently in a single network.
method A top-down control network modifies main recognition network activations based on selected task, image content, and spatial location.
result Significantly better results on four datasets compared to state-of-the-art approaches.
An important goal of computer vision is to build systems that learn visual representations over time that can be applied to many tasks. In this paper, we investigate a vision-language embedding as a core representation and show that it leads to better cross-task transfer than standard multi-task learning. In particular…
The democratization of machine learning (ML) has led to ML-based machine vision systems for autonomous driving, traffic monitoring, and video surveillance. However, true democratization cannot be achieved without greatly simplifying the process of collecting groundtruth for training and testing these systems. This grou…
In this work, a new approach for Sun tracking systems is presented. Due to the current system limitations regarding costs and operational problems, a new approach based on low cost, computer vision open hardware and deep learning has been developed. The preliminary tests carried out successfully in Plataforma solar de …
Distributed Reinforcement Learning of Targeted Grasping with Active Vision for Mobile Manipulatorscs.RO
Robotic grasping system learns to target objects from a single image.
problem Robotic grasping in unstructured environments.
method Distributed reinforcement learning, active vision, synchronous SGD.
result System learns to grasp unseen objects without retraining.
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…
With the advent of large labelled datasets and high-capacity models, the performance of machine vision systems has been improving rapidly. However, the technology has still major limitations, starting from the fact that different vision problems are still solved by different models, trained from scratch or fine-tuned o…
V-SysId identifies keypoints and 3D system from unlabeled videos.
problem Identifying keypoints and 3D system from unlabeled videos.
method Alternates between parameter estimation and extrinsic camera calibration, using motion equations as weak supervision.
result Utility of the approach demonstrated across various settings.
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.
A new system combines vision and language for person re-identification.
problem Real-world surveillance lacks visual data for person re-identification.
method Two-stream CNN framework with shared logits, CCA for modalities, multi-modal testing protocol.
result 22% improvement in re-identification performance with multi-modal queries.
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.
Language grounded image understanding tasks have often been proposed as a method for evaluating progress in artificial intelligence. Ideally, these tasks should test a plethora of capabilities that integrate computer vision, reasoning, and natural language understanding. However, rather than behaving as visual Turing t…
Unified inference framework for spatiotemporal data.
problem Challenges in extracting mechanistic insights from complex spatiotemporal data.
method Vision transformer-driven variational encoding and likelihood-free Bayesian approach.
result Unified inference framework for identifying spatial and temporal patterns.
FedVision uses federated learning to improve object detection without transmitting data.
problem Challenges in building object detection models on large training datasets due to privacy and cost issues.
method Federated learning (FL) platform for easy integration by non-experts.
result Significant efficiency improvement and cost reduction in smart city applications.
Active learning improves inspection systems by using weakly labeled data.
problem Rapidly updating machine vision inspection systems in evolving manufacturing processes.
method Developed a methodology for active learning from weakly labeled data, addressing covariate shift with domain-adversarial training.
result Demonstrated that active learning can accelerate the annotation process and reduce false positives.
The vision systems of the eagle and the snake outperform everything that we can make in the laboratory, but snakes and eagles cannot build an eyeglass or a telescope or a microscope. (Judea Pearl)
We present a system for the automatic differentiation of a higher-order functional array-processing language. The core functional language underlying this system simultaneously supports both source-to-source automatic differentiation and global optimizations such as loop transformations. Thanks to this feature, we demo…
In this paper, we study the problem of learning vision-based dynamic manipulation skills using a scalable reinforcement learning approach. We study this problem in the context of grasping, a longstanding challenge in robotic manipulation. In contrast to static learning behaviors that choose a grasp point and then execu…
PerceptNet mimics human vision to estimate image quality.
problem Estimating perceptual distance between images and their perturbations.
method Inspired by human visual system, PerceptNet uses convolutional neural network architecture.
result PerceptNet outperforms traditional image quality metrics and deep learning methods.
System discovers new classes from unlabeled data, improving model performance.
problem Handling datapoints outside initial training distribution.
method Develops new classes through semi-supervised learning, using Dataset Reconstruction Accuracy and class learnability.
result Demonstrates improved model quality through automatic class discovery.
Intelligent control for greenhouses using deep reinforcement learning.
problem Uncertain nonlinear system of greenhouse environment control.
method Model Embedded Deep Reinforcement Learning (MEDRL) with computer vision and crop growth models.
result Precision and convenience in precise control of greenhouse environment.
Deep learning improves material recognition in construction monitoring.
problem Varying illuminations and low accuracy rates in material classification.
method Deep learning methods, including convolutional neural networks, were used to classify and recognize materials in construction sites.
result Achieved 97.35% accuracy rate for material classification.
AI models aligned with human vision perform well on few data tasks.
problem Few-shot learning performance with limited data.
method Information-theoretic analysis and empirical testing of 491 models.
result Highly aligned models show better robustness to attacks and domain shifts.
Highly Autonomous Driving (HAD) systems rely on deep neural networks for the visual perception of the driving environment. Such networks are trained on large manually annotated databases. In this work, a semi-parametric approach to one-shot learning is proposed, with the aim of bypassing the manual annotation step requ…
New approach replaces BN layers with shifted-ReLU for embedded systems.
problem Complexity and overheads of BN layers in low-power embedded systems.
method Used shifted-ReLU layers instead of BN layers in wide residual networks.
result Shifted-ReLU layers offer advantages in speed, memory, and complexity without significant accuracy loss.
Paper proposes privacy-preserving learning for images, making them imperceptible to humans but recognizable by machines.
problem Conflict between developing AI systems and protecting sensitive training data.
method Encryption strategies (random shuffling and sub-patch mixing) followed by minimal adaptation to vision transformer.
result Achieves comparable accuracy to competitive methods while ensuring human-imperceptibility of encrypted images.
Machine vision is critical to robotics due to a wide range of applications which rely on input from visual sensors such as autonomous mobile robots and smart production systems. To create the smart homes and systems of tomorrow, an overview about current challenges in the research field would be of use to identify furt…
CovidSens uses social media to track COVID-19 spread.
problem Accurate and timely dissemination of COVID-19 information.
method Social sensing to analyze online user data.
result Real-time COVID-19 spread tracking system.
CVPR 2020 challenge evaluates continual learning in computer vision.
problem Making AI systems more adaptive and efficient.
method Evaluated different continual learning approaches on a common hardware with shared metrics.
result Reported main results, finalists, and prize winners.
Paper proposes EEIPU, a memoization-aware BO algorithm to reduce hyperparameter tuning costs.
problem High costs in GPU-days for training and fine-tuning language models.
method Memoization-aware Bayesian Optimization (EEIPU) algorithm in tandem with pipeline caching.
result EEIPU produces 103% more hyperparameter candidates and 108% more validation metric improvement.
Proposes hinge-Wasserstein to improve uncertainty estimation in regression tasks.
problem Estimating multimodal aleatoric uncertainty in regression tasks from images.
method Regression-by-classification paradigm with hinge-Wasserstein loss.
result Hinge-Wasserstein loss improves uncertainty estimation on challenging tasks.
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.
We introduce a technique that can automatically tune the parameters of a rule-based computer vision system comprised of thresholds, combinational logic, and time constants. This lets us retain the flexibility and perspicacity of a conventionally structured system while allowing us to perform approximate gradient descen…
Introduces basic facts on early vision's functional architecture.
problem Accessibility of early vision's functional architecture for non-specialists.
method Survey of three neurogeometric models and discussion of the conformal model.
result Synthesis of symplectic and spherical models into the conformal model.
In this paper, we propose to apply object detection methods from the vision domain on the speech recognition domain, by treating audio fragments as objects. More specifically, we present SpeechYOLO, which is inspired by the YOLO algorithm for object detection in images. The goal of SpeechYOLO is to localize boundaries …
Automatic classification of trees using remotely sensed data has been a dream of many scientists and land use managers. Recently, Unmanned aerial vehicles (UAV) has been expected to be an easy-to-use, cost-effective tool for remote sensing of forests, and deep learning has attracted attention for its ability concerning…
Paper presents certified defenses against adversarial patch attacks.
problem Certified defenses against adversarial patch attacks are needed.
method Proposes the first certified defense and faster training methods.
result Demonstrates robustness transfer across different patch shapes.
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.
Machine learning models learn what we teach them to learn. Machine learning is at the heart of recommender systems. If a machine learning model is trained on biased data, the resulting recommender system may reflect the biases in its recommendations. Biases arise at different stages in a recommender system, from existi…
Image classifiers are sensitive to small changes, affecting most images in a class.
problem Sensitivity of image classifiers to small perturbations.
method Demonstrated sensitivity for any classifier over images, showing that for most classes, a tiny perturbation can change the classification of a majority of images.
result Image classifiers are sensitive to small perturbations, affecting most images in a class.
Unsupervised fire and smoke segmentation from IR videos.
problem Early detection of fire from infrared videos.
method Spatial, temporal, and motion information fusion using optical flow, divergence, and intensity values.
result Markov Random Field outperforms other clustering algorithms in fire and smoke segmentation.
Deep learning predicts mass from images with sparse ground truth.
problem Accurately estimating mass from images with limited ground truth.
method Semi-supervised deep learning with gradient aggregation and sparse ground truth.
result Deep neural network accurately predicts mass from images.
A tailored HTR system improves CER to 0.015 for medieval Latin.
problem Digitizing handwritten medieval Latin records for a low-resource language.
method End-to-end pipeline using image segmentation and transformer-based models with extensive data augmentation.
result Best-performing setup achieved CER of 0.015, superior to commercial models.