Search Results for author:
Found 64 papers, 33 papers with code
NeuroNCAP: Photorealistic Closed-loop Safety Testing for Autonomous Driving
We present a versatile NeRF-based simulator for testing autonomous driving (AD) software systems, designed with a focus on sensor-realistic closed-loop evaluation and the creation of safety-critical scenarios.
Composed Video Retrieval via Enriched Context and Discriminative Embeddings
Composed video retrieval (CoVR) is a challenging problem in computer vision which has recently highlighted the integration of modification text with visual queries for more sophisticated video search in large databases.
DiffSF: Diffusion Models for Scene Flow Estimation
Aiming at improving accuracy while additionally providing an estimate for uncertainty, we propose DiffSF that combines transformer-based scene flow estimation with denoising diffusion models.
MobiLlama: Towards Accurate and Lightweight Fully Transparent GPT
"Bigger the better" has been the predominant trend in recent Large Language Models (LLMs) development.
PALO: A Polyglot Large Multimodal Model for 5B People
PALO offers visual reasoning capabilities in 10 major languages, including English, Chinese, Hindi, Spanish, French, Arabic, Bengali, Russian, Urdu, and Japanese, that span a total of ~5B people (65% of the world population).
SeTformer is What You Need for Vision and Language
Kernel methods are employed to simplify computations by approximating softmax but often lead to performance drops compared to softmax attention.
Steerers: A framework for rotation equivariant keypoint descriptors
Image keypoint descriptions that are discriminative and matchable over large changes in viewpoint are vital for 3D reconstruction.
Certainty In, Certainty Out: REVQCs for Quantum Machine Learning
The field of Quantum Machine Learning (QML) has emerged recently in the hopes of finding new machine learning protocols or exponential speedups for classical ones.
Leveraging the Power of Data Augmentation for Transformer-based Tracking
Due to long-distance correlation and powerful pretrained models, transformer-based methods have initiated a breakthrough in visual object tracking performance.
IBAFormer: Intra-batch Attention Transformer for Domain Generalized Semantic Segmentation
Domain generalized semantic segmentation (DGSS) is a critical yet challenging task, where the model is trained only on source data without access to any target data.
DeDoDe: Detect, Don't Describe -- Describe, Don't Detect for Local Feature Matching
To train a descriptor, we maximize the mutual nearest neighbour objective over the keypoints with a separate network.
Learning to Augment: Hallucinating Data for Domain Generalized Segmentation
Domain generalized semantic segmentation (DGSS) is an essential but highly challenging task, in which the model is trained only on source data and any target data is not available.
Learning Coverage Paths in Unknown Environments with Deep Reinforcement Learning
Coverage path planning (CPP) is the problem of finding a path that covers the entire free space of a confined area, with applications ranging from robotic lawn mowing to search-and-rescue.
Flexible Distribution Alignment: Towards Long-tailed Semi-supervised Learning with Proper Calibration
Long-tailed semi-supervised learning (LTSSL) represents a practical scenario for semi-supervised applications, challenged by skewed labeled distributions that bias classifiers.
O$n$ Learning Deep O($n$)-Equivariant Hyperspheres
In this paper, we utilize hyperspheres and regular $n$-simplexes and propose an approach to learning deep features equivariant under the transformations of $n$D reflections and rotations, encompassed by the powerful group of O$(n)$.
RoMa: Robust Dense Feature Matching
The aim is to learn a robust model, i. e., a model able to match under challenging real-world changes.
High-fidelity Pseudo-labels for Boosting Weakly-Supervised Segmentation
Our work is based on two techniques for improving CAMs; importance sampling, which is a substitute for GAP, and the feature similarity loss, which utilizes a heuristic that object contours almost always align with color edges in images.
Flow-guided Semi-supervised Video Object Segmentation
A model to extract the combined information from optical flow and the image is proposed, which is then used as input to the target model and the decoder network.
Raw or Cooked? Object Detection on RAW Images
Images fed to a deep neural network have in general undergone several handcrafted image signal processing (ISP) operations, all of which have been optimized to produce visually pleasing images.
Evidential Deep Learning for Class-Incremental Semantic Segmentation
In this paper, we address the problem of how to model unlabeled classes while avoiding spurious feature clustering of future uncorrelated classes.
TetraSphere: A Neural Descriptor for O(3)-Invariant Point Cloud Analysis
In our approach, we perform TetraTransform--an equivariant embedding of the 3D input into 4D, constructed from the steerable neurons--and extract deeper O(3)-equivariant features using vector neurons.
Balanced Product of Calibrated Experts for Long-Tailed Recognition
We show how to properly define these distributions and combine the experts in order to achieve unbiased predictions, by proving that the ensemble is Fisher-consistent for minimizing the balanced error.
Long-tail Learning
Long-tail Learning on CIFAR-10-LT (ρ=100)
+1
Video Instance Segmentation via Multi-scale Spatio-temporal Split Attention Transformer
When using the ResNet50 backbone, our MS-STS achieves a mask AP of 50. 1 %, outperforming the best reported results in literature by 2. 7 % and by 4. 8 % at higher overlap threshold of AP_75, while being comparable in model size and speed on Youtube-VIS 2019 val.
Importance Sampling CAMs for Weakly-Supervised Segmentation
Classification networks can be used to localize and segment objects in images by means of class activation maps (CAMs).
Weakly supervised Semantic Segmentation
Weakly-Supervised Semantic Segmentation
Visual Feature Encoding for GNNs on Road Networks
In this work, we present a novel approach to learning an encoding of visual features into graph neural networks with the application on road network data.
DKM: Dense Kernelized Feature Matching for Geometry Estimation
This changes with our novel dense method, which outperforms both dense and sparse methods on geometry estimation.
Learning to integrate vision data into road network data
Road networks are the core infrastructure for connected and autonomous vehicles, but creating meaningful representations for machine learning applications is a challenging task.
DoodleFormer: Creative Sketch Drawing with Transformers
Creative sketch image generation is a challenging vision problem, where the task is to generate diverse, yet realistic creative sketches possessing the unseen composition of the visual-world objects.
Visual Object Tracking with Discriminative Filters and Siamese Networks: A Survey and Outlook
Accurate and robust visual object tracking is one of the most challenging and fundamental computer vision problems.
Dense Gaussian Processes for Few-Shot Segmentation
Given the support set, our dense GP learns the mapping from local deep image features to mask values, capable of capturing complex appearance distributions.
Ranked #1 on
Few-Shot Semantic Segmentation
on COCO-20i (10-shot)
Modeling Unknown Semantic Labels as Uncertainty in the Prediction: Evidential Deep Learning for Class-Incremental Semantic Segmentation
In this paper we address the problem of how to model unlabeled classes to avoid unnecessary feature clustering of uncorrelated classes.
Fully Steerable 3D Spherical Neurons
Emerging from low-level vision theory, steerable filters found their counterpart in prior work on steerable convolutional neural networks equivariant to rigid transformations.
Graph Representation Learning for Road Type Classification
We present a novel learning-based approach to graph representations of road networks employing state-of-the-art graph convolutional neural networks.
VidHarm: A Clip Based Dataset for Harmful Content Detection
Automatically identifying harmful content in video is an important task with a wide range of applications.
Steerable 3D Spherical Neurons
In our work, we propose a steerable feed-forward learning-based approach that consists of neurons with spherical decision surfaces and operates on point clouds.
A Bayesian Approach to Reinforcement Learning of Vision-Based Vehicular Control
We trained our system using both ground truth and estimated semantic segmentation input.
Deep Gaussian Processes for Few-Shot Segmentation
Through the expressivity of the GP, our approach is capable of modeling complex appearance distributions in the deep feature space.
Normalized Convolution Upsampling for Refined Optical Flow Estimation
Our proposed approach formulates the upsampling task as a sparse problem and employs the normalized convolutional neural networks to solve it.
Learning Video Instance Segmentation with Recurrent Graph Neural Networks
Most existing approaches to video instance segmentation comprise multiple modules that are heuristically combined to produce the final output.
Embed Me If You Can: A Geometric Perceptron
Our extension of the MLHP model, the multilayer geometric perceptron (MLGP), and its respective layer units, i. e., geometric neurons, are consistent with the 3D geometry and provide a geometric handle of the learned coefficients.
Uncertainty-Aware CNNs for Depth Completion: Uncertainty from Beginning to End
In this work, we thus focus on modeling the uncertainty of depth data in depth completion starting from the sparse noisy input all the way to the final prediction.
Learning What to Learn for Video Object Segmentation
This allows us to achieve a rich internal representation of the target in the current frame, significantly increasing the segmentation accuracy of our approach.
Learning Fast and Robust Target Models for Video Object Segmentation
The target appearance model consists of a light-weight module, which is learned during the inference stage using fast optimization techniques to predict a coarse but robust target segmentation.
Unsupervised Learning of Anomaly Detection from Contaminated Image Data using Simultaneous Encoder Training
In this work, we evaluate the effects of anomaly contaminations in the training data on state-of-the-art GAN-based anomaly detection methods.
Discriminative Online Learning for Fast Video Object Segmentation
We propose a novel approach, based on a dedicated target appearance model that is exclusively learned online to discriminate between the target and background image regions.
A Generative Appearance Model for End-to-end Video Object Segmentation
One of the fundamental challenges in video object segmentation is to find an effective representation of the target and background appearance.
ATOM: Accurate Tracking by Overlap Maximization
We argue that this approach is fundamentally limited since target estimation is a complex task, requiring high-level knowledge about the object.
Ranked #7 on
Object Tracking
on FE108
Confidence Propagation through CNNs for Guided Sparse Depth Regression
In this paper, we propose an algebraically-constrained normalized convolution layer for CNNs with highly sparse input that has a smaller number of network parameters compared to related work.
Ranked #7 on
Depth Completion
on KITTI Depth Completion
Propagating Confidences through CNNs for Sparse Data Regression
To tackle this challenging problem, we introduce an algebraically-constrained convolution layer for CNNs with sparse input and demonstrate its capabilities for the scene depth completion task.
Unveiling the Power of Deep Tracking
In the field of generic object tracking numerous attempts have been made to exploit deep features.
Density Adaptive Point Set Registration
Contrary to previous works, we model the underlying structure of the scene as a latent probability distribution, and thereby induce invariance to point set density changes.
DCCO: Towards Deformable Continuous Convolution Operators
Generally, DCF based trackers learn a rigid appearance model of the target.
Deep Projective 3D Semantic Segmentation
Recent attempts, based on 3D deep learning approaches (3D-CNNs), have achieved below-expected results.
Ranked #15 on
Semantic Segmentation
on Semantic3D
Deep Motion Features for Visual Tracking
To the best of our knowledge, we are the first to propose fusing appearance information with deep motion features for visual tracking.
Scale Coding Bag of Deep Features for Human Attribute and Action Recognition
Most approaches to human attribute and action recognition in still images are based on image representation in which multi-scale local features are pooled across scale into a single, scale-invariant encoding.
ECO: Efficient Convolution Operators for Tracking
Moreover, our fast variant, using hand-crafted features, operates at 60 Hz on a single CPU, while obtaining 65. 0% AUC on OTB-2015.
Ranked #13 on
Visual Object Tracking
on VOT2017/18
Discriminative Scale Space Tracking
Compared to the standard exhaustive scale search, our approach achieves a gain of 2. 5% in average overlap precision on the OTB dataset.
Adaptive Decontamination of the Training Set: A Unified Formulation for Discriminative Visual Tracking
We propose a novel generic approach for alleviating the problem of corrupted training samples in tracking-by-detection frameworks.
Learning Spatially Regularized Correlation Filters for Visual Tracking
These methods utilize a periodic assumption of the training samples to efficiently learn a classifier on all patches in the target neighborhood.
Beyond Correlation Filters: Learning Continuous Convolution Operators for Visual Tracking
We also demonstrate the effectiveness of our learning formulation in extensive feature point tracking experiments.
A Probabilistic Framework for Color-Based Point Set Registration
On the Stanford Lounge dataset, our approach achieves a relative reduction of the failure rate by 78% compared to the baseline.
Efficient Robust Mean Value Calculation of 1D Features
A robust mean value is often a good alternative to the standard mean value when dealing with data containing many outliers.
Adaptive Color Attributes for Real-Time Visual Tracking
This paper investigates the contribution of color in a tracking-by-detection framework.
