Search Results for author:
Found 55 papers, 33 papers with code
FLOSS: Free Lunch in Open-vocabulary Semantic Segmentation
Our plug-and-play method, coined FLOSS, is orthogonal and complementary to existing OVSS methods, offering a ''free lunch'' to systematically improve OVSS without labels and additional training.
Open Vocabulary Semantic Segmentation
Open-Vocabulary Semantic Segmentation
+1
VaViM and VaVAM: Autonomous Driving through Video Generative Modeling
We explore the potential of large-scale generative video models for autonomous driving, introducing an open-source auto-regressive video model (VaViM) and its companion video-action model (VaVAM) to investigate how video pre-training transfers to real-world driving.
DOC-Depth: A novel approach for dense depth ground truth generation
We demonstrate the effectiveness of our approach on the KITTI dataset, improving its density from 16. 1% to 71. 2% and release this new fully dense depth annotation, to facilitate future research in the domain.
Domain Adaptation with a Single Vision-Language Embedding
Domain adaptation has been extensively investigated in computer vision but still requires access to target data at the training time, which might be difficult to obtain in some uncommon conditions.
One-shot Unsupervised Domain Adaptation
Semantic Segmentation
+1
Fine-Tuning CLIP's Last Visual Projector: A Few-Shot Cornucopia
We consider the problem of adapting a contrastively pretrained vision-language model like CLIP (Radford et al., 2021) for few-shot classification.
The BRAVO Semantic Segmentation Challenge Results in UNCV2024
We propose the unified BRAVO challenge to benchmark the reliability of semantic segmentation models under realistic perturbations and unknown out-of-distribution (OOD) scenarios.
LED: Light Enhanced Depth Estimation at Night
Nighttime camera-based depth estimation is a highly challenging task, especially for autonomous driving applications, where accurate depth perception is essential for ensuring safe navigation.
No Train, all Gain: Self-Supervised Gradients Improve Deep Frozen Representations
This paper introduces FUNGI, Features from UNsupervised GradIents, a method to enhance the features of transformer encoders by leveraging self-supervised gradients.
Test-time Contrastive Concepts for Open-world Semantic Segmentation
Recent CLIP-like Vision-Language Models (VLMs), pre-trained on large amounts of image-text pairs to align both modalities with a simple contrastive objective, have paved the way to open-vocabulary semantic segmentation.
Open Vocabulary Semantic Segmentation
Open-Vocabulary Semantic Segmentation
+1
Valeo4Cast: A Modular Approach to End-to-End Forecasting
In end-to-end forecasting, the model must jointly detect and track from sensor data (cameras or LiDARs) the past trajectories of the different elements of the scene and predict their future locations.
OccFeat: Self-supervised Occupancy Feature Prediction for Pretraining BEV Segmentation Networks
Models pretrained with our method exhibit improved BEV semantic segmentation performance, particularly in low-data scenarios.
POP-3D: Open-Vocabulary 3D Occupancy Prediction from Images
We describe an approach to predict open-vocabulary 3D semantic voxel occupancy map from input 2D images with the objective of enabling 3D grounding, segmentation and retrieval of free-form language queries.
3D Semantic Occupancy Prediction
3D Semantic Segmentation
+3
Make Me a BNN: A Simple Strategy for Estimating Bayesian Uncertainty from Pre-trained Models
Deep Neural Networks (DNNs) are powerful tools for various computer vision tasks, yet they often struggle with reliable uncertainty quantification - a critical requirement for real-world applications.
CLIP-DINOiser: Teaching CLIP a few DINO tricks for open-vocabulary semantic segmentation
We propose to locally improve dense MaskCLIP features, which are computed with a simple modification of CLIP's last pooling layer, by integrating localization priors extracted from self-supervised features.
Open Vocabulary Semantic Segmentation
Open-Vocabulary Semantic Segmentation
+1
A Simple Recipe for Language-guided Domain Generalized Segmentation
Generalization to new domains not seen during training is one of the long-standing challenges in deploying neural networks in real-world applications.
Three Pillars improving Vision Foundation Model Distillation for Lidar
In particular, thanks to our scalable distillation method named ScaLR, we show that scaling the 2D and 3D backbones and pretraining on diverse datasets leads to a substantial improvement of the feature quality.
The Robust Semantic Segmentation UNCV2023 Challenge Results
This paper outlines the winning solutions employed in addressing the MUAD uncertainty quantification challenge held at ICCV 2023.
Improving CLIP Robustness with Knowledge Distillation and Self-Training
This paper examines the robustness of a multi-modal computer vision model, CLIP (Contrastive Language-Image Pretraining), in the context of unsupervised learning.
Learning to Generate Training Datasets for Robust Semantic Segmentation
We propose a novel approach to improve the robustness of semantic segmentation techniques by leveraging the synergy between label-to-image generators and image-to-label segmentation models.
MOCA: Self-supervised Representation Learning by Predicting Masked Online Codebook Assignments
Self-supervised learning can be used for mitigating the greedy needs of Vision Transformer networks for very large fully-annotated datasets.
RangeViT: Towards Vision Transformers for 3D Semantic Segmentation in Autonomous Driving
(c) We refine pixel-wise predictions with a convolutional decoder and a skip connection from the convolutional stem to combine low-level but fine-grained features of the the convolutional stem with the high-level but coarse predictions of the ViT encoder.
PODA: Prompt-driven Zero-shot Domain Adaptation
In this paper, we propose the task of 'Prompt-driven Zero-shot Domain Adaptation', where we adapt a model trained on a source domain using only a general description in natural language of the target domain, i. e., a prompt.
PØDA: Prompt-driven Zero-shot Domain Adaptation
In this paper, we propose the task of `Prompt-driven Zero-shot Domain Adaptation', where we adapt a model trained on a source domain using only a general description in natural language of the target domain, i. e., a prompt.
Packed-Ensembles for Efficient Uncertainty Estimation
Deep Ensembles (DE) are a prominent approach for achieving excellent performance on key metrics such as accuracy, calibration, uncertainty estimation, and out-of-distribution detection.
Active Learning Strategies for Weakly-supervised Object Detection
On COCO, using on average 10 fully-annotated images per class, or equivalently 1% of the training set, BiB also reduces the performance gap (in AP) between the weakly-supervised detector and the fully-supervised Fast RCNN by over 70%, showing a good trade-off between performance and data efficiency.
Improving Predictive Performance and Calibration by Weight Fusion in Semantic Segmentation
Albeit effective, only few works haveimproved the understanding and the performance of weight averaging. Here, we revisit this approach and show that a simple weight fusion (WF)strategy can lead to a significantly improved predictive performance andcalibration.
Latent Discriminant deterministic Uncertainty
Predictive uncertainty estimation is essential for deploying Deep Neural Networks in real-world autonomous systems.
Instance-Aware Observer Network for Out-of-Distribution Object Segmentation
To address this issue, we build upon the recent ObsNet approach by providing object instance knowledge to the observer.
LaRa: Latents and Rays for Multi-Camera Bird's-Eye-View Semantic Segmentation
Recent works in autonomous driving have widely adopted the bird's-eye-view (BEV) semantic map as an intermediate representation of the world.
Ranked #6 on
Bird's-Eye View Semantic Segmentation
on nuScenes
Image-to-Lidar Self-Supervised Distillation for Autonomous Driving Data
In this context, we propose a self-supervised pre-training method for 3D perception models that is tailored to autonomous driving data.
UnShadowNet: Illumination Critic Guided Contrastive Learning For Shadow Removal
Shadows are frequently encountered natural phenomena that significantly hinder the performance of computer vision perception systems in practical settings, e. g., autonomous driving.
Solving Disjunctive Temporal Networks with Uncertainty under Restricted Time-Based Controllability using Tree Search and Graph Neural Networks
Moreover, we leverage a graph neural network as a heuristic for tree search guidance.
What to Hide from Your Students: Attention-Guided Masked Image Modeling
In this work, we argue that image token masking differs from token masking in text, due to the amount and correlation of tokens in an image.
Drive&Segment: Unsupervised Semantic Segmentation of Urban Scenes via Cross-modal Distillation
This work investigates learning pixel-wise semantic image segmentation in urban scenes without any manual annotation, just from the raw non-curated data collected by cars which, equipped with cameras and LiDAR sensors, drive around a city.
MUAD: Multiple Uncertainties for Autonomous Driving, a benchmark for multiple uncertainty types and tasks
However, disentangling the different types and sources of uncertainty is non trivial for most datasets, especially since there is no ground truth for uncertainty.
Localizing Objects with Self-Supervised Transformers and no Labels
We also show that training a class-agnostic detector on the discovered objects boosts results by another 7 points.
Ranked #4 on
Weakly-Supervised Object Localization
on CUB-200-2011
(Top-1 Localization Accuracy metric)
Triggering Failures: Out-Of-Distribution detection by learning from local adversarial attacks in Semantic Segmentation
In this paper, we tackle the detection of out-of-distribution (OOD) objects in semantic segmentation.
Out-of-Distribution Detection
Out of Distribution (OOD) Detection
+2
Learning-based Preference Prediction for Constrained Multi-Criteria Path-Planning
The uncertain criterion represents the feasibility of driving through the path without requiring human intervention.
Optimal Solving of Constrained Path-Planning Problems with Graph Convolutional Networks and Optimized Tree Search
More specifically, a graph neural network is used to assist the branch and bound algorithm in handling constraints associated with a desired solution path.
Time-based Dynamic Controllability of Disjunctive Temporal Networks with Uncertainty: A Tree Search Approach with Graph Neural Network Guidance
Scheduling in the presence of uncertainty is an area of interest in artificial intelligence due to the large number of applications.
Constrained Shortest Path Search with Graph Convolutional Neural Networks
In this paper, we focus on shortest path search with mandatory nodes on a given connected graph.
Robust Semantic Segmentation with Superpixel-Mix
Along with predictive performance and runtime speed, reliability is a key requirement for real-world semantic segmentation.
StyleLess layer: Improving robustness for real-world driving
Robustness to various image corruptions, caused by changing weather conditions or sensor degradation and aging, is crucial for safety when such vehicles are deployed in the real world.
OBoW: Online Bag-of-Visual-Words Generation for Self-Supervised Learning
With this in mind, we propose a teacher-student scheme to learn representations by training a convolutional net to reconstruct a bag-of-visual-words (BoW) representation of an image, given as input a perturbed version of that same image.
Ranked #18 on
Semi-Supervised Image Classification
on ImageNet - 1% labeled data
(Top 5 Accuracy metric)
Encoding the latent posterior of Bayesian Neural Networks for uncertainty quantification
Bayesian neural networks (BNNs) have been long considered an ideal, yet unscalable solution for improving the robustness and the predictive uncertainty of deep neural networks.
Ranked #144 on
Image Classification
on CIFAR-10
Spherical Perspective on Learning with Normalization Layers
Normalization Layers (NLs) are widely used in modern deep-learning architectures.
One Versus all for deep Neural Network Incertitude (OVNNI) quantification
This is due to the fact that modern DNNs are usually uncalibrated and we cannot characterize their epistemic uncertainty.
PLOP: Probabilistic poLynomial Objects trajectory Planning for autonomous driving
Our model processes ego vehicle front-facing camera images and bird-eye view grid, computed from Lidar point clouds, with detections of past and present objects, in order to generate multiple trajectories for both ego vehicle and its neighbors.
Learning Representations by Predicting Bags of Visual Words
Inspired by the success of NLP methods in this area, in this work we propose a self-supervised approach based on spatially dense image descriptions that encode discrete visual concepts, here called visual words.
Dynamic Task Weighting Methods for Multi-task Networks in Autonomous Driving Systems
Deep multi-task networks are of particular interest for autonomous driving systems.
TRADI: Tracking deep neural network weight distributions for uncertainty estimation
During training, the weights of a Deep Neural Network (DNN) are optimized from a random initialization towards a nearly optimum value minimizing a loss function.
This dataset does not exist: training models from generated images
This naturally brings the question: Can we train a classifier only on the generated data?
Boosting Few-Shot Visual Learning with Self-Supervision
Few-shot learning and self-supervised learning address different facets of the same problem: how to train a model with little or no labeled data.
Dense Classification and Implanting for Few-Shot Learning
Training deep neural networks from few examples is a highly challenging and key problem for many computer vision tasks.
Understanding and Improving Kernel Local Descriptors
We propose a multiple-kernel local-patch descriptor based on efficient match kernels from pixel gradients.
