Search Results for author:
Found 28 papers, 16 papers with code
2024 BRAVO Challenge Track 1 1st Place Report: Evaluating Robustness of Vision Foundation Models for Semantic Segmentation
In this report, we present our solution for Track 1 of the 2024 BRAVO Challenge, where a model is trained on Cityscapes and its robustness is evaluated on several out-of-distribution datasets.
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.
Task-aligned Part-aware Panoptic Segmentation through Joint Object-Part Representations
However, their part-level predictions are not linked to individual parent objects.
Exploring the Benefits of Vision Foundation Models for Unsupervised Domain Adaptation
These results underscore the significant benefits of combining VFMs with UDA, setting new standards and baselines for Unsupervised Domain Adaptation in semantic segmentation.
ALGM: Adaptive Local-then-Global Token Merging for Efficient Semantic Segmentation with Plain Vision Transformers
This work presents Adaptive Local-then-Global Merging (ALGM), a token reduction method for semantic segmentation networks that use plain Vision Transformers.
How to Benchmark Vision Foundation Models for Semantic Segmentation?
The benchmarking setup recommended in this paper enables a performance analysis of VFMs for semantic segmentation.
Content-aware Token Sharing for Efficient Semantic Segmentation with Vision Transformers
This paper introduces Content-aware Token Sharing (CTS), a token reduction approach that improves the computational efficiency of semantic segmentation networks that use Vision Transformers (ViTs).
Intra-Batch Supervision for Panoptic Segmentation on High-Resolution Images
Unified panoptic segmentation methods are achieving state-of-the-art results on several datasets.
Ranked #5 on
Panoptic Segmentation
on Mapillary val
Off-Policy Action Anticipation in Multi-Agent Reinforcement Learning
Learning anticipation in Multi-Agent Reinforcement Learning (MARL) is a reasoning paradigm where agents anticipate the learning steps of other agents to improve cooperation among themselves.
Unified Perception: Efficient Depth-Aware Video Panoptic Segmentation with Minimal Annotation Costs
Furthermore, we show that our tracking strategies are effective for long-term object association on KITTI-STEP, achieving an STQ of 59. 1 which exceeded the performance of state-of-the-art methods that employ the same backbone network.
Depth-aware Video Panoptic Segmentation
Scene Understanding
+1
Training Semantic Segmentation on Heterogeneous Datasets
We explore semantic segmentation beyond the conventional, single-dataset homogeneous training and bring forward the problem of Heterogeneous Training of Semantic Segmentation (HTSS).
Self-Supervised Road Layout Parsing with Graph Auto-Encoding
Aiming for higher-level scene understanding, this work presents a neural network approach that takes a road-layout map in bird's-eye-view as input, and predicts a human-interpretable graph that represents the road's topological layout.
Deep Adaptive Multi-Intention Inverse Reinforcement Learning
This paper presents a deep Inverse Reinforcement Learning (IRL) framework that can learn an a priori unknown number of nonlinear reward functions from unlabeled experts' demonstrations.
Exploiting Image Translations via Ensemble Self-Supervised Learning for Unsupervised Domain Adaptation
To exploit the advantage of using multiple image translations, we propose an ensemble learning approach, where three classifiers calculate their prediction by taking as input features of different image translations, making each classifier learn independently, with the purpose of combining their outputs by sparse Multinomial Logistic Regression.
Ranked #1 on
Domain Generalization
on WildDash
Part-aware Panoptic Segmentation
In this work, we introduce the new scene understanding task of Part-aware Panoptic Segmentation (PPS), which aims to understand a scene at multiple levels of abstraction, and unifies the tasks of scene parsing and part parsing.
Ranked #2 on
Image Segmentation
on Pascal Panoptic Parts
Image-Graph-Image Translation via Auto-Encoding
To overcome this, we are the first to present a self-supervised approach based on a fully-differentiable auto-encoder in which the bottleneck encodes the graph's nodes and edges.
Cityscapes-Panoptic-Parts and PASCAL-Panoptic-Parts datasets for Scene Understanding
In this technical report, we present two novel datasets for image scene understanding.
Fast Panoptic Segmentation Network
For lower resolutions of the Cityscapes dataset and for the Pascal VOC dataset, FPSNet runs at 22 and 35 frames per second, respectively.
Semantic Foreground Inpainting from Weak Supervision
Our approach is inherently more efficient than the previous two-stage state-of-the-art method, and outperforms it by a margin of 3% IoU for the inpainted foreground regions on Cityscapes.
Hallucinating Beyond Observation: Learning to Complete with Partial Observation and Unpaired Prior Knowledge
We propose a novel single-step training strategy that allows convolutional encoder-decoder networks that use skip connections, to complete partially observed data by means of hallucination.
Data Selection for training Semantic Segmentation CNNs with cross-dataset weak supervision
Training convolutional networks for semantic segmentation with strong (per-pixel) and weak (per-bounding-box) supervision requires a large amount of weakly labeled data.
On Boosting Semantic Street Scene Segmentation with Weak Supervision
We collect street scene images and weak labels from the immense Open Images dataset to generate the OpenScapes dataset, and we use this novel dataset to increase segmentation performance on two established per-pixel labeled datasets, Cityscapes and Vistas.
Single Network Panoptic Segmentation for Street Scene Understanding
Our network is evaluated on two street scene datasets: Cityscapes and Mapillary Vistas.
A Domain Agnostic Normalization Layer for Unsupervised Adversarial Domain Adaptation
We show that conventional normalization layers worsen the performance of current Unsupervised Adversarial Domain Adaption (UADA), which is a method to improve network performance on unlabeled datasets and the focus of our research.
Panoptic Segmentation with a Joint Semantic and Instance Segmentation Network
For instance segmentation, a Mask R-CNN type of architecture is used, while the semantic segmentation branch is augmented with a Pyramid Pooling Module.
Ranked #11 on
Panoptic Segmentation
on Mapillary val
Monocular Semantic Occupancy Grid Mapping with Convolutional Variational Encoder-Decoder Networks
In this work, we research and evaluate end-to-end learning of monocular semantic-metric occupancy grid mapping from weak binocular ground truth.
Ranked #2 on
Bird's-Eye View Semantic Segmentation
on nuScenes
(IoU veh - 224x480 - No vis filter - 100x50 at 0.25 metric)
Training of Convolutional Networks on Multiple Heterogeneous Datasets for Street Scene Semantic Segmentation
We propose a convolutional network with hierarchical classifiers for per-pixel semantic segmentation, which is able to be trained on multiple, heterogeneous datasets and exploit their semantic hierarchy.
Ranked #5 on
Semantic Segmentation
on KITTI Semantic Segmentation
Free-Space Detection with Self-Supervised and Online Trained Fully Convolutional Networks
Experiments show that the online training boosts performance with 5% when compared to offline training, both for Fmax and AP.
