1.4k citations · 3.1k across the 72 of their papers we have counts for
14 papers · 1 filter
Decoupling Zero-Shot Semantic Segmentation
Jian Ding, Nan Xue, Gui-Song Xia +1
Zero-shot semantic segmentation (ZS3) aims to segment the novel categories that have not been seen in the training. Existing works formulate ZS3 as a pixel-level zeroshot classific…
CoSSL: Co-Learning of Representation and Classifier for Imbalanced Semi-Supervised Learning
Yue Fan, Dengxin Dai, Anna Kukleva +1
In this paper, we propose a novel co-learning framework (CoSSL) with decoupled representation learning and classifier learning for imbalanced SSL. To handle the data imbalance, we…
Both Style and Fog Matter: Cumulative Domain Adaptation for Semantic Foggy Scene Understanding
Xianzheng Ma, Zhixiang Wang, Yacheng Zhan +4
Although considerable progress has been made in semantic scene understanding under clear weather, it is still a tough problem under adverse weather conditions, such as dense fog, d…
DAFormer: Improving Network Architectures and Training Strategies for Domain-Adaptive Semantic Segmentation
Lukas Hoyer, Dengxin Dai, Luc Van Gool
As acquiring pixel-wise annotations of real-world images for semantic segmentation is a costly process, a model can instead be trained with more accessible synthetic data and adapt…
TACS: Taxonomy Adaptive Cross-Domain Semantic Segmentation
Rui Gong, Martin Danelljan, Dengxin Dai +4
Traditional domain adaptive semantic segmentation addresses the task of adapting a model to a novel target domain under limited or no additional supervision. While tackling the inp…
Binaural SoundNet: Predicting Semantics, Depth and Motion with Binaural Sounds
Dengxin Dai, Arun Balajee Vasudevan, Jiri Matas +1
Humans can robustly recognize and localize objects by using visual and/or auditory cues. While machines are able to do the same with visual data already, less work has been done wi…
Improving Semi-Supervised and Domain-Adaptive Semantic Segmentation with Self-Supervised Depth Estimation
Lukas Hoyer, Dengxin Dai, Qin Wang +2
Training deep networks for semantic segmentation requires large amounts of labeled training data, which presents a major challenge in practice, as labeling segmentation masks is a…
Fog Simulation on Real LiDAR Point Clouds for 3D Object Detection in Adverse Weather
Martin Hahner, Christos Sakaridis, Dengxin Dai +1
This work addresses the challenging task of LiDAR-based 3D object detection in foggy weather. Collecting and annotating data in such a scenario is very time, labor and cost intensi…
End-to-End Urban Driving by Imitating a Reinforcement Learning Coach
Zhejun Zhang, Alexander Liniger, Dengxin Dai +2
End-to-end approaches to autonomous driving commonly rely on expert demonstrations. Although humans are good drivers, they are not good coaches for end-to-end algorithms that deman…
Learnable Online Graph Representations for 3D Multi-Object Tracking
Jan-Nico Zaech, Dengxin Dai, Alexander Liniger +2
Tracking of objects in 3D is a fundamental task in computer vision that finds use in a wide range of applications such as autonomous driving, robotics or augmented reality. Most re…
Domain Adaptive Semantic Segmentation with Self-Supervised Depth Estimation
Qin Wang, Dengxin Dai, Lukas Hoyer +2
Domain adaptation for semantic segmentation aims to improve the model performance in the presence of a distribution shift between source and target domain. Leveraging the supervisi…
ACDC: The Adverse Conditions Dataset with Correspondences for Robust Semantic Driving Scene Perception
Christos Sakaridis, Haoran Wang, Ke Li +6
Level-5 driving automation requires a robust visual perception system that can parse input images under any condition. However, existing driving datasets for dense semantic percept…
Spectral Tensor Train Parameterization of Deep Learning Layers
Anton Obukhov, Maxim Rakhuba, Alexander Liniger +4
We study low-rank parameterizations of weight matrices with embedded spectral properties in the Deep Learning context. The low-rank property leads to parameter efficiency and permi…
Hyperspectral Image Super-Resolution with Spectral Mixup and Heterogeneous Datasets
Ke Li, Dengxin Dai, Ender Konukoglu +1
This work studies Hyperspectral image (HSI) super-resolution (SR). HSI SR is characterized by high-dimensional data and a limited amount of training examples. This exacerbates the…