On advantages of Mask-level Recognition for Open-set Segmentation in the Wild

Most dense recognition methods bring a separate decision in each particular pixel. This approach still delivers competitive performance in usual closed-set setups with small taxonomies. However, important applications in the wild typically require strong open-set performance and large numbers of known classes. We show that these two demanding setups greatly benefit from mask-level predictions, even in the case of non-finetuned baseline models. Moreover, we propose an alternative formulation of dense recognition uncertainty that effectively reduces false positive responses at semantic borders. The proposed formulation produces a further improvement over a very strong baseline and sets the new state of the art in dense anomaly detection without training on negative data. Our contributions also lead to a performance improvement in a recent open-set panoptic setup. In-depth experiments confirm that our approach succeeds due to implicit aggregation of pixel-level cues into mask-level predictions.

Weakly supervised training of universal visual concepts for multi-domain semantic segmentation

Deep supervised models have an unprecedented capacity to absorb large quantities of training data. Hence, training on multiple datasets becomes a method of choice towards strong generalization in usual scenes and graceful performance degradation in edge cases. Unfortunately, different datasets often have incompatible labels. For instance, the Cityscapes road class subsumes all driving surfaces, while Vistas defines separate classes for road markings, manholes etc. Furthermore, many datasets have overlapping labels. For instance, pickups are labeled as trucks in VIPER, cars in Vistas, and vans in ADE20k. We address this challenge by considering labels as unions of universal visual concepts. This allows seamless and principled learning on multi-domain dataset collections without requiring any relabeling effort. Our method achieves competitive within-dataset and cross-dataset generalization, as well as ability to learn visual concepts which are not separately labeled in any of the training datasets. Experiments reveal competitive or state-of-the-art performance on two multi-domain dataset collections and on the WildDash 2 benchmark.

Panoptic SwiftNet: Pyramidal Fusion for Real-time Panoptic Segmentation

Dense panoptic prediction is a key ingredient in many existing applications such as autonomous driving, automated warehouses or agri-robotics. However, most of these applications leverage the recovered dense semantics as an input to visual closed-loop control. Hence, practical deployments require real-time inference over large input resolutions on embedded hardware. These requirements call for computationally efficient approaches which deliver high accuracy with limited computational resources. We propose to achieve this goal by trading-off backbone capacity for multi-scale feature extraction. In comparison with contemporaneous approaches to panoptic segmentation, the main novelties of our method are scale-equivariant feature extraction and cross-scale upsampling through pyramidal fusion. Our best model achieves 55.9% PQ on Cityscapes val at 60 FPS on full resolution 2MPx images and RTX3090 with FP16 Tensor RT optimization.

Multi-domain semantic segmentation with overlapping labels

Deep supervised models have an unprecedented capacity to absorb large quantities of training data. Hence, training on many datasets becomes a method of choice towards graceful degradation in unusual scenes. Unfortunately, different datasets often use incompatible labels. For instance, the Cityscapes road class subsumes all driving surfaces, while Vistas defines separate classes for road markings, manholes etc. We address this challenge by proposing a principled method for seamless learning on datasets with overlapping classes based on partial labels and probabilistic loss. Our method achieves competitive within-dataset and cross-dataset generalization, as well as ability to learn visual concepts which are not separately labeled in any of the training datasets. Experiments reveal competitive or state-of-the-art performance on two multi-domain dataset collections and on the WildDash 2 benchmark.

Joint Forecasting of Features and Feature Motion for Dense Semantic Future Prediction

We present a novel dense semantic forecasting approach which is applicable to a variety of architectures and tasks. The approach consists of two modules. Feature-to-motion (F2M) module forecasts a dense deformation field which warps past features into their future positions. Feature-to-feature (F2F) module regresses the future features directly and is therefore able to account for emergent scenery. The compound F2MF approach decouples effects of motion from the effects of novelty in a task-agnostic manner. We aim to apply F2MF forecasting to the most subsampled and the most abstract representation of a desired single-frame model. Our implementations take advantage of deformable convolutions and pairwise correlation coefficients across neighbouring time instants. We perform experiments on three dense prediction tasks: semantic segmentation, instance-level segmentation, and panoptic segmentation. The results reveal state-of-the-art forecasting accuracy across all three modalities on the Cityscapes dataset.

Multimodal semantic forecasting based on conditional generation of future features

This paper considers semantic forecasting in road-driving scenes. Most existing approaches address this problem as deterministic regression of future features or future predictions given observed frames. However, such approaches ignore the fact that future can not always be guessed with certainty. For example, when a car is about to turn around a corner, the road which is currently occluded by buildings may turn out to be either free to drive, or occupied by people, other vehicles or roadworks. When a deterministic model confronts such situation, its best guess is to forecast the most likely outcome. However, this is not acceptable since it defeats the purpose of forecasting to improve security. It also throws away valuable training data, since a deterministic model is unable to learn any deviation from the norm. We address this problem by providing more freedom to the model through allowing it to forecast different futures. We propose to formulate multimodal forecasting as sampling of a multimodal generative model conditioned on the observed frames. Experiments on the Cityscapes dataset reveal that our multimodal model outperforms its deterministic counterpart in short-term forecasting while performing slightly worse in the mid-term case.

Multi-domain semantic segmentation with pyramidal fusion

We present our submission to the semantic segmentation contest of the Robust Vision Challenge held at ECCV 2020. The contest requires submitting the same model to seven benchmarks from three different domains. Our approach is based on the SwiftNet architecture with pyramidal fusion. We address inconsistent taxonomies with a single-level 193-dimensional softmax output. We strive to train with large batches in order to stabilize optimization of a hard recognition problem, and to favour smooth evolution of batchnorm statistics. We achieve this by implementing a custom backward step through log-sum-prob loss, and by using small crops before freezing the population statistics. Our model ranks first on the RVC semantic segmentation challenge as well as on the WildDash 2 leaderboard. This suggests that pyramidal fusion is competitive not only for efficient inference with lightweight backbones, but also in large-scale setups for multi-domain application.

Single Level Feature-to-Feature Forecasting with Deformable Convolutions

Future anticipation is of vital importance in autonomous driving and other decision-making systems. We present a method to anticipate semantic segmentation of future frames in driving scenarios based on feature-to-feature forecasting. Our method is based on a semantic segmentation model without lateral connections within the upsampling path. Such design ensures that the forecasting addresses only the most abstract features on a very coarse resolution. We further propose to express feature-to-feature forecasting with deformable convolutions. This increases the modelling power due to being able to represent different motion patterns within a single feature map. Experiments show that our models with deformable convolutions outperform their regular and dilated counterparts while minimally increasing the number of parameters. Our method achieves state of the art performance on the Cityscapes validation set when forecasting nine timesteps into the future.