Traditional domain adaptation addresses the task of adapting a model to a novel target domain under limited or no additional supervision. While tackling the input domain gap, the standard domain adaptation settings assume no domain change in the outp
ut space. In semantic prediction tasks, different datasets are often labeled according to different semantic taxonomies. In many real-world settings, the target domain task requires a different taxonomy than the one imposed by the source domain. We therefore introduce the more general taxonomy adaptive domain adaptation (TADA) problem, allowing for inconsistent taxonomies between the two domains. We further propose an approach that jointly addresses the image-level and label-level domain adaptation. On the label-level, we employ a bilateral mixed sampling strategy to augment the target domain, and a relabelling method to unify and align the label spaces. We address the image-level domain gap by proposing an uncertainty-rectified contrastive learning method, leading to more domain-invariant and class discriminative features. We extensively evaluate the effectiveness of our framework under different TADA settings: open taxonomy, coarse-to-fine taxonomy, and partially-overlapping taxonomy. Our framework outperforms previous state-of-the-art by a large margin, while capable of adapting to new target domain taxonomies.
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 with sounds. This work develops an approach for scene understanding pure
ly based on binaural sounds. The considered tasks include predicting the semantic masks of sound-making objects, the motion of sound-making objects, and the depth map of the scene. To this aim, we propose a novel sensor setup and record a new audio-visual dataset of street scenes with eight professional binaural microphones and a 360-degree camera. The co-existence of visual and audio cues is leveraged for supervision transfer. In particular, we employ a cross-modal distillation framework that consists of multiple vision teacher methods and a sound student method -- the student method is trained to generate the same results as the teacher methods do. This way, the auditory system can be trained without using human annotations. To further boost the performance, we propose another novel auxiliary task, coined Spatial Sound Super-Resolution, to increase the directional resolution of sounds. We then formulate the four tasks into one end-to-end trainable multi-tasking network aiming to boost the overall performance. Experimental results show that 1) our method achieves good results for all four tasks, 2) the four tasks are mutually beneficial -- training them together achieves the best performance, 3) the number and orientation of microphones are both important, and 4) features learned from the standard spectrogram and features obtained by the classic signal processing pipeline are complementary for auditory perception tasks. The data and code are released.
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 highly labor-intensive process. To address this issue, we present a fr
amework for semi-supervised and domain-adaptive semantic segmentation, which is enhanced by self-supervised monocular depth estimation (SDE) trained only on unlabeled image sequences. In particular, we utilize SDE as an auxiliary task comprehensively across the entire learning framework: First, we automatically select the most useful samples to be annotated for semantic segmentation based on the correlation of sample diversity and difficulty between SDE and semantic segmentation. Second, we implement a strong data augmentation by mixing images and labels using the geometry of the scene. Third, we transfer knowledge from features learned during SDE to semantic segmentation by means of transfer and multi-task learning. And fourth, we exploit additional labeled synthetic data with Cross-Domain DepthMix and Matching Geometry Sampling to align synthetic and real data. We validate the proposed model on the Cityscapes dataset, where all four contributions demonstrate significant performance gains, and achieve state-of-the-art results for semi-supervised semantic segmentation as well as for semi-supervised domain adaptation. In particular, with only 1/30 of the Cityscapes labels, our method achieves 92% of the fully-supervised baseline performance and even 97% when exploiting additional data from GTA. The source code is available at https://github.com/lhoyer/improving_segmentation_with_selfsupervised_depth.
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 demand dense on-policy supervision. On the contrary, automated experts that
leverage privileged information can efficiently generate large scale on-policy and off-policy demonstrations. However, existing automated experts for urban driving make heavy use of hand-crafted rules and perform suboptimally even on driving simulators, where ground-truth information is available. To address these issues, we train a reinforcement learning expert that maps birds-eye view images to continuous low-level actions. While setting a new performance upper-bound on CARLA, our expert is also a better coach that provides informative supervision signals for imitation learning agents to learn from. Supervised by our reinforcement learning coach, a baseline end-to-end agent with monocular camera-input achieves expert-level performance. Our end-to-end agent achieves a 78% success rate while generalizing to a new town and new weather on the NoCrash-dense benchmark and state-of-the-art performance on the more challenging CARLA LeaderBoard.
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 recent approaches for 3D multi object tracking (MOT) from LIDAR use obje
ct dynamics together with a set of handcrafted features to match detections of objects. However, manually designing such features and heuristics is cumbersome and often leads to suboptimal performance. In this work, we instead strive towards a unified and learning based approach to the 3D MOT problem. We design a graph structure to jointly process detection and track states in an online manner. To this end, we employ a Neural Message Passing network for data association that is fully trainable. Our approach provides a natural way for track initialization and handling of false positive detections, while significantly improving track stability. We show the merit of the proposed approach on the publicly available nuScenes dataset by achieving state-of-the-art performance of 65.6% AMOTA and 58% fewer ID-switches.
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 highly labor-intensive process. To address this issue, we present a fr
amework for semi-supervised semantic segmentation, which is enhanced by self-supervised monocular depth estimation from unlabeled image sequences. In particular, we propose three key contributions: (1) We transfer knowledge from features learned during self-supervised depth estimation to semantic segmentation, (2) we implement a strong data augmentation by blending images and labels using the geometry of the scene, and (3) we utilize the depth feature diversity as well as the level of difficulty of learning depth in a student-teacher framework to select the most useful samples to be annotated for semantic segmentation. We validate the proposed model on the Cityscapes dataset, where all three modules demonstrate significant performance gains, and we achieve state-of-the-art results for semi-supervised semantic segmentation. The implementation is available at https://github.com/lhoyer/improving_segmentation_with_selfsupervised_depth.
Object recognition advances very rapidly these days. One challenge is to generalize existing methods to new domains, to more classes and/or to new data modalities. In order to avoid annotating one dataset for each of these new cases, one needs to com
bine and reuse existing datasets that may belong to different domains, have partial annotations, and/or have different data modalities. This paper treats this task as a multi-source domain adaptation and label unification (mDALU) problem and proposes a novel method for it. Our method consists of a partially-supervised adaptation stage and a fully-supervised adaptation stage. In the former, partial knowledge is transferred from multiple source domains to the target domain and fused therein. Negative transfer between unmatched label space is mitigated via three new modules: domain attention, uncertainty maximization and attention-guided adversarial alignment. In the latter, knowledge is transferred in the unified label space after a label completion process with pseudo-labels. We verify the method on three different tasks, image classification, 2D semantic image segmentation, and joint 2D-3D semantic segmentation. Extensive experiments show that our method outperforms all competing methods significantly.
This work studies the problem of predicting the sequence of future actions for surround vehicles in real-world driving scenarios. To this aim, we make three main contributions. The first contribution is an automatic method to convert the trajectories
recorded in real-world driving scenarios to action sequences with the help of HD maps. The method enables automatic dataset creation for this task from large-scale driving data. Our second contribution lies in applying the method to the well-known traffic agent tracking and prediction dataset Argoverse, resulting in 228,000 action sequences. Additionally, 2,245 action sequences were manually annotated for testing. The third contribution is to propose a novel action sequence prediction method by integrating past positions and velocities of the traffic agents, map information and social context into a single end-to-end trainable neural network. Our experiments prove the merit of the data creation method and the value of the created dataset - prediction performance improves consistently with the size of the dataset and shows that our action prediction method outperforms comparing models.
This work addresses the problem of semantic scene understanding under foggy road conditions. Although marked progress has been made in semantic scene understanding over the recent years, it is mainly concentrated on clear weather outdoor scenes. Exte
nding semantic segmentation methods to adverse weather conditions like fog is crucially important for outdoor applications such as self-driving cars. In this paper, we propose a novel method, which uses purely synthetic data to improve the performance on unseen real-world foggy scenes captured in the streets of Zurich and its surroundings. Our results highlight the potential and power of photo-realistic synthetic images for training and especially fine-tuning deep neural nets. Our contributions are threefold, 1) we created a purely synthetic, high-quality foggy dataset of 25,000 unique outdoor scenes, that we call Foggy Synscapes and plan to release publicly 2) we show that with this data we outperform previous approaches on real-world foggy test data 3) we show that a combination of our data and previously used data can even further improve the performance on real-world foggy data.
Comprehensive semantic segmentation is one of the key components for robust scene understanding and a requirement to enable autonomous driving. Driven by large scale datasets, convolutional neural networks show impressive results on this task. Howeve
r, a segmentation algorithm generalizing to various scenes and conditions would require an enormously diverse dataset, making the labour intensive data acquisition and labeling process prohibitively expensive. Under the assumption of structural similarities between segmentation maps, domain adaptation promises to resolve this challenge by transferring knowledge from existing, potentially simulated datasets to new environments where no supervision exists. While the performance of this approach is contingent on the concept that neural networks learn a high level understanding of scene structure, recent work suggests that neural networks are biased towards overfitting to texture instead of learning structural and shape information. Considering the ideas underlying semantic segmentation, we employ random image stylization to augment the training dataset and propose a training procedure that facilitates texture underfitting to improve the performance of domain adaptation. In experiments with supervised as well as unsupervised methods for the task of synthetic-to-real domain adaptation, we show that our approach outperforms conventional training methods.
