Event cameras are novel bio-inspired sensors, which asynchronously capture pixel-level intensity changes in the form of "events". Due to their sensing mechanism, event cameras have little to no motion blur, a very high temporal resolution and require significantly less power and memory than traditional frame-based cameras. These characteristics make them a perfect fit to several real-world applications such as egocentric action recognition on wearable devices, where fast camera motion and limited power challenge traditional vision sensors. However, the ever-growing field of event-based vision has, to date, overlooked the potential of event cameras in such applications. In this paper, we show that event data is a very valuable modality for egocentric action recognition. To do so, we introduce N-EPIC-Kitchens, the first event-based camera extension of the large-scale EPIC-Kitchens dataset. In this context, we propose two strategies: (i) directly processing event-camera data with traditional video-processing architectures (E$^2$(GO)) and (ii) using event-data to distill optical flow information (E$^2$(GO)MO). On our proposed benchmark, we show that event data provides a comparable performance to RGB and optical flow, yet without any additional flow computation at deploy time, and an improved performance of up to 4% with respect to RGB only information.
Although existing semantic segmentation approaches achieve impressive results, they still struggle to update their models incrementally as new categories are uncovered. Furthermore, pixel-by-pixel annotations are expensive and time-consuming. This paper proposes a novel framework for Weakly Incremental Learning for Semantic Segmentation, that aims at learning to segment new classes from cheap and largely available image-level labels. As opposed to existing approaches, that need to generate pseudo-labels offline, we use an auxiliary classifier, trained with image-level labels and regularized by the segmentation model, to obtain pseudo-supervision online and update the model incrementally. We cope with the inherent noise in the process by using soft-labels generated by the auxiliary classifier. We demonstrate the effectiveness of our approach on the Pascal VOC and COCO datasets, outperforming offline weakly-supervised methods and obtaining results comparable with incremental learning methods with full supervision.
Semantic segmentation models have reached remarkable performance across various tasks. However, this performance is achieved with extremely large models, using powerful computational resources and without considering training and inference time. Real-world applications, on the other hand, necessitate models with minimal memory demands, efficient inference speed, and executable with low-resources embedded devices, such as self-driving vehicles. In this paper, we look at the challenge of real-time semantic segmentation across domains, and we train a model to act appropriately on real-world data even though it was trained on a synthetic realm. We employ a new lightweight and shallow discriminator that was specifically created for this purpose. To the best of our knowledge, we are the first to present a real-time adversarial approach for assessing the domain adaption problem in semantic segmentation. We tested our framework in the two standard protocol: GTA5 to Cityscapes and SYNTHIA to Cityscapes. Code is available at: https://github.com/taveraantonio/RTDA.
In this paper we consider the task of semantic segmentation in autonomous driving applications. Specifically, we consider the cross-domain few-shot setting where training can use only few real-world annotated images and many annotated synthetic images. In this context, aligning the domains is made more challenging by the pixel-wise class imbalance that is intrinsic in the segmentation and that leads to ignoring the underrepresented classes and overfitting the well represented ones. We address this problem with a novel framework called Pixel-By-Pixel Cross-Domain Alignment (PixDA). We propose a novel pixel-by-pixel domain adversarial loss following three criteria: (i) align the source and the target domain for each pixel, (ii) avoid negative transfer on the correctly represented pixels, and (iii) regularize the training of infrequent classes to avoid overfitting. The pixel-wise adversarial training is assisted by a novel sample selection procedure, that handles the imbalance between source and target data, and a knowledge distillation strategy, that avoids overfitting towards the few target images. We demonstrate on standard synthetic-to-real benchmarks that PixDA outperforms previous state-of-the-art methods in (1-5)-shot settings.
First person action recognition is becoming an increasingly researched area thanks to the rising popularity of wearable cameras. This is bringing to light cross-domain issues that are yet to be addressed in this context. Indeed, the information extracted from learned representations suffers from an intrinsic "environmental bias". This strongly affects the ability to generalize to unseen scenarios, limiting the application of current methods to real settings where labeled data are not available during training. In this work, we introduce the first domain generalization approach for egocentric activity recognition, by proposing a new audio-visual loss, called Relative Norm Alignment loss. It re-balances the contributions from the two modalities during training, over different domains, by aligning their feature norm representations. Our approach leads to strong results in domain generalization on both EPIC-Kitchens-55 and EPIC-Kitchens-100, as demonstrated by extensive experiments, and can be extended to work also on domain adaptation settings with competitive results.
In this paper we propose a novel method for image matching based on dense local features and tailored for visual geolocalization. Dense local features matching is robust against changes in illumination and occlusions, but not against viewpoint shifts which are a fundamental aspect of geolocalization. Our method, called GeoWarp, directly embeds invariance to viewpoint shifts in the process of extracting dense features. This is achieved via a trainable module which learns from the data an invariance that is meaningful for the task of recognizing places. We also devise a new self-supervised loss and two new weakly supervised losses to train this module using only unlabeled data and weak labels. GeoWarp is implemented efficiently as a re-ranking method that can be easily embedded into pre-existing visual geolocalization pipelines. Experimental validation on standard geolocalization benchmarks demonstrates that GeoWarp boosts the accuracy of state-of-the-art retrieval architectures. The code and trained models are available at https://github.com/gmberton/geo_warp
Vision systems trained in closed-world scenarios will inevitably fail when presented with new environmental conditions, new data distributions and novel classes at deployment time. How to move towards open-world learning is a long standing research question, but the existing solutions mainly focus on specific aspects of the problem (single domain Open-Set, multi-domain Closed-Set), or propose complex strategies which combine multiple losses and manually tuned hyperparameters. In this work we tackle multi-source Open-Set domain adaptation by introducing HyMOS: a straightforward supervised model that exploits the power of contrastive learning and the properties of its hyperspherical feature space to correctly predict known labels on the target, while rejecting samples belonging to any unknown class. HyMOS includes a tailored data balancing to enforce cross-source alignment and introduces style transfer among the instance transformations of contrastive learning for source-target adaptation, avoiding the risk of negative transfer. Finally a self-training strategy refines the model without the need for handcrafted thresholds. We validate our method over three challenging datasets and provide an extensive quantitative and qualitative experimental analysis. The obtained results show that HyMOS outperforms several Open-Set and universal domain adaptation approaches, defining the new state-of-the-art.
Robotic visual systems operating in the wild must act in unconstrained scenarios, under different environmental conditions while facing a variety of semantic concepts, including unknown ones. To this end, recent works tried to empower visual object recognition methods with the capability to i) detect unseen concepts and ii) extended their knowledge over time, as images of new semantic classes arrive. This setting, called Open World Recognition (OWR), has the goal to produce systems capable of breaking the semantic limits present in the initial training set. However, this training set imposes to the system not only its own semantic limits, but also environmental ones, due to its bias toward certain acquisition conditions that do not necessarily reflect the high variability of the real-world. This discrepancy between training and test distribution is called domain-shift. This work investigates whether OWR algorithms are effective under domain-shift, presenting the first benchmark setup for assessing fairly the performances of OWR algorithms, with and without domain-shift. We then use this benchmark to conduct analyses in various scenarios, showing how existing OWR algorithms indeed suffer a severe performance degradation when train and test distributions differ. Our analysis shows that this degradation is only slightly mitigated by coupling OWR with domain generalization techniques, indicating that the mere plug-and-play of existing algorithms is not enough to recognize new and unknown categories in unseen domains. Our results clearly point toward open issues and future research directions, that need to be investigated for building robot visual systems able to function reliably under these challenging yet very real conditions. Code available at https://github.com/DarioFontanel/OWR-VisualDomains
In this report, we describe the technical details of our submission to the EPIC-Kitchens-100 Unsupervised Domain Adaptation (UDA) Challenge in Action Recognition. To tackle the domain-shift which exists under the UDA setting, we first exploited a recent Domain Generalization (DG) technique, called Relative Norm Alignment (RNA). It consists in designing a model able to generalize well to any unseen domain, regardless of the possibility to access target data at training time. Then, in a second phase, we extended the approach to work on unlabelled target data, allowing the model to adapt to the target distribution in an unsupervised fashion. For this purpose, we included in our framework existing UDA algorithms, such as Temporal Attentive Adversarial Adaptation Network (TA3N), jointly with new multi-stream consistency losses, namely Temporal Hard Norm Alignment (T-HNA) and Min-Entropy Consistency (MEC). Our submission (entry 'plnet') is visible on the leaderboard and it achieved the 1st position for 'verb', and the 3rd position for both 'noun' and 'action'.