Barbara Caputo

Recognizing human activities from visual inputs, particularly through a first-person viewpoint, is essential for enabling robots to replicate human behavior. Egocentric vision, characterized by cameras worn by observers, captures diverse changes in illumination, viewpoint, and environment. This variability leads to a notable drop in the performance of Egocentric Action Recognition models when tested in environments not seen during training. In this paper, we tackle these challenges by proposing a domain generalization approach for Egocentric Action Recognition. Our insight is that action sequences often reflect consistent user intent across visual domains. By leveraging action sequences, we aim to enhance the model's generalization ability across unseen environments. Our proposed method, named SeqDG, introduces a visual-text sequence reconstruction objective (SeqRec) that uses contextual cues from both text and visual inputs to reconstruct the central action of the sequence. Additionally, we enhance the model's robustness by training it on mixed sequences of actions from different domains (SeqMix). We validate SeqDG on the EGTEA and EPIC-KITCHENS-100 datasets. Results on EPIC-KITCHENS-100, show that SeqDG leads to +2.4% relative average improvement in cross-domain action recognition in unseen environments, and on EGTEA the model achieved +0.6% Top-1 accuracy over SOTA in intra-domain action recognition.

Statistical heterogeneity in Federated Learning (FL) often leads to client drift and biased local solutions. Priorwork in the literature shows that client drift particularly affects the parameters of the classification layer, hindering both convergence and accuracy. While Personalized FL (PFL) addresses this by allowing client-specific models, it can overlook valuable global knowledge. This paper introduces Federated Recursive Ridge Regression (Fed3R), a fast and efficient method to construct a closed-form classifier that effectively incorporates global knowledge while being inherently robust to statistical heterogeneity. Fed3R leverages a pre-trained feature extractor and a recursive ridge regression formulation to achieve exact aggregation of local classifiers and recover the centralized solution. We demonstrate that Fed3R serves as a robust initialization for further fine-tuning with various FL and PFL algorithms, accelerating convergence and boosting performance. Furthermore, we propose Only Local Labels (OLL), a novel PFL technique that simplifies local classifiers by focusing only on locally relevant classes, preventing misclassifications and improving efficiency. Our empirical evaluation on real-world cross-device datasets shows that Fed3R, combined with OLL, significantly improves performance and reduces training costs in heterogeneous FL and PFL scenarios.

Human activities exhibit a strong correlation between actions and the places where these are performed, such as washing something at a sink. More specifically, in daily living environments we may identify particular locations, hereinafter named activity-centric zones, which may afford a set of homogeneous actions. Their knowledge can serve as a prior to favor vision models to recognize human activities. However, the appearance of these zones is scene-specific, limiting the transferability of this prior information to unfamiliar areas and domains. This problem is particularly relevant in egocentric vision, where the environment takes up most of the image, making it even more difficult to separate the action from the context. In this paper, we discuss the importance of decoupling the domain-specific appearance of activity-centric zones from their universal, domain-agnostic representations, and show how the latter can improve the cross-domain transferability of Egocentric Action Recognition (EAR) models. We validate our solution on the EPIC-Kitchens-100 and Argo1M datasets

Segmenting unknown or anomalous object instances is a critical task in autonomous driving applications, and it is approached traditionally as a per-pixel classification problem. However, reasoning individually about each pixel without considering their contextual semantics results in high uncertainty around the objects’ boundaries and numerous false positives. We propose a paradigm change by shifting from a per-pixel classification to a mask classification. Our mask-based method, Mask2Anomaly, demonstrates the feasibility of integrating a mask-classification architecture to jointly address anomaly segmentation, open-set semantic segmentation, and open-set panoptic segmentation. Mask2Anomaly includes several technical novelties that are designed to improve the detection of anomalies/unknown objects: i) a global masked attention module to focus individually on the foreground and background regions; ii) a mask contrastive learning that maximizes the margin between an anomaly and known classes; iii) a mask refinement solution to reduce false positives; and iv) a novel approach to mine unknown instances based on the mask- architecture properties. By comprehensive qualitative and qualitative evaluation, we show Mask2Anomaly achieves new state-of-the-art results across the benchmarks of anomaly segmentation, open-set semantic segmentation, and open-set panoptic segmentation.

Federated Learning (FL) allows training machine learning models in privacy-constrained scenarios by enabling the cooperation of edge devices without requiring local data sharing. This approach raises several challenges due to the different statistical distribution of the local datasets and the clients’ computational heterogeneity. In particular, the presence of highly non-i.i.d. data severely impairs both the performance of the trained neural network and its convergence rate, increasing the number of communication rounds required to reach centralized performance. As a solution, we propose FedSeq, a novel framework leveraging the sequential training of subgroups of heterogeneous clients, i.e., superclients, to learn more robust models before the server-side averaging step. Given a fixed budget of communication rounds, we show that FedSeq outperforms or match several state-of-the-art federated algorithms in terms of final performance and speed of convergence. Our method can be easily integrated with other approaches available in the literature, and empirical results show that combining existing algorithms with FedSeq further improves its final performance and convergence speed. We evaluate our method across multiple FL benchmarks, establishing its effectiveness in both i.i.d. and non-i.i.d. scenarios. Lastly, we highlight that the sequential training introduced here does not introduce additional privacy concerns when compared to the de facto standard, FedAvg.

Multi-modal learning has gained significant attention due to its ability to enhance machine learning algorithms. However, it brings challenges related to modality heterogeneity and domain shift. In this work, we address these challenges by proposing a new approach called Relative Norm Alignment (RNA) loss. RNA loss exploits the observation that variations in marginal distributions between modalities manifest as discrepancies in their mean feature norms, and rebalances feature norms across domains, modalities, and classes. This rebalancing improves the accuracy of models on test data from unseen (“target”) distributions. In the context of Unsupervised Domain Adaptation (UDA), we use unlabeled target data to enhance feature transferability. We achieve this by combining RNA loss with an adversarial domain loss and an Information Maximization term that regularizes predictions on target data. We present a comprehensive analysis and ablation of our method for both Domain Generalization and UDA settings, testing our approach on different modalities for tasks such as first and third person action recognition, object recognition, and fatigue detection. Experimental results show that our approach achieves competitive or state-of-the-art performance on the proposed benchmarks, showing the versatility and effectiveness of our method in a wide range of applications.

Visual Place Recognition aims at recognizing previously visited places by relying on visual clues, and it is used in robotics applications for SLAM and localization. Since typically a mobile robot has access to a continuous stream of frames, this task is naturally cast as a sequence-to-sequence localization problem. Nevertheless, obtaining sequences of labelled data is much more expensive than collecting isolated images, which can be done in an automated way with little supervision. As a mitigation to this problem, we propose a novel Joint Image and Sequence Training (JIST) protocol that leverages large uncurated sets of images through a multi-task learning framework. With JIST we also introduce SeqGeM, an aggregation layer that revisits the popular GeM pooling to produce a single robust and compact embedding from a sequence of single-frame embeddings. We show that our model is able to outperform previous state of the art while being faster, using eight times smaller descriptors, having a lighter architecture and allowing to process sequences of various lengths.

We propose FedDrive v2, an extension of the Federated Learning benchmark for Semantic Segmentation in Autonomous Driving. While the first version aims at studying the effect of domain shift of the visual features across clients, in this work, we focus on the distribution skewness of the labels. We propose six new federated scenarios to investigate how label skewness affects the performance of segmentation models and compare it with the effect of domain shift. Finally, we study the impact of using the domain information during testing. Official website: https://feddrive.github.io

We propose and address a new generalisation problem: can a model trained for action recognition successfully classify actions when they are performed within a previously unseen scenario and in a previously unseen location? To answer this question, we introduce the Action Recognition Generalisation Over scenarios and locations dataset (ARGO1M), which contains 1.1M video clips from the large-scale Ego4D dataset, across 10 scenarios and 13 locations. We demonstrate recognition models struggle to generalise over 10 proposed test splits, each of an unseen scenario in an unseen location. We thus propose CIR, a method to represent each video as a Cross-Instance Reconstruction of videos from other domains. Reconstructions are paired with text narrations to guide the learning of a domain generalisable representation. We provide extensive analysis and ablations on ARGO1M that show CIR outperforms prior domain generalisation works on all test splits. Code and data: https://chiaraplizz.github.io/what-can-a-cook/.