Recent works showed that Generative Adversarial Networks (GANs) can be successfully applied in unsupervised domain adaptation, where, given a labeled source dataset and an unlabeled target dataset, the goal is to train powerful classifiers for the target samples. In particular, it was shown that a GAN objective function can be used to learn target features indistinguishable from the source ones. In this work, we extend this framework by (i) forcing the learned feature extractor to be domain-invariant, and (ii) training it through data augmentation in the feature space, namely performing feature augmentation. While data augmentation in the image space is a well established technique in deep learning, feature augmentation has not yet received the same level of attention. We accomplish it by means of a feature generator trained by playing the GAN minimax game against source features. Results show that both enforcing domain-invariance and performing feature augmentation lead to superior or comparable performance to state-of-the-art results in several unsupervised domain adaptation benchmarks.

Abstract-The emergence of new wearable technologies such as action cameras and smart-glasses has increased the interest of computer vision scientists in the First Person perspective. Nowadays, this field is attracting attention and investments of companies aiming to develop commercial devices with First Person Vision recording capabilities. Due to this interest, an increasing demand of methods to process these videos, possibly in real-time, is expected. Current approaches present a particular combinations of different image features and quantitative methods to accomplish specific objectives like object detection, activity recognition, user machine interaction and so on. This paper summarizes the evolution of the state of the art in First Person Vision video analysis between 1997 and 2014, highlighting, among others, most commonly used features, methods, challenges and opportunities within the field.

Diverse input data modalities can provide complementary cues for several tasks, usually leading to more robust algorithms and better performance. However, while a (training) dataset could be accurately designed to include a variety of sensory inputs, it is often the case that not all modalities could be available in real life (testing) scenarios, where a model has to be deployed. This raises the challenge of how to learn robust representations leveraging multimodal data in the training stage, while considering limitations at test time, such as noisy or missing modalities. This paper presents a new approach for multimodal video action recognition, developed within the unified frameworks of distillation and privileged information, named generalized distillation. Particularly, we consider the case of learning representations from depth and RGB videos, while relying on RGB data only at test time. We propose a new approach to train an hallucination network that learns to distill depth features through multiplicative connections of spatiotemporal representations, leveraging soft labels and hard labels, as well as distance between feature maps. We report state-of-the-art results on video action classification on the largest multimodal dataset available for this task, the NTU RGB+D. Code available at https://github.com/ncgarcia/ modality-distillation

No abstract

Dropout is a very effective way of regularizing neural networks. Stochastically "dropping out" units with a certain probability discourages over-specific co-adaptations of feature detectors, preventing overfitting and improving network generalization. Besides, Dropout can be interpreted as an approximate model aggregation technique, where an exponential number of smaller networks are averaged in order to get a more powerful ensemble. In this paper, we show that using a fixed dropout probability during training is a suboptimal choice. We thus propose a time scheduling for the probability of retaining neurons in the network. This induces an adaptive regularization scheme that smoothly increases the difficulty of the optimization problem. This idea of "starting easy" and adaptively increasing the difficulty of the learning problem has its roots in curriculum learning and allows one to train better models. Indeed, we prove that our optimization strategy implements a very general curriculum scheme, by gradually adding noise to both the input and intermediate feature representations within the network architecture. Experiments on seven image classification datasets and different network architectures show that our method, named Curriculum Dropout, frequently yields to better generalization and, at worst, performs just as well as the standard Dropout method.

No abstract

In this paper, we investigate how to learn rich and robust feature representations for audio classification from visual data and acoustic images, a novel audio data modality. Former models learn audio representations from raw signals or spectral data acquired by a single microphone, with remarkable results in classification and retrieval. However, such representations are not so robust towards variable environmental sound conditions. We tackle this drawback by exploiting a new multimodal labeled action recognition dataset acquired by a hybrid audio-visual sensor that provides RGB video, raw audio signals, and spatialized acoustic data, also known as acoustic images, where the visual and acoustic images are aligned in space and synchronized in time. Using this richer information, we train audio deep learning models in a teacher-student fashion. In particular, we distill knowledge into audio networks from both visual and acoustic image teachers. Our experiments suggest that the learned representations are more powerful and have better generalization capabilities than the features learned from models trained using just single-microphone audio data.

Abstract. 3D action recognition was shown to benefit from a covariance representation of the input data (joint 3D positions). A kernel machine feed with such feature is an effective paradigm for 3D action recognition, yielding state-of-the-art results. Yet, the whole framework is affected by the well-known scalability issue. In fact, in general, the kernel function has to be evaluated for all pairs of instances inducing a Gram matrix whose complexity is quadratic in the number of samples. In this work we reduce such complexity to be linear by proposing a novel and explicit feature map to approximate the kernel function. This allows to train a linear classifier with an explicit feature encoding, which implicitly implements a Log-Euclidean machine in a scalable fashion. Not only we prove that the proposed approximation is unbiased, but also we work out an explicit strong bound for its variance, attesting a theoretical superiority of our approach with respect to existing ones. Experimentally, we verify that our representation provides a compact encoding and outperforms other approximation schemes on a number of publicly available benchmark datasets for 3D action recognition.