This paper explores a semi-supervised object detection approach to detect hot spots on the internal wall of Tokamaks. A huge amount of data is produced during an experimental campaign by the infrared (IR) viewing systems used to monitor the inner thermal shields during machine operation. The amount of data to be processed and analysed is such that protecting the first wall is an overwhelming job. Automatizing this job with artificial intelligence (AI) is an attractive solution, but AI requires large labelled databases which are not readily available for Tokamak walls. Semi-supervised learning (SSL) is a possible solution to being able to train deep learning models with a small amount of labelled data and a large amount of unlabelled data. SSL is explored as a possible tool to rapidly adapt a model trained on an experimental campaign A of Tokamak WEST to a new experimental campaign B by using labelled data from campaign A, a little labelled data from campaign B and a lot of unlabelled data from campaign B. Model performances are evaluated on two labelled datasets and two methods including semi-supervised learning. Semi-supervised learning increased the mAP metric by over six percentage points on the first smaller scale database and over four percentage points on the second larger scale dataset depending on the employed method.
The progress in the generation of synthetic images has made it crucial to assess their quality. While several metrics have been proposed to assess the rendering of images, it is crucial for Text-to-Image (T2I) models, which generate images based on a prompt, to consider additional aspects such as to which extent the generated image matches the important content of the prompt. Moreover, although the generated images usually result from a random starting point, the influence of this one is generally not considered. In this article, we propose a new metric based on prompt templates to study the alignment between the content specified in the prompt and the corresponding generated images. It allows us to better characterize the alignment in terms of the type of the specified objects, their number, and their color. We conducted a study on several recent T2I models about various aspects. An additional interesting result we obtained with our approach is that image quality can vary drastically depending on the latent noise used as a seed for the images. We also quantify the influence of the number of concepts in the prompt, their order as well as their (color) attributes. Finally, our method allows us to identify some latent seeds that produce better images than others, opening novel directions of research on this understudied topic.
Visual SLAM -- Simultaneous Localization and Mapping -- in dynamic environments typically relies on identifying and masking image features on moving objects to prevent them from negatively affecting performance. Current approaches are suboptimal: they either fail to mask objects when needed or, on the contrary, mask objects needlessly. Thus, we propose a novel SLAM that learns when masking objects improves its performance in dynamic scenarios. Given a method to segment objects and a SLAM, we give the latter the ability of Temporal Masking, i.e., to infer when certain classes of objects should be masked to maximize any given SLAM metric. We do not make any priors on motion: our method learns to mask moving objects by itself. To prevent high annotations costs, we created an automatic annotation method for self-supervised training. We constructed a new dataset, named ConsInv, which includes challenging real-world dynamic sequences respectively indoors and outdoors. Our method reaches the state of the art on the TUM RGB-D dataset and outperforms it on KITTI and ConsInv datasets.
Zero-shot learning (ZSL) aims at recognizing classes for which no visual sample is available at training time. To address this issue, one can rely on a semantic description of each class. A typical ZSL model learns a mapping between the visual samples of seen classes and the corresponding semantic descriptions, in order to do the same on unseen classes at test time. State of the art approaches rely on generative models that synthesize visual features from the prototype of a class, such that a classifier can then be learned in a supervised manner. However, these approaches are usually biased towards seen classes whose visual instances are the only one that can be matched to a given class prototype. We propose a regularization method that can be applied to any conditional generative-based ZSL method, by leveraging only the semantic class prototypes. It learns to synthesize discriminative features for possible semantic description that are not available at training time, that is the unseen ones. The approach is evaluated for ZSL and GZSL on four datasets commonly used in the literature, either in inductive and transductive settings, with results on-par or above state of the art approaches.
Various controls over the generated data can be extracted from the latent space of a pre-trained GAN, as it implicitly encodes the semantics of the training data. The discovered controls allow to vary semantic attributes in the generated images but usually lead to entangled edits that affect multiple attributes at the same time. Supervised approaches typically sample and annotate a collection of latent codes, then train classifiers in the latent space to identify the controls. Since the data generated by GANs reflects the biases of the original dataset, so do the resulting semantic controls. We propose to address disentanglement by subsampling the generated data to remove over-represented co-occuring attributes thus balancing the semantics of the dataset before training the classifiers. We demonstrate the effectiveness of this approach by extracting disentangled linear directions for face manipulation on two popular GAN architectures, PGGAN and StyleGAN, and two datasets, CelebAHQ and FFHQ. We show that this approach outperforms state-of-the-art classifier-based methods while avoiding the need for disentanglement-enforcing post-processing.
Zero-shot learning deals with the ability to recognize objects without any visual training sample. To counterbalance this lack of visual data, each class to recognize is associated with a semantic prototype that reflects the essential features of the object. The general approach is to learn a mapping from visual data to semantic prototypes, then use it at inference to classify visual samples from the class prototypes only. Different settings of this general configuration can be considered depending on the use case of interest, in particular whether one only wants to classify objects that have not been employed to learn the mapping or whether one can use unlabelled visual examples to learn the mapping. This chapter presents a review of the approaches based on deep neural networks to tackle the ZSL problem. We highlight findings that had a large impact on the evolution of this domain and list its current challenges.
Among the wide variety of image generative models, two models stand out: Variational Auto Encoders (VAE) and Generative Adversarial Networks (GAN). GANs can produce realistic images, but they suffer from mode collapse and do not provide simple ways to get the latent representation of an image. On the other hand, VAEs do not have these problems, but they often generate images less realistic than GANs. In this article, we explain that this lack of realism is partially due to a common underestimation of the natural image manifold dimensionality. To solve this issue we introduce a new framework that combines VAE and GAN in a novel and complementary way to produce an auto-encoding model that keeps VAEs properties while generating images of GAN-quality. We evaluate our approach both qualitatively and quantitatively on five image datasets.
We present a method to automatically learn to segment dynamic objects using SLAM outliers. It requires only one monocular sequence per dynamic object for training and consists in localizing dynamic objects using SLAM outliers, creating their masks, and using these masks to train a semantic segmentation network. We integrate the trained network in ORB-SLAM 2 and LDSO. At runtime we remove features on dynamic objects, making the SLAM unaffected by them. We also propose a new stereo dataset and new metrics to evaluate SLAM robustness. Our dataset includes consensus inversions, i.e., situations where the SLAM uses more features on dynamic objects that on the static background. Consensus inversions are challenging for SLAM as they may cause major SLAM failures. Our approach performs better than the State-of-the-Art on the TUM RGB-D dataset in monocular mode and on our dataset in both monocular and stereo modes.
Zero-shot learning aims to recognize instances of unseen classes, for which no visual instance is available during training, by learning multimodal relations between samples from seen classes and corresponding class semantic representations. These class representations usually consist of either attributes, which do not scale well to large datasets, or word embeddings, which lead to poorer performance. A good trade-off could be to employ short sentences in natural language as class descriptions. We explore different solutions to use such short descriptions in a ZSL setting and show that while simple methods cannot achieve very good results with sentences alone, a combination of usual word embeddings and sentences can significantly outperform current state-of-the-art.