Abstract: Until recently, most computer vision models remained illiterate, largely ignoring the semantically rich and explicit information contained in scene text. Recent progress in scene text detection and recognition has recently allowed exploring its role in a diverse set of open computer vision problems, e.g. image classification, image-text retrieval, image captioning, and visual question answering to name a few. The explicit semantics of scene text closely requires specific modeling similar to language. However, scene text is a particular signal that has to be interpreted according to a comprehensive perspective that encapsulates all the visual cues in an image. Incorporating this information is a straightforward task for humans, but if we are unfamiliar with a language or scripture, achieving a complete world understanding is impossible (e.a. visiting a foreign country with a different alphabet). Despite the importance of scene text, modeling it requires considering the several ways in which scene text interacts with an image, processing and fusing an additional modality. In this thesis, we mainly focus
on two tasks, scene text-based fine-grained image classification, and cross-modal retrieval. In both studied tasks we identify existing limitations in current approaches and propose plausible solutions. Concretely, in each chapter: i) We define a compact way to embed scene text that generalizes to unseen words at training time while performing in real-time. ii) We incorporate the previously learned scene text embedding to create an image-level descriptor that overcomes optical character recognition (OCR) errors which is well-suited to the fine-grained image classification task. iii) We design a region-level reasoning network that learns the interaction through semantics among salient visual regions and scene text instances. iv) We employ scene text information in image-text matching and introduce the Scene Text Aware Cross-Modal retrieval StacMR task. We gather a dataset that incorporates scene text and design a model suited for the newly studied modality. v) We identify the drawbacks of current retrieval metrics in cross-modal retrieval. An image captioning metric is proposed as a way of better evaluating semantics in retrieved results. Ample experimentation shows that incorporating such semantics into a model yields better semantic results while
requiring significantly less data to converge.

Abstract: Food image recognition is a complex computer vision task, because of the large number of fine-grained food classes. Fine-grained recognition tasks focus on learning subtle discriminative details to distinguish similar classes. In this paper, we introduce a new method to improve the classification of classes that are more difficult to discriminate based on Multi-Subsets learning. Using a pre-trained network, we organize classes in multiple subsets using a clustering technique. Later, we embed these subsets in a multi-head model structure. This structure has three distinguishable parts. First, we use several shared blocks to learn the generalized representation of the data. Second, we use multiple specialized blocks focusing on specific subsets that are difficult to distinguish. Lastly, we use a fully connected layer to weight the different subsets in an end-to-end manner by combining the neuron outputs. We validated our proposed method using two recent state-of-the-art vision transformers on three public food recognition datasets. Our method was successful in learning the confused classes better and we outperformed the state-of-the-art on the three datasets.

Abstract: The task of image-text matching aims to map representations from different modalities into a common joint visual-textual embedding. However, the most widely used datasets for this task, MSCOCO and Flickr30K, are actually image captioning datasets that offer a very limited set of relationships between images and sentences in their ground-truth annotations. This limited ground truth information forces us to use evaluation metrics based on binary relevance: given a sentence query we consider only one image as relevant. However, many other relevant images or captions may be present in the dataset. In this work, we propose two metrics that evaluate the degree of semantic relevance of retrieved items, independently of their annotated binary relevance. Additionally, we incorporate a novel strategy that uses an image captioning metric, CIDEr, to define a Semantic Adaptive Margin (SAM) to be optimized in a standard triplet loss. By incorporating our formulation to existing models, a large improvement is obtained in scenarios where available training data is limited. We also demonstrate that the performance on the annotated image-caption pairs is maintained while improving on other non-annotated relevant items when employing the full training set. The code for our new metric can be found at github. com/furkanbiten/ncsmetric and the model implementation at github. com/andrespmd/semanticadaptive_margin.

Abstract: The problem of food image recognition is an essential one in today’s context because health conditions such as diabetes, obesity, and heart disease require constant monitoring of a person’s diet. To automate this process, several models are available to recognize food images. Due to a considerable number of unique food dishes and various cuisines, a traditional flat classifier ceases to perform well. To address this issue, prediction schemes consisting of both flat and hierarchical classifiers, with the analysis of epistemic uncertainty are used to switch between the classifiers. However, the accuracy of the predictions made using epistemic uncertainty data remains considerably low. Therefore, this paper presents a prediction scheme using three different threshold criteria that helps to increase the accuracy of epistemic uncertainty predictions. The performance of the proposed method is demonstrated using several experiments performed on the MAFood-121 dataset. The experimental results validate the proposal performance and show that the proposed threshold criteria help to increase the overall accuracy of the predictions by correctly classifying the uncertainty distribution of the samples.

Abstract: Memes evolve and mutate through their diffusion in social media. They have the potential to propagate ideas and, by extension, products. Many studies have focused on memes, but none so far, to our knowledge, on the users that post them, their relationships, and the reach of their influence. In this article, we define a meme influence graph together with suitable metrics to visualize and quantify influence between users who post memes, and we also describe a process to implement our definitions using a new approach to meme detection based on text-to-image area ratio and contrast. After applying our method to a set of users of the social media platform Instagram, we conclude that our metrics add information to already existing user characteristics.

Abstract: Background and study aims Artificial intelligence is currently able to accurately predict the histology of colorectal polyps. However, systems developed to date use complex optical technologies and have not been tested in vivo. The objective of this study was to evaluate the efficacy of a new deep learning-based optical diagnosis system, ATENEA, in a real clinical setting using only high-definition white light endoscopy (WLE) and to compare its performance with endoscopists. Methods ATENEA was prospectively tested in real life on consecutive polyps detected in colorectal cancer screening colonoscopies at Hospital Clínic. No images were discarded, and only WLE was used. The in vivo ATENEA's prediction (adenoma vs non-adenoma) was compared with the prediction of four staff endoscopists without specific training in optical diagnosis for the study purposes. Endoscopists were blind to the ATENEA output. Histology was the gold standard. Results Ninety polyps (median size: 5 mm, range: 2-25) from 31 patients were included of which 69 (76.7 %) were adenomas. ATENEA correctly predicted the histology in 63 of 69 (91.3 %, 95 % CI: 82 %-97 %) adenomas and 12 of 21 (57.1 %, 95 % CI: 34 %-78 %) non-adenomas while endoscopists made correct predictions in 52 of 69 (75.4 %, 95 % CI: 60 %-85 %) and 20 of 21 (95.2 %, 95 % CI: 76 %-100 %), respectively. The global accuracy was 83.3 % (95 % CI: 74%-90 %) and 80 % (95 % CI: 70 %-88 %) for ATENEA and endoscopists, respectively. Conclusion ATENEA can accurately be used for in vivo characterization of colorectal polyps, enabling the endoscopist to make direct decisions. ATENEA showed a global accuracy similar to that of endoscopists despite an unsatisfactory performance for non-adenomatous lesions.

Abstract: Rain removal plays an important role in the restoration of degraded images. Recently, CNN-based methods have achieved remarkable success. However, these approaches neglect that the appearance of real-world rain is often accompanied by low light conditions, which will further degrade the image quality, thereby hindering the restoration mission. Therefore, it is very indispensable to jointly remove the rain and enhance illumination for real-world rain image restoration. To this end, we proposed a novel spatially-adaptive network, dubbed SANet, which can remove the rain and enhance illumination in one go with the guidance of degradation mask. Meanwhile, to fully utilize negative samples, a contrastive loss is proposed to preserve more natural textures and consistent illumination. In addition, we present a new synthetic dataset, named DarkRain, to boost the development of rain image restoration algorithms in practical scenarios. DarkRain not only contains different degrees of rain, but also considers different lighting conditions, and more realistically simulates real-world rainfall scenarios. SANet is extensively evaluated on the proposed dataset and attains new state-of-the-art performance against other combining methods. Moreover, after a simple transformation, our SANet surpasses existing the state-of-the-art algorithms in both rain removal and low-light image enhancement.