Abstract: Artificial intelligence is innovating the fashion industry by proposing new applications and solutions to the problems encountered by researchers and engineers working in the industry. In this thesis, we address three of these problems. In the first part of the thesis, we tackle the problem of multi-label image classification which is very related to fashion attribute recognition. In the second part of the thesis, we address two problems that are specific to fashion. Firstly, we address the problem of main product detection which is the task of associating correct image parts (e.g. bounding boxes) with the fashion product being sold. Secondly, we address the problem of color naming for multicolored fashion items. The task of multi-label image classification consists in assigning various concepts such as objects or attributes to images. Usually, there are dependencies that can be learned between the concepts to capture label correlations (chair and table classes are more likely to co-exist than chair and giraffe).
If we treat the multi-label image classification problem as an orderless set prediction problem, we can exploit recurrent neural networks (RNN) to capture label correlations. However, RNNs are trained to predict ordered sequences of tokens, so if the order of the predicted sequence is different than the order of the ground truth sequence, there will be penalization although the predictions are correct. Therefore, in the first part of the thesis, we propose an orderless loss function which will order the labels in the ground truth sequence dynamically in a way that the minimum loss is achieved. This results in a significant improvement of RNN models on multi-label image classification over the previous methods.
However, RNNs suffer from long term dependencies when the cardinality of set grows bigger. The decoding process might stop early if the current hidden state cannot find any object and outputs the termination token. This would cause the remaining classes not to be predicted and lower recall metric. Transformers can be used to avoid the long term dependency problem exploiting their selfattention modules that process sequential data simultaneously. Consequently, we propose a novel transformer model for multi-label image classification which surpasses the state-of-the-art results by a large margin.
In the second part of thesis, we focus on two fashion-specific problems. Main product detection is the task of associating image parts with the fashion product that is being sold, generally using associated textual metadata (product title or description). Normally, in fashion e-commerces, products are represented by multiple images where a person wears the product along with other fashion items. If all the fashion items in the images are marked with bounding boxes, we can use the textual metadata to decide which item is the main product. The initial work treated each of these images independently, discarding the fact that they all belong to the same product. In this thesis, we represent the bounding boxes from all the images as nodes in a fully connected graph. This allows the algorithm to learn relations between the nodes during training and take the entire context into account for the final decision. Our algorithm results in a significant improvement of the state-ofthe-art.
Moreover, we address the problem of color naming for multicolored fashion items, which is a challenging task due to the external factors such as illumination changes or objects that act as clutter. In the context of multi-label classification, the vaguely defined lines between the classes in the color space cause ambiguity. For example, a shade of blue which is very close to green might cause the model to incorrectly predict the color blue and green at the same time. Based on this, models trained for color naming are expected to recognize the colors and their quantities in both single colored and multicolored fashion items. Therefore, in this thesis, we propose a novel architecture with an additional head that explicitly estimates the number of colors in fashion items. This removes the ambiguity problem and results in better color naming performance.

Abstract: Single image super-resolution (SISR) is an important task in image processing which aims to enhance the resolution of imaging systems. Recently, SISR has witnessed great strides with the rapid development of deep learning. Recent advances in SISR are mostly devoted to designing deeper and wider networks to enhance their representation learning capacity. However, as the depth of networks increases, deep learning-based methods are faced with the challenge of computational complexity in practice. Moreover, most existing methods rarely leverage the intermediate features and also do not discriminate the computation of features by their frequencial components, thereby achieving relatively low performance. Aside from the aforementioned problems, another desired ability is to upsample images to arbitrary scales using a single model. Most current SISR methods train a dedicated model for each target resolution, losing generality and increasing memory requirements. In this thesis, we address the aforementioned issues and propose solutions to them: i) We present a novel frequency-based enhancement block which treats different frequencies in a heterogeneous way and also models inter-channel dependencies, which consequently enrich the output feature. Thus it helps the network generate more discriminative representations by explicitly recovering finer details. ii) We introduce OverNet which contains two main parts: a lightweight feature extractor that follows a novel recursive framework of skip and dense connections to reduce low-level feature degradation, and an overscaling module that generates an accurate SR image by internally constructing an overscaled intermediate representation of the output features. Then, to solve the problem of reconstruction at arbitrary scale factors, we introduce a novel multi-scale loss, that allows the simultaneous training of all scale factors using a single model. iii) We propose a directional variance attention network which leverages a novel attention mechanism to enhance features in different channels and spatial regions. Moreover, we introduce a novel procedure for using attention mechanisms together with residual blocks to facilitate the preservation of finer details. Finally, we demonstrate that our approaches achieve considerably better performance than previous state-of-the-art methods, in terms of both quantitative and visual quality.

Abstract: The mass irruption of Deep Convolutional Neural Networks (CNNs) in computer vision since 2012 led to a dominance of the image understanding paradigm consisting in an end-to-end fully supervised learning workflow over large-scale annotated datasets. This approach proved to be extremely useful at solving a myriad of classic and new computer vision tasks with unprecedented performance —often, surpassing that of humans—, at the expense of vast amounts of human-labeled data, extensive computational resources and the disposal of all of our prior knowledge on the task at hand. Even though simple transfer learning methods, such as fine-tuning, have achieved remarkable impact, their success when the amount of labeled data in the target domain is small is limited. Furthermore, the non-static nature of data generation sources will often derive in data distribution shifts that degrade the performance of deployed models. As a consequence, there is a growing demand for methods that can exploit elements of prior knowledge and sources of information other than the manually generated ground truth annotations of the images during the network training process, so that they can adapt to new domains that constitute, if not a small data regime, at least a small labeled data regime. This thesis targets such few or no labeled data scenario in three distinct image-to-image mapping learning problems. It contributes with various approaches that leverage our previous knowledge of different elements of the image formation process: We first present a data-efficient framework for both defocus and motion blur detection, based on a model able to produce realistic synthetic local degradations. The framework comprises a self-supervised, a weakly-supervised and a semi-supervised instantiation, depending on the absence or availability and the nature of human annotations, and outperforms fully-supervised counterparts in a variety of settings. Our knowledge on color image formation is then used to gather input and target ground truth image pairs for the RGB to hyperspectral image reconstruction task. We make use of a CNN to tackle this problem, which, for the first time, allows us to exploit spatial context and achieve state-of-the-art results given a limited hyperspectral image set. In our last contribution to the subfield of data-efficient image-to-image transformation problems, we present the novel semi-supervised task of zero-pair cross-view semantic segmentation: we consider the case of relocation of the camera in an end-to-end trained and deployed monocular, fixed-view semantic segmentation system often found in industry. Under the assumption that we are allowed to obtain an additional set of synchronized but unlabeled image pairs of new scenes from both original and new camera poses, we present ZPCVNet, a model and training procedure that enables the production of dense semantic predictions in either source or target views at inference time. The lack of existing suitable public datasets to develop this approach led us to the creation of MVMO, a large-scale Multi-View, Multi-Object path-traced dataset with per-view semantic segmentation annotations. We expect MVMO to propel future research in the exciting under-developed fields of cross-view and multi-view semantic segmentation. Last, in a piece of applied research of direct application in the context of process monitoring of an Electric Arc Furnace (EAF) in a steelmaking plant, we also consider the problem of simultaneously estimating the temperature and spectral emissivity of distant hot emissive samples. To that end, we design our own capturing device, which integrates three point spectrometers covering a wide range of the Ultra-Violet, visible, and Infra-Red spectra and is capable of registering the radiance signal incoming from an 8cm diameter spot located up to 20m away. We then define a physically accurate radiative transfer model that comprises the effects of atmospheric absorbance, of the optical system transfer function, and of the sample temperature and spectral emissivity themselves. We solve this inverse problem without the need for annotated data using a probabilistic programming-based Bayesian approach, which yields full posterior distribution estimates of the involved variables that are consistent with laboratory-grade measurements.

Abstract: Handwritten Music Recognition, especially in the historical domain, is an inherently challenging endeavour; paper degradation artefacts and the ambiguous nature of handwriting make recognising such scores an error-prone process, even for the current state-of-the-art Sequence to Sequence models. In this work we propose a way of reducing the production of statistically implausible output sequences by fusing a Language Model into a recognition Sequence to Sequence model. The idea is leveraging visually-conditioned and context-conditioned output distributions in order to automatically find and correct any mistakes that would otherwise break context significantly. We have found this approach to improve recognition results to 25.15 SER (%) from a previous best of 31.79 SER (%) in the literature.

Abstract: Vision and Language are broadly regarded as cornerstones of intelligence. Even though language and vision have different aims – language having the purpose of communication, transmission of information and vision having the purpose of constructing mental representations around us to navigate and interact with objects – they cooperate and depend on one another in many tasks we perform effortlessly. This reliance is actively being studied in various Computer Vision tasks, e.g. image captioning, visual question answering, image-sentence retrieval, phrase grounding, just to name a few. All of these tasks share the inherent difficulty of the aligning the two modalities, while being robust to language
priors and various biases existing in the datasets. One of the ultimate goal for vision and language research is to be able to inject world knowledge while getting rid of the biases that come with the datasets. In this thesis, we mainly focus on two vision and language tasks, namely Image Captioning and Scene-Text Visual Question Answering (STVQA).
In both domains, we start by defining a new task that requires the utilization of world knowledge and in both tasks, we find that the models commonly employed are prone to biases that exist in the data. Concretely, we introduce new tasks and discover several problems that impede performance at each level and provide remedies or possible solutions in each chapter: i) We define a new task to move beyond Image Captioning to Image Interpretation that can utilize Named Entities in the form of world knowledge. ii) We study the object hallucination problem in classic Image Captioning systems and develop an architecture-agnostic solution. iii) We define a sub-task of Visual Question Answering that requires reading the text in the image (STVQA), where we highlight the limitations of current models. iv) We propose an architecture for the STVQA task that can point to the answer in the image and show how to combine it with classic VQA models. v) We show how far language can get us in STVQA and discover yet another bias which causes the models to disregard the image while doing Visual Question Answering.

Abstract: In this thesis, we propose different contributions with the goal of enhancing and recognizing historical handwritten document images, especially the ones with rare scripts, such as cipher documents.
In the first part, some effective end-to-end models for Document Image Enhancement (DIE) using deep learning models were presented. First, Generative Adversarial Networks (cGAN) for different tasks (document clean-up, binarization, deblurring, and watermark removal) were explored. Next, we further improve the results by recovering the degraded document images into a clean and readable form by integrating a text recognizer into the cGAN model to promote the generated document image to be more readable. Afterward, we present a new encoder-decoder architecture based on vision transformers to enhance both machine-printed and handwritten document images, in an end-to-end fashion.
The second part of the thesis addresses Handwritten Text Recognition (HTR) in low resource scenarios, i.e. when only few labeled training data is available. We propose novel methods for recognizing ciphers with rare scripts. First, a few-shot object detection based method was proposed. Then, we incorporate a progressive learning strategy that automatically assignspseudo-labels to a set of unlabeled data to reduce the human labor of annotating few pages while maintaining the good performance of the model. Secondly, a data generation technique based on Bayesian Program Learning (BPL) is proposed to overcome the lack of data in such rare scripts. Thirdly, we propose a Text-Degradation Invariant Auto Encoder (Text-DIAE). This latter self-supervised model is designed to tackle two tasks, text recognition and document image enhancement. The proposed model does not exhibit limitations of previous state-of-the-art methods based on contrastive losses, while at the same time, it requires substantially fewer data samples to converge.
In the third part of the thesis, we analyze, from the user perspective, the usage of HTR systems in low resource scenarios. This contrasts with the usual research on HTR, which often focuses on technical aspects only and rarely devotes efforts on implementing software tools for scholars in Humanities.

Abstract: GANs have matured in recent years and are able to generate high-resolution, realistic images. However, the computational resources and the data required for the training of high-quality GANs are enormous, and the study of transfer learning of these models is therefore an urgent topic. Many of the available high-quality pretrained GANs are unconditional (like StyleGAN). For many applications, however, conditional GANs are preferable, because they provide more control over the generation process, despite often suffering more training difficulties. Therefore, in this paper, we focus on transferring from high-quality pretrained unconditional GANs to conditional GANs. This requires architectural adaptation of the pretrained GAN to perform the conditioning. To this end, we propose hyper-modulated generative networks that allow for shared and complementary supervision. To prevent the additional weights of the hypernetwork to overfit, with subsequent mode collapse on small target domains, we introduce a self-initialization procedure that does not require any real data to initialize the hypernetwork parameters. To further improve the sample efficiency of the transfer, we apply contrastive learning in the discriminator, which effectively works on very limited batch sizes. In extensive experiments, we validate the efficiency of the hypernetworks, self-initialization and contrastive loss for knowledge transfer on standard benchmarks.

Abstract: Self-supervised learning has been widely applied to train high-quality vision transformers. Unleashing their excellent performance on memory and compute constraint devices is therefore an important research topic. However, how to distill knowledge from one self-supervised ViT to another has not yet been explored. Moreover, the existing self-supervised knowledge distillation (SSKD) methods focus on ConvNet based architectures are suboptimal for ViT knowledge distillation. In this paper, we study knowledge distillation of self-supervised vision transformers (ViT-SSKD). We show that directly distilling information from the crucial attention mechanism from teacher to student can significantly narrow the performance gap between both. In experiments on ImageNet-Subset and ImageNet-1K, we show that our method AttnDistill outperforms existing self-supervised knowledge distillation (SSKD) methods and achieves state-of-the-art k-NN accuracy compared with self-supervised learning (SSL) methods learning from scratch (with the ViT-S model). We are also the first to apply the tiny ViT-T model on self-supervised learning. Moreover, AttnDistill is independent of self-supervised learning algorithms, it can be adapted to ViT based SSL methods to improve the performance in future research.