Abstract: A crucial part of image classification consists of capturing non-local spatial semantics of image content. This paper describes the multi-scale hybrid vision transformer (MSHViT), an extension of the classical convolutional neural network (CNN) backbone, for multi-label sewer defect classification. To better model spatial semantics in the images, features are aggregated at different scales non-locally through the use of a lightweight vision transformer, and a smaller set of tokens was produced through a novel Sinkhorn clustering-based tokenizer using distinct cluster centers. The proposed MSHViT and Sinkhorn tokenizer were evaluated on the Sewer-ML multi-label sewer defect classification dataset, showing consistent performance improvements of up to 2.53 percentage points.

Abstract: Active learning aims to reduce the labeling effort that is required to train algorithms by learning an acquisition function selecting the most relevant data for which a label should be requested from a large unlabeled data pool. Active learning is generally studied on balanced datasets where an equal amount of images per class is available. However, real-world datasets suffer from severe imbalanced classes, the so called long-tail distribution. We argue that this further complicates the active learning process, since the imbalanced data pool can result in suboptimal classifiers. To address this problem in the context of active learning, we proposed a general optimization framework that explicitly takes class-balancing into account. Results on three datasets showed that the method is general (it can be combined with most existing active learning algorithms) and can be effectively applied to boost the performance of both informative and representative-based active learning methods. In addition, we showed that also on balanced datasets
our method 1 generally results in a performance gain.

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: Automatic image and video exploitation or content analysis is a technique to extract higher-level information from a scene such as objects, behavior, (inter-)actions, environment, or even weather conditions. The relevant information is assumed to be contained in the two-dimensional signal provided in an image (width and height in pixels) or the three-dimensional signal provided in a video (width, height, and time). But also intermediate-level information such as object classes [196], locations [197], or motion [198] can help applications to fulfill certain tasks such as intelligent compression [199], video summarization [200], or video retrieval [201]. Usually, videos with their temporal dimension are a richer source of data compared to single images [202] and thus certain video content can be extracted from videos only such as object motion or object behavior. Often, machine learning or nowadays deep learning techniques are utilized to model prior knowledge about object or scene appearance using labeled training samples [203, 204]. After a learning phase, these models are then applied in real world applications, which is called inference.