Abstract: The emergence of transformer models like BERT, GPT-2, GPT-3, RoBERTa, T5 for natural language understanding tasks has opened the floodgates towards solving a wide array of machine learning tasks in other modalities like images, audio, music, sketches and so on. These language models are domain-agnostic and as a result could be applied to 1-D sequences of any kind. However, the key challenge lies in bridging the modality gap so that they could generate strong features beneficial for out-of-domain tasks. This work focuses on leveraging the power of such pre-trained language models and discusses the challenges in predicting challenging handwritten symbols and alphabets.

Abstract: Explainable Artificial Intelligence (XAI) provides tools to help understanding how the machine learning models work and reach a specific outcome. It helps to increase the interpretability of models and makes the models more trustworthy and transparent. In this context, many XAI methods were proposed being SHAP and LIME the most popular. However, the proposed methods assume that used predictors in the machine learning models are independent which in general is not necessarily true. Such assumption casts shadows on the robustness of the XAI outcomes such as the list of informative predictors. Here, we propose a simple, yet useful proxy that modifies the outcome of any XAI feature ranking method allowing to account for the dependency among the predictors. The proposed approach has the advantage of being model-agnostic as well as simple to calculate the impact of each predictor in the model in presence of collinearity.

Abstract: Multi-label zero-shot learning strives to classify images into multiple unseen categories for which no data is available during training. The test samples can additionally contain seen categories in the generalized variant. Existing approaches rely on learning either shared or label-specific attention from the seen classes. Nevertheless, computing reliable attention maps for unseen classes during inference in a multi-label setting is still a challenge. In contrast, state-of-the-art single-label generative adversarial network (GAN) based approaches learn to directly synthesize the class-specific visual features from the corresponding class attribute embeddings. However, synthesizing multi-label features from GANs is still unexplored in the context of zero-shot setting. When multiple objects occur jointly in a single image, a critical question is how to effectively fuse multi-class information. In this work, we introduce different fusion approaches at the attribute-level, feature-level and cross-level (across attribute and feature-levels) for synthesizing multi-label features from their corresponding multi-label class embeddings. To the best of our knowledge, our work is the first to tackle the problem of multi-label feature synthesis in the (generalized) zero-shot setting. Our cross-level fusion-based generative approach outperforms the state-of-the-art on three zero-shot benchmarks: NUS-WIDE, Open Images and MS COCO. Furthermore, we show the generalization capabilities of our fusion approach in the zero-shot detection task on MS COCO, achieving favorable performance against existing methods.

Abstract: Online continual learning aims to get closer to a live learning experience by learning directly on a stream of data with temporally shifting distribution and by storing a minimum amount of data from that stream. In this empirical evaluation, we evaluate various methods from the literature that tackle online continual learning. More specifically, we focus on the class-incremental setting in the context of image classification, where the learner must learn new classes incrementally from a stream of data. We compare these methods on the Split-CIFAR100 and Split-TinyImagenet benchmarks, and measure their average accuracy, forgetting, stability, and quality of the representations, to evaluate various aspects of the algorithm at the end but also during the whole training period. We find that most methods suffer from stability and underfitting issues. However, the learned representations are comparable to i.i.d. training under the same computational budget. No clear winner emerges from the results and basic experience replay, when properly tuned and implemented, is a very strong baseline. We release our modular and extensible codebase at this https URL based on the avalanche framework to reproduce our results and encourage future research.

Abstract: Multi-domain recommender systems benefit from cross-domain representation learning and positive knowledge transfer. Both can be achieved by introducing a specific modeling of input data (i.e. disjoint history) or trying dedicated training regimes. At the same time, treating domains as separate input sources becomes a limitation as it does not capture the interplay that naturally exists between domains. In this work, we efficiently learn multi-domain representation of sequential users’ interactions using graph neural networks. We use temporal intra- and inter-domain interactions as contextual information for our method called MAGRec (short for Multi-dom Ain Graph-based Recommender). To better capture all relations in a multi-domain setting, we learn two graph-based sequential representations simultaneously: domain-guided for recent user interest, and general for long-term interest. This approach helps to mitigate the negative knowledge transfer problem from multiple domains and improve overall representation. We perform experiments on publicly available datasets in different scenarios where MAGRec consistently outperforms state-of-the-art methods. Furthermore, we provide an ablation study and discuss further extensions of our method.

Abstract: The SoccerNet 2023 challenges were the third annual video understanding challenges organized by the SoccerNet team. For this third edition, the challenges were composed of seven vision-based tasks split into three main themes. The first theme, broadcast video understanding, is composed of three high-level tasks related to describing events occurring in the video broadcasts: (1) action spotting, focusing on retrieving all timestamps related to global actions in soccer, (2) ball action spotting, focusing on retrieving all timestamps related to the soccer ball change of state, and (3) dense video captioning, focusing on describing the broadcast with natural language and anchored timestamps. The second theme, field understanding, relates to the single task of (4) camera calibration, focusing on retrieving the intrinsic and extrinsic camera parameters from images. The third and last theme, player understanding, is composed of three low-level tasks related to extracting information about the players: (5) re-identification, focusing on retrieving the same players across multiple views, (6) multiple object tracking, focusing on tracking players and the ball through unedited video streams, and (7) jersey number recognition, focusing on recognizing the jersey number of players from tracklets. Compared to the previous editions of the SoccerNet challenges, tasks (2-3-7) are novel, including new annotations and data, task (4) was enhanced with more data and annotations, and task (6) now focuses on end-to-end approaches. More information on the tasks, challenges, and leaderboards are available on this https URL. Baselines and development kits can be found on this https URL.

Abstract: Human vision is restricted to the visual-optical spectrum. Machine vision is not.
Cameras sensitive to diverse infrared spectral bands can improve the capacities of
autonomous systems and provide a comprehensive view. Relevant scene content
can be made visible, particularly in situations when sensors of other modalities,
such as a visual-optical camera, require a source of illumination. As a result, increasing the level of automation not only avoids human errors but also reduces
machine-induced errors. Furthermore, multi-spectral sensor systems with infrared
imagery as one modality are a rich source of information and can conceivably
increase the robustness of many autonomous systems. Robotics, automobiles,
biometrics, security, surveillance, and the military are some examples of fields
that can profit from the use of infrared imagery in their respective applications.
Although multimodal spectral sensors have come a long way, there are still several
bottlenecks that prevent us from combining their output information and using
them as comprehensive images. The primary issue with infrared imaging is the lack
of potential benefits due to their cost influence on sensor resolution, which grows
exponentially with greater resolution. Due to the more costly sensor technology
required for their development, their resolutions are substantially lower than thoseof regular digital cameras.
This thesis aims to improve beyond-visible-spectrum machine vision by integrating multi-modal spectral sensors. The emphasis is on transforming the produced images to enhance their resolution to match expected human perception, bring the color representation close to human understanding of natural color, and improve machine vision application performance. This research focuses mainly on two tasks, image Colorization and Image Super resolution for both single- and cross-domain problems. We first start with an extensive review of the state of the art in both tasks, point out the shortcomings of existing approaches, and then present our solutions to address their limitations. Our solutions demonstrate that low-cost channel information (i.e., visible image) can be used to improve expensive channel
information (i.e., infrared image), resulting in images with higher quality and closer to human perception at a lower cost than a high-cost infrared camera.

Abstract: Recent breakthroughs in single image super resolution have investigated the potential of deep Convolutional Neural Networks (CNNs) to improve performance. However, CNNs based models suffer from their limited fields and their inability to adapt to the input content. Recently, Transformer based models were presented, which demonstrated major performance gains in Natural Language Processing and Vision tasks while mitigating the drawbacks of CNNs. Nevertheless, Transformer computational complexity can increase quadratically for high-resolution images, and the fact that it ignores the original structures of the image by converting them to the 1D structure can make it problematic to capture the local context information and adapt it for real-time applications. In this paper, we present, SRFormer, an efficient yet powerful Transformer-based architecture, by making several key designs in the building of Transformer blocks and Transformer layers that allow us to consider the original structure of the image (i.e., 2D structure) while capturing both local and global dependencies without raising computational demands or memory consumption. We also present a Gated Multi-Layer Perceptron (MLP) Feature Fusion module to aggregate the features of different stages of Transformer blocks by focusing on inter-spatial relationships while adding minor computational costs to the network. We have conducted extensive experiments on several super-resolution benchmark datasets to evaluate our approach. SRFormer demonstrates superior performance compared to state-of-the-art methods from both Transformer and Convolutional networks, with an improvement margin of 0.1∼0.53dB . Furthermore, while SRFormer has almost the same model size, it outperforms SwinIR by 0.47% and inference time by half the time of SwinIR. The code will be available on GitHub.