Anders Skaarup Johansen, Kamal Nasrollahi, Sergio Escalera, & Thomas B. Moeslund. (2023). Who Cares about the Weather? Inferring Weather Conditions for Weather-Aware Object Detection in Thermal Images. AS - Applied Sciences, 13(18).
Abstract: Deployments of real-world object detection systems often experience a degradation in performance over time due to concept drift. Systems that leverage thermal cameras are especially susceptible because the respective thermal signatures of objects and their surroundings are highly sensitive to environmental changes. In this study, two types of weather-aware latent conditioning methods are investigated. The proposed method aims to guide two object detectors, (YOLOv5 and Deformable DETR) to become weather-aware. This is achieved by leveraging an auxiliary branch that predicts weather-related information while conditioning intermediate layers of the object detector. While the conditioning methods proposed do not directly improve the accuracy of baseline detectors, it can be observed that conditioned networks manage to extract a weather-related signal from the thermal images, thus resulting in a decreased miss rate at the cost of increased false positives. The extracted signal appears noisy and is thus challenging to regress accurately. This is most likely a result of the qualitative nature of the thermal sensor; thus, further work is needed to identify an ideal method for optimizing the conditioning branch, as well as to further improve the accuracy of the system.
Keywords: thermal; object detection; concept drift; conditioning; weather recognition
|
Lei Kang, Lichao Zhang, & Dazhi Jiang. (2023). Learning Robust Self-Attention Features for Speech Emotion Recognition with Label-Adaptive Mixup. In IEEE International Conference on Acoustics, Speech and Signal Processing.
Abstract: Speech Emotion Recognition (SER) is to recognize human emotions in a natural verbal interaction scenario with machines, which is considered as a challenging problem due to the ambiguous human emotions. Despite the recent progress in SER, state-of-the-art models struggle to achieve a satisfactory performance. We propose a self-attention based method with combined use of label-adaptive mixup and center loss. By adapting label probabilities in mixup and fitting center loss to the mixup training scheme, our proposed method achieves a superior performance to the state-of-the-art methods.
|
Daniel Marczak, Grzegorz Rypesc, Sebastian Cygert, Tomasz Trzcinski, & Bartłomiej Twardowski. (2023). Generalized Continual Category Discovery.
Abstract: Most of Continual Learning (CL) methods push the limit of supervised learning settings, where an agent is expected to learn new labeled tasks and not forget previous knowledge. However, these settings are not well aligned with real-life scenarios, where a learning agent has access to a vast amount of unlabeled data encompassing both novel (entirely unlabeled) classes and examples from known classes. Drawing inspiration from Generalized Category Discovery (GCD), we introduce a novel framework that relaxes this assumption. Precisely, in any task, we allow for the existence of novel and known classes, and one must use continual version of unsupervised learning methods to discover them. We call this setting Generalized Continual Category Discovery (GCCD). It unifies CL and GCD, bridging the gap between synthetic benchmarks and real-life scenarios. With a series of experiments, we present that existing methods fail to accumulate knowledge from subsequent tasks in which unlabeled samples of novel classes are present. In light of these limitations, we propose a method that incorporates both supervised and unsupervised signals and mitigates the forgetting through the use of centroid adaptation. Our method surpasses strong CL methods adopted for GCD techniques and presents a superior representation learning performance.
|
Hao Wu, Alejandro Ariza-Casabona, Bartłomiej Twardowski, & Tri Kurniawan Wijaya. (2023). MM-GEF: Multi-modal representation meet collaborative filtering.
Abstract: In modern e-commerce, item content features in various modalities offer accurate yet comprehensive information to recommender systems. The majority of previous work either focuses on learning effective item representation during modelling user-item interactions, or exploring item-item relationships by analysing multi-modal features. Those methods, however, fail to incorporate the collaborative item-user-item relationships into the multi-modal feature-based item structure. In this work, we propose a graph-based item structure enhancement method MM-GEF: Multi-Modal recommendation with Graph Early-Fusion, which effectively combines the latent item structure underlying multi-modal contents with the collaborative signals. Instead of processing the content feature in different modalities separately, we show that the early-fusion of multi-modal features provides significant improvement. MM-GEF learns refined item representations by injecting structural information obtained from both multi-modal and collaborative signals. Through extensive experiments on four publicly available datasets, we demonstrate systematical improvements of our method over state-of-the-art multi-modal recommendation methods.
|
Anthony Cioppa, Silvio Giancola, Vladimir Somers, Floriane Magera, Xin Zhou, Hassan Mkhallati, et al. (2023). SoccerNet 2023 Challenges Results.
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.
|
Damian Sojka, Yuyang Liu, Dipam Goswami, Sebastian Cygert, Bartłomiej Twardowski, & Joost van de Weijer. (2023). Technical Report for ICCV 2023 Visual Continual Learning Challenge: Continuous Test-time Adaptation for Semantic Segmentation.
Abstract: The goal of the challenge is to develop a test-time adaptation (TTA) method, which could adapt the model to gradually changing domains in video sequences for semantic segmentation task. It is based on a synthetic driving video dataset – SHIFT. The source model is trained on images taken during daytime in clear weather. Domain changes at test-time are mainly caused by varying weather conditions and times of day. The TTA methods are evaluated in each image sequence (video) separately, meaning the model is reset to the source model state before the next sequence. Images come one by one and a prediction has to be made at the arrival of each frame. Each sequence is composed of 401 images and starts with the source domain, then gradually drifts to a different one (changing weather or time of day) until the middle of the sequence. In the second half of the sequence, the domain gradually shifts back to the source one. Ground truth data is available only for the validation split of the SHIFT dataset, in which there are only six sequences that start and end with the source domain. We conduct an analysis specifically on those sequences. Ground truth data for test split, on which the developed TTA methods are evaluated for leader board ranking, are not publicly available.
The proposed solution secured a 3rd place in a challenge and received an innovation award. Contrary to the solutions that scored better, we did not use any external pretrained models or specialized data augmentations, to keep the solutions as general as possible. We have focused on analyzing the distributional shift and developing a method that could adapt to changing data dynamics and generalize across different scenarios.
|
Mert Kilickaya, Joost van de Weijer, & Yuki M. Asano. (2023). Towards Label-Efficient Incremental Learning: A Survey.
Abstract: The current dominant paradigm when building a machine learning model is to iterate over a dataset over and over until convergence. Such an approach is non-incremental, as it assumes access to all images of all categories at once. However, for many applications, non-incremental learning is unrealistic. To that end, researchers study incremental learning, where a learner is required to adapt to an incoming stream of data with a varying distribution while preventing forgetting of past knowledge. Significant progress has been made, however, the vast majority of works focus on the fully supervised setting, making these algorithms label-hungry thus limiting their real-life deployment. To that end, in this paper, we make the first attempt to survey recently growing interest in label-efficient incremental learning. We identify three subdivisions, namely semi-, few-shot- and self-supervised learning to reduce labeling efforts. Finally, we identify novel directions that can further enhance label-efficiency and improve incremental learning scalability. Project website: this https URL.
|
Souhail Bakkali, Sanket Biswas, Zuheng Ming, Mickael Coustaty, Marçal Rusiñol, Oriol Ramos Terrades, et al. (2023). TransferDoc: A Self-Supervised Transferable Document Representation Learning Model Unifying Vision and Language.
Abstract: The field of visual document understanding has witnessed a rapid growth in emerging challenges and powerful multi-modal strategies. However, they rely on an extensive amount of document data to learn their pretext objectives in a ``pre-train-then-fine-tune'' paradigm and thus, suffer a significant performance drop in real-world online industrial settings. One major reason is the over-reliance on OCR engines to extract local positional information within a document page. Therefore, this hinders the model's generalizability, flexibility and robustness due to the lack of capturing global information within a document image. We introduce TransferDoc, a cross-modal transformer-based architecture pre-trained in a self-supervised fashion using three novel pretext objectives. TransferDoc learns richer semantic concepts by unifying language and visual representations, which enables the production of more transferable models. Besides, two novel downstream tasks have been introduced for a ``closer-to-real'' industrial evaluation scenario where TransferDoc outperforms other state-of-the-art approaches.
|
Henry Velesaca, Gisel Bastidas-Guacho, Mohammad Rouhani, & Angel Sappa. (2024). Multimodal image registration techniques: a comprehensive survey. MTAP - Multimedia Tools and Applications, .
Abstract: This manuscript presents a review of state-of-the-art techniques proposed in the literature for multimodal image registration, addressing instances where images from different modalities need to be precisely aligned in the same reference system. This scenario arises when the images to be registered come from different modalities, among the visible and thermal spectral bands, 3D-RGB, or flash-no flash, or NIR-visible. The review spans different techniques from classical approaches to more modern ones based on deep learning, aiming to highlight the particularities required at each step in the registration pipeline when dealing with multimodal images. It is noteworthy that medical images are excluded from this review due to their specific characteristics, including the use of both active and passive sensors or the non-rigid nature of the body contained in the image.
|
Justine Giroux, Mohammad Reza Karimi Dastjerdi, Yannick Hold-Geoffroy, Javier Vazquez, & Jean François Lalonde. (2024). Towards a Perceptual Evaluation Framework for Lighting Estimation. In Arxiv.
Abstract: rogress in lighting estimation is tracked by computing existing image quality assessment (IQA) metrics on images from standard datasets. While this may appear to be a reasonable approach, we demonstrate that doing so does not correlate to human preference when the estimated lighting is used to relight a virtual scene into a real photograph. To study this, we design a controlled psychophysical experiment where human observers must choose their preference amongst rendered scenes lit using a set of lighting estimation algorithms selected from the recent literature, and use it to analyse how these algorithms perform according to human perception. Then, we demonstrate that none of the most popular IQA metrics from the literature, taken individually, correctly represent human perception. Finally, we show that by learning a combination of existing IQA metrics, we can more accurately represent human preference. This provides a new perceptual framework to help evaluate future lighting estimation algorithms.
|
Trevor Canham, Javier Vazquez, D Long, Richard F. Murray, & Michael S Brown. (2021). Noise Prism: A Novel Multispectral Visualization Technique. 31st Color and Imaging Conference, .
Abstract: A novel technique for visualizing multispectral images is proposed. Inspired by how prisms work, our method spreads spectral information over a chromatic noise pattern. This is accomplished by populating the pattern with pixels representing each measurement band at a count proportional to its measured intensity. The method is advantageous because it allows for lightweight encoding and visualization of spectral information
while maintaining the color appearance of the stimulus. A four alternative forced choice (4AFC) experiment was conducted to validate the method’s information-carrying capacity in displaying metameric stimuli of varying colors and spectral basis functions. The scores ranged from 100% to 20% (less than chance given the 4AFC task), with many conditions falling somewhere in between at statistically significant intervals. Using this data, color and texture difference metrics can be evaluated and optimized to predict the legibility of the visualization technique.
|
Mohamed Ramzy Ibrahim, Robert Benavente, Daniel Ponsa, & Felipe Lumbreras. (2024). SWViT-RRDB: Shifted Window Vision Transformer Integrating Residual in Residual Dense Block for Remote Sensing Super-Resolution. In 19th International Joint Conference on Computer Vision, Imaging and Computer Graphics Theory and Applications.
Abstract: Remote sensing applications, impacted by acquisition season and sensor variety, require high-resolution images. Transformer-based models improve satellite image super-resolution but are less effective than convolutional neural networks (CNNs) at extracting local details, crucial for image clarity. This paper introduces SWViT-RRDB, a new deep learning model for satellite imagery super-resolution. The SWViT-RRDB, combining transformer with convolution and attention blocks, overcomes the limitations of existing models by better representing small objects in satellite images. In this model, a pipeline of residual fusion group (RFG) blocks is used to combine the multi-headed self-attention (MSA) with residual in residual dense block (RRDB). This combines global and local image data for better super-resolution. Additionally, an overlapping cross-attention block (OCAB) is used to enhance fusion and allow interaction between neighboring pixels to maintain long-range pixel dependencies across the image. The SWViT-RRDB model and its larger variants outperform state-of-the-art (SoTA) models on two different satellite datasets in terms of PSNR and SSIM.
|
Mingyi Yang, Fei Yang, Luka Murn, Marc Gorriz Blanch, Juil Sock, Shuai Wan, et al. (2024). Task-Switchable Pre-Processor for Image Compression for Multiple Machine Vision Tasks. IEEE Transactions on Circuits and Systems for Video Technology, .
Abstract: Visual content is increasingly being processed by machines for various automated content analysis tasks instead of being consumed by humans. Despite the existence of several compression methods tailored for machine tasks, few consider real-world scenarios with multiple tasks. In this paper, we aim to address this gap by proposing a task-switchable pre-processor that optimizes input images specifically for machine consumption prior to encoding by an off-the-shelf codec designed for human consumption. The proposed task-switchable pre-processor adeptly maintains relevant semantic information based on the specific characteristics of different downstream tasks, while effectively suppressing irrelevant information to reduce bitrate. To enhance the processing of semantic information for diverse tasks, we leverage pre-extracted semantic features to modulate the pixel-to-pixel mapping within the pre-processor. By switching between different modulations, multiple tasks can be seamlessly incorporated into the system. Extensive experiments demonstrate the practicality and simplicity of our approach. It significantly reduces the number of parameters required for handling multiple tasks while still delivering impressive performance. Our method showcases the potential to achieve efficient and effective compression for machine vision tasks, supporting the evolving demands of real-world applications.
Keywords: M Yang, F Yang, L Murn, MG Blanch, J Sock, S Wan, F Yang, L Herranz
|
Rafael E. Rivadeneira, Henry Velesaca, & Angel Sappa. (2023). Object Detection in Very Low-Resolution Thermal Images through a Guided-Based Super-Resolution Approach. In 17th International Conference on Signal-Image Technology & Internet-Based Systems.
Abstract: This work proposes a novel approach that integrates super-resolution techniques with off-the-shelf object detection methods to tackle the problem of handling very low-resolution thermal images. The suggested approach begins by enhancing the low-resolution (LR) thermal images through a guided super-resolution strategy, leveraging a high-resolution (HR) visible spectrum image. Subsequently, object detection is performed on the high-resolution thermal image. The experimental results demonstrate tremendous improvements in comparison with both scenarios: when object detection is performed on the LR thermal image alone, as well as when object detection is conducted on the up-sampled LR thermal image. Moreover, the proposed approach proves highly valuable in camouflaged scenarios where objects might remain undetected in visible spectrum images.
|
Ruben Tito, Khanh Nguyen, Marlon Tobaben, Raouf Kerkouche, Mohamed Ali Souibgui, Kangsoo Jung, et al. (2023). Privacy-Aware Document Visual Question Answering.
Abstract: Document Visual Question Answering (DocVQA) is a fast growing branch of document understanding. Despite the fact that documents contain sensitive or copyrighted information, none of the current DocVQA methods offers strong privacy guarantees.
In this work, we explore privacy in the domain of DocVQA for the first time. We highlight privacy issues in state of the art multi-modal LLM models used for DocVQA, and explore possible solutions.
Specifically, we focus on the invoice processing use case as a realistic, widely used scenario for document understanding, and propose a large scale DocVQA dataset comprising invoice documents and associated questions and answers. We employ a federated learning scheme, that reflects the real-life distribution of documents in different businesses, and we explore the use case where the ID of the invoice issuer is the sensitive information to be protected.
We demonstrate that non-private models tend to memorise, behaviour that can lead to exposing private information. We then evaluate baseline training schemes employing federated learning and differential privacy in this multi-modal scenario, where the sensitive information might be exposed through any of the two input modalities: vision (document image) or language (OCR tokens).
Finally, we design an attack exploiting the memorisation effect of the model, and demonstrate its effectiveness in probing different DocVQA models.
|
