Michael Kampffmeyer

Daniel J. Trosten, Sigurd Løkse, Robert Jenssen et al.

Self-supervised learning is a central component in recent approaches to deep multi-view clustering (MVC). However, we find large variations in the development of self-supervision-based methods for deep MVC, potentially slowing the progress of the field. To address this, we present DeepMVC, a unified framework for deep MVC that includes many recent methods as instances. We leverage our framework to make key observations about the effect of self-supervision, and in particular, drawbacks of aligning representations with contrastive learning. Further, we prove that contrastive alignment can negatively influence cluster separability, and that this effect becomes worse when the number of views increases. Motivated by our findings, we develop several new DeepMVC instances with new forms of self-supervision. We conduct extensive experiments and find that (i) in line with our theoretical findings, contrastive alignments decreases performance on datasets with many views; (ii) all methods benefit from some form of self-supervision; and (iii) our new instances outperform previous methods on several datasets. Based on our results, we suggest several promising directions for future research. To enhance the openness of the field, we provide an open-source implementation of DeepMVC, including recent models and our new instances. Our implementation includes a consistent evaluation protocol, facilitating fair and accurate evaluation of methods and components.

Haoyuan Li, Haoye Dong, Hanchao Jia et al.

Multi-person 3D mesh recovery from videos is a critical first step towards automatic perception of group behavior in virtual reality, physical therapy and beyond. However, existing approaches rely on multi-stage paradigms, where the person detection and tracking stages are performed in a multi-person setting, while temporal dynamics are only modeled for one person at a time. Consequently, their performance is severely limited by the lack of inter-person interactions in the spatial-temporal mesh recovery, as well as by detection and tracking defects. To address these challenges, we propose the Coordinate transFormer (CoordFormer) that directly models multi-person spatial-temporal relations and simultaneously performs multi-mesh recovery in an end-to-end manner. Instead of partitioning the feature map into coarse-scale patch-wise tokens, CoordFormer leverages a novel Coordinate-Aware Attention to preserve pixel-level spatial-temporal coordinate information. Additionally, we propose a simple, yet effective Body Center Attention mechanism to fuse position information. Extensive experiments on the 3DPW dataset demonstrate that CoordFormer significantly improves the state-of-the-art, outperforming the previously best results by 4.2%, 8.8% and 4.7% according to the MPJPE, PAMPJPE, and PVE metrics, respectively, while being 40% faster than recent video-based approaches. The released code can be found at https://github.com/Li-Hao-yuan/CoordFormer.

Xujie Zhang, Yu Sha, Michael C. Kampffmeyer et al.

Cross-modal fashion image synthesis has emerged as one of the most promising directions in the generation domain due to the vast untapped potential of incorporating multiple modalities and the wide range of fashion image applications. To facilitate accurate generation, cross-modal synthesis methods typically rely on Contrastive Language-Image Pre-training (CLIP) to align textual and garment information. In this work, we argue that simply aligning texture and garment information is not sufficient to capture the semantics of the visual information and therefore propose MaskCLIP. MaskCLIP decomposes the garments into semantic parts, ensuring fine-grained and semantically accurate alignment between the visual and text information. Building on MaskCLIP, we propose ARMANI, a unified cross-modal fashion designer with part-level garment-text alignment. ARMANI discretizes an image into uniform tokens based on a learned cross-modal codebook in its first stage and uses a Transformer to model the distribution of image tokens for a real image given the tokens of the control signals in its second stage. Contrary to prior approaches that also rely on two-stage paradigms, ARMANI introduces textual tokens into the codebook, making it possible for the model to utilize fine-grain semantic information to generate more realistic images. Further, by introducing a cross-modal Transformer, ARMANI is versatile and can accomplish image synthesis from various control signals, such as pure text, sketch images, and partial images. Extensive experiments conducted on our newly collected cross-modal fashion dataset demonstrate that ARMANI generates photo-realistic images in diverse synthesis tasks and outperforms existing state-of-the-art cross-modal image synthesis approaches.Our code is available at https://github.com/Harvey594/ARMANI.

Stine Hansen, Srishti Gautam, Robert Jenssen et al.

Recent work has shown that label-efficient few-shot learning through self-supervision can achieve promising medical image segmentation results. However, few-shot segmentation models typically rely on prototype representations of the semantic classes, resulting in a loss of local information that can degrade performance. This is particularly problematic for the typically large and highly heterogeneous background class in medical image segmentation problems. Previous works have attempted to address this issue by learning additional prototypes for each class, but since the prototypes are based on a limited number of slices, we argue that this ad-hoc solution is insufficient to capture the background properties. Motivated by this, and the observation that the foreground class (e.g., one organ) is relatively homogeneous, we propose a novel anomaly detection-inspired approach to few-shot medical image segmentation in which we refrain from modeling the background explicitly. Instead, we rely solely on a single foreground prototype to compute anomaly scores for all query pixels. The segmentation is then performed by thresholding these anomaly scores using a learned threshold. Assisted by a novel self-supervision task that exploits the 3D structure of medical images through supervoxels, our proposed anomaly detection-inspired few-shot medical image segmentation model outperforms previous state-of-the-art approaches on two representative MRI datasets for the tasks of abdominal organ segmentation and cardiac segmentation.

Kristoffer Wickstrøm, Michael Kampffmeyer, Karl Øyvind Mikalsen et al.

The lack of labeled data is a key challenge for learning useful representation from time series data. However, an unsupervised representation framework that is capable of producing high quality representations could be of great value. It is key to enabling transfer learning, which is especially beneficial for medical applications, where there is an abundance of data but labeling is costly and time consuming. We propose an unsupervised contrastive learning framework that is motivated from the perspective of label smoothing. The proposed approach uses a novel contrastive loss that naturally exploits a data augmentation scheme in which new samples are generated by mixing two data samples with a mixing component. The task in the proposed framework is to predict the mixing component, which is utilized as soft targets in the loss function. Experiments demonstrate the framework's superior performance compared to other representation learning approaches on both univariate and multivariate time series and illustrate its benefits for transfer learning for clinical time series.

Srishti Gautam, Ahcene Boubekki, Stine Hansen et al.

The need for interpretable models has fostered the development of self-explainable classifiers. Prior approaches are either based on multi-stage optimization schemes, impacting the predictive performance of the model, or produce explanations that are not transparent, trustworthy or do not capture the diversity of the data. To address these shortcomings, we propose ProtoVAE, a variational autoencoder-based framework that learns class-specific prototypes in an end-to-end manner and enforces trustworthiness and diversity by regularizing the representation space and introducing an orthonormality constraint. Finally, the model is designed to be transparent by directly incorporating the prototypes into the decision process. Extensive comparisons with previous self-explainable approaches demonstrate the superiority of ProtoVAE, highlighting its ability to generate trustworthy and diverse explanations, while not degrading predictive performance.

Solveig Thrun, Stine Hansen, Zijun Sun et al.

Regular mammography screening is crucial for early breast cancer detection. By leveraging deep learning-based risk models, screening intervals can be personalized, especially for high-risk individuals. While recent methods increasingly incorporate longitudinal information from prior mammograms, accurate spatial alignment across time points remains a key challenge. Misalignment can obscure meaningful tissue changes and degrade model performance. In this study, we provide insights into various alignment strategies, image-based registration, feature-level (representation space) alignment with and without regularization, and implicit alignment methods, for their effectiveness in longitudinal deep learning-based risk modeling. Using two large-scale mammography datasets, we assess each method across key metrics, including predictive accuracy, precision, recall, and deformation field quality. Our results show that image-based registration consistently outperforms the more recently favored feature-based and implicit approaches across all metrics, enabling more accurate, temporally consistent predictions and generating smooth, anatomically plausible deformation fields. Although regularizing the deformation field improves deformation quality, it reduces the risk prediction performance of feature-level alignment. Applying image-based deformation fields within the feature space yields the best risk prediction performance. These findings underscore the importance of image-based deformation fields for spatial alignment in longitudinal risk modeling, offering improved prediction accuracy and robustness. This approach has strong potential to enhance personalized screening and enable earlier interventions for high-risk individuals. The code is available at https://github.com/sot176/Mammogram_Alignment_Study_Risk_Prediction.git, allowing full reproducibility of the results.

Nanqing Dong, Zhipeng Wang, Jiahao Sun et al.

In the era of deep learning, federated learning (FL) presents a promising approach that allows multi-institutional data owners, or clients, to collaboratively train machine learning models without compromising data privacy. However, most existing FL approaches rely on a centralized server for global model aggregation, leading to a single point of failure. This makes the system vulnerable to malicious attacks when dealing with dishonest clients. In this work, we address this problem by proposing a secure and reliable FL system based on blockchain and distributed ledger technology. Our system incorporates a peer-to-peer voting mechanism and a reward-and-slash mechanism, which are powered by on-chain smart contracts, to detect and deter malicious behaviors. Both theoretical and empirical analyses are presented to demonstrate the effectiveness of the proposed approach, showing that our framework is robust against malicious client-side behaviors.

Daniel J. Trosten, Rwiddhi Chakraborty, Sigurd Løkse et al.

Distance-based classification is frequently used in transductive few-shot learning (FSL). However, due to the high-dimensionality of image representations, FSL classifiers are prone to suffer from the hubness problem, where a few points (hubs) occur frequently in multiple nearest neighbour lists of other points. Hubness negatively impacts distance-based classification when hubs from one class appear often among the nearest neighbors of points from another class, degrading the classifier's performance. To address the hubness problem in FSL, we first prove that hubness can be eliminated by distributing representations uniformly on the hypersphere. We then propose two new approaches to embed representations on the hypersphere, which we prove optimize a tradeoff between uniformity and local similarity preservation -- reducing hubness while retaining class structure. Our experiments show that the proposed methods reduce hubness, and significantly improves transductive FSL accuracy for a wide range of classifiers.

Kristoffer Knutsen Wickstrøm, Eirik Agnalt Østmo, Keyur Radiya et al.

Deep learning-based approaches for content-based image retrieval (CBIR) of CT liver images is an active field of research, but suffers from some critical limitations. First, they are heavily reliant on labeled data, which can be challenging and costly to acquire. Second, they lack transparency and explainability, which limits the trustworthiness of deep CBIR systems. We address these limitations by (1) proposing a self-supervised learning framework that incorporates domain-knowledge into the training procedure and (2) providing the first representation learning explainability analysis in the context of CBIR of CT liver images. Results demonstrate improved performance compared to the standard self-supervised approach across several metrics, as well as improved generalisation across datasets. Further, we conduct the first representation learning explainability analysis in the context of CBIR, which reveals new insights into the feature extraction process. Lastly, we perform a case study with cross-examination CBIR that demonstrates the usability of our proposed framework. We believe that our proposed framework could play a vital role in creating trustworthy deep CBIR systems that can successfully take advantage of unlabeled data.

Kristoffer Wickstrøm, J. Emmanuel Johnson, Sigurd Løkse et al.

This paper presents the kernelized Taylor diagram, a graphical framework for visualizing similarities between data populations. The kernelized Taylor diagram builds on the widely used Taylor diagram, which is used to visualize similarities between populations. However, the Taylor diagram has several limitations such as not capturing non-linear relationships and sensitivity to outliers. To address such limitations, we propose the kernelized Taylor diagram. Our proposed kernelized Taylor diagram is capable of visualizing similarities between populations with minimal assumptions of the data distributions. The kernelized Taylor diagram relates the maximum mean discrepancy and the kernel mean embedding in a single diagram, a construction that, to the best of our knowledge, have not been devised prior to this work. We believe that the kernelized Taylor diagram can be a valuable tool in data visualization.

Sara Björk, Stian N. Anfinsen, Michael Kampffmeyer et al.

In prediction of forest parameters with data from remote sensing (RS), regression models have traditionally been trained on a small sample of ground reference data. This paper proposes to impute this sample of true prediction targets with data from an existing RS-based prediction map that we consider as pseudo-targets. This substantially increases the amount of target training data and leverages the use of deep learning (DL) for semi-supervised regression modelling. We use prediction maps constructed from airborne laser scanning (ALS) data to provide accurate pseudo-targets and free data from Sentinel-1's C-band synthetic aperture radar (SAR) as regressors. A modified U-Net architecture is adapted with a selection of different training objectives. We demonstrate that when a judicious combination of loss functions is used, the semi-supervised imputation strategy produces results that surpass traditional ALS-based regression models, even though \sen data are considered as inferior for forest monitoring. These results are consistent for experiments on above-ground biomass prediction in Tanzania and stem volume prediction in Norway, representing a diversity in parameters and forest types that emphasises the robustness of the approach.

Xujie Zhang, Binbin Yang, Michael C. Kampffmeyer et al.

Cross-modal garment synthesis and manipulation will significantly benefit the way fashion designers generate garments and modify their designs via flexible linguistic interfaces.Current approaches follow the general text-to-image paradigm and mine cross-modal relations via simple cross-attention modules, neglecting the structural correspondence between visual and textual representations in the fashion design domain. In this work, we instead introduce DiffCloth, a diffusion-based pipeline for cross-modal garment synthesis and manipulation, which empowers diffusion models with flexible compositionality in the fashion domain by structurally aligning the cross-modal semantics. Specifically, we formulate the part-level cross-modal alignment as a bipartite matching problem between the linguistic Attribute-Phrases (AP) and the visual garment parts which are obtained via constituency parsing and semantic segmentation, respectively. To mitigate the issue of attribute confusion, we further propose a semantic-bundled cross-attention to preserve the spatial structure similarities between the attention maps of attribute adjectives and part nouns in each AP. Moreover, DiffCloth allows for manipulation of the generated results by simply replacing APs in the text prompts. The manipulation-irrelevant regions are recognized by blended masks obtained from the bundled attention maps of the APs and kept unchanged. Extensive experiments on the CM-Fashion benchmark demonstrate that DiffCloth both yields state-of-the-art garment synthesis results by leveraging the inherent structural information and supports flexible manipulation with region consistency.

Zhenyu Xie, Zaiyu Huang, Fuwei Zhao et al.

Image-based virtual try-on is one of the most promising applications of human-centric image generation due to its tremendous real-world potential. In this work, we take a step forwards to explore versatile virtual try-on solutions, which we argue should possess three main properties, namely, they should support unsupervised training, arbitrary garment categories, and controllable garment editing. To this end, we propose a characteristic-preserving end-to-end network, the PAtch-routed SpaTially-Adaptive GAN++ (PASTA-GAN++), to achieve a versatile system for high-resolution unpaired virtual try-on. Specifically, our PASTA-GAN++ consists of an innovative patch-routed disentanglement module to decouple the intact garment into normalized patches, which is capable of retaining garment style information while eliminating the garment spatial information, thus alleviating the overfitting issue during unsupervised training. Furthermore, PASTA-GAN++ introduces a patch-based garment representation and a patch-guided parsing synthesis block, allowing it to handle arbitrary garment categories and support local garment editing. Finally, to obtain try-on results with realistic texture details, PASTA-GAN++ incorporates a novel spatially-adaptive residual module to inject the coarse warped garment feature into the generator. Extensive experiments on our newly collected UnPaired virtual Try-on (UPT) dataset demonstrate the superiority of PASTA-GAN++ over existing SOTAs and its ability for controllable garment editing.

Zaiyu Huang, Hanhui Li, Zhenyu Xie et al.

In this paper, we target image-based person-to-person virtual try-on in the presence of diverse poses and large viewpoint variations. Existing methods are restricted in this setting as they estimate garment warping flows mainly based on 2D poses and appearance, which omits the geometric prior of the 3D human body shape. Moreover, current garment warping methods are confined to localized regions, which makes them ineffective in capturing long-range dependencies and results in inferior flows with artifacts. To tackle these issues, we present 3D-aware global correspondences, which are reliable flows that jointly encode global semantic correlations, local deformations, and geometric priors of 3D human bodies. Particularly, given an image pair depicting the source and target person, (a) we first obtain their pose-aware and high-level representations via two encoders, and introduce a coarse-to-fine decoder with multiple refinement modules to predict the pixel-wise global correspondence. (b) 3D parametric human models inferred from images are incorporated as priors to regularize the correspondence refinement process so that our flows can be 3D-aware and better handle variations of pose and viewpoint. (c) Finally, an adversarial generator takes the garment warped by the 3D-aware flow, and the image of the target person as inputs, to synthesize the photo-realistic try-on result. Extensive experiments on public benchmarks and our HardPose test set demonstrate the superiority of our method against the SOTA try-on approaches.

Luca Tomasetti, Stine Hansen, Mahdieh Khanmohammadi et al.

Precise ischemic lesion segmentation plays an essential role in improving diagnosis and treatment planning for ischemic stroke, one of the prevalent diseases with the highest mortality rate. While numerous deep neural network approaches have recently been proposed to tackle this problem, these methods require large amounts of annotated regions during training, which can be impractical in the medical domain where annotated data is scarce. As a remedy, we present a prototypical few-shot segmentation approach for ischemic lesion segmentation using only one annotated sample during training. The proposed approach leverages a novel self-supervised training mechanism that is tailored to the task of ischemic stroke lesion segmentation by exploiting color-coded parametric maps generated from Computed Tomography Perfusion scans. We illustrate the benefits of our proposed training mechanism, leading to considerable improvements in performance in the few-shot setting. Given a single annotated patient, an average Dice score of 0.58 is achieved for the segmentation of ischemic lesions.

Nanqing Dong, Michael Kampffmeyer, Irina Voiculescu

Using decentralized data for federated training is one promising emerging research direction for alleviating data scarcity in the medical domain. However, in contrast to large-scale fully labeled data commonly seen in general object recognition tasks, the local medical datasets are more likely to only have images annotated for a subset of classes of interest due to high annotation costs. In this paper, we consider a practical yet under-explored problem, where underrepresented classes only have few labeled instances available and only exist in a few clients of the federated system. We show that standard federated learning approaches fail to learn robust multi-label classifiers with extreme class imbalance and address it by proposing a novel federated learning framework, FedFew. FedFew consists of three stages, where the first stage leverages federated self-supervised learning to learn class-agnostic representations. In the second stage, the decentralized partially labeled data are exploited to learn an energy-based multi-label classifier for the common classes. Finally, the underrepresented classes are detected based on the energy and a prototype-based nearest-neighbor model is proposed for few-shot matching. We evaluate FedFew on multi-label thoracic disease classification tasks and demonstrate that it outperforms the federated baselines by a large margin.

Eirik A. Østmo, Kristoffer K. Wickstrøm, Keyur Radiya et al.

Deep learning has the potential to revolutionize medical practice by automating and performing important tasks like detecting and delineating the size and locations of cancers in medical images. However, most deep learning models rely on augmentation techniques that treat medical images as natural images. For contrast-enhanced Computed Tomography (CT) images in particular, the signals producing the voxel intensities have physical meaning, which is lost during preprocessing and augmentation when treating such images as natural images. To address this, we propose a novel preprocessing and intensity augmentation scheme inspired by how radiologists leverage multiple viewing windows when evaluating CT images. Our proposed method, window shifting, randomly places the viewing windows around the region of interest during training. This approach improves liver lesion segmentation performance and robustness on images with poorly timed contrast agent. Our method outperforms classical intensity augmentations as well as the intensity augmentation pipeline of the popular nn-UNet on multiple datasets.

Theodor Forgaard, Jarle H. Reksten, Anders U. Waldeland et al.

Current Earth observation foundation models are architecturally rigid, struggle with heterogeneous sensors and are constrained to fixed patch sizes. This limits their deployment in real-world scenarios requiring flexible computeaccuracy trade-offs. We propose THOR, a "computeadaptive" foundation model that solves both input heterogeneity and deployment rigidity. THOR is the first architecture to unify data from Copernicus Sentinel-1, -2, and -3 (OLCI & SLSTR) satellites, processing their native 10 m to 1000 m resolutions in a single model. We pre-train THOR with a novel randomized patch and input image size strategy. This allows a single set of pre-trained weights to be deployed at inference with any patch size, enabling a dynamic trade-off between computational cost and feature resolution without retraining. We pre-train THOR on THOR Pretrain, a new, large-scale multi-sensor dataset and demonstrate state-of-the-art performance on downstream benchmarks, particularly in data-limited regimes like the PANGAEA 10% split, validating that THOR's flexible feature generation excels for diverse climate and society applications.

Zhenyu Xie, Ji Xia, Michael Kampffmeyer et al.

Controllable character animation has advanced rapidly in recent years, yet multi-character animation remains underexplored. As the number of characters grows, multi-character reference encoding becomes more susceptible to latent identity entanglement, resulting in identity bleeding and reduced controllability. Moreover, learning precise and spatio-temporally consistent correspondences between reference identities and driving pose sequences becomes increasingly challenging, often leading to identity-pose mis-binding and inconsistency in generated videos. To address these challenges, we propose AnyCrowd, a Diffusion Transformer (DiT)-based video generation framework capable of scaling to an arbitrary number of characters. Specifically, we first introduce an Instance-Isolated Latent Representation (IILR), which encodes character instances independently prior to DiT processing to prevent latent identity entanglement. Building on this disentangled representation, we further propose Tri-Stage Decoupled Attention (TSDA) to bind identities to driving poses by decomposing self-attention into: (i) instance-aware foreground attention, (ii) background-centric interaction, and (iii) global foreground-background coordination. Furthermore, to mitigate token ambiguity in overlapping regions, an Adaptive Gated Fusion (AGF) module is integrated within TSDA to predict identity-aware weights, effectively fusing competing token groups into identity-consistent representations...

Kristoffer Wickstrøm, Teresa Dorszewski, Siyan Chen et al.

Current approaches for designing self-explainable models (SEMs) require complicated training procedures and specific architectures which makes them impractical. With the advance of general purpose foundation models based on Vision Transformers (ViTs), this impracticability becomes even more problematic. Therefore, new methods are necessary to provide transparency and reliability to ViT-based foundation models. In this work, we present a new method for turning any well-trained ViT-based model into a SEM without retraining, which we call Keypoint Counting Classifiers (KCCs). Recent works have shown that ViTs can automatically identify matching keypoints between images with high precision, and we build on these results to create an easily interpretable decision process that is inherently visualizable in the input. We perform an extensive evaluation which show that KCCs improve the human-machine communication compared to recent baselines. We believe that KCCs constitute an important step towards making ViT-based foundation models more transparent and reliable.

Rwiddhi Chakraborty, Adrian Sletten, Michael Kampffmeyer

Group robustness strategies aim to mitigate learned biases in deep learning models that arise from spurious correlations present in their training datasets. However, most existing methods rely on the access to the label distribution of the groups, which is time-consuming and expensive to obtain. As a result, unsupervised group robustness strategies are sought. Based on the insight that a trained model's classification strategies can be inferred accurately based on explainability heatmaps, we introduce ExMap, an unsupervised two stage mechanism designed to enhance group robustness in traditional classifiers. ExMap utilizes a clustering module to infer pseudo-labels based on a model's explainability heatmaps, which are then used during training in lieu of actual labels. Our empirical studies validate the efficacy of ExMap - We demonstrate that it bridges the performance gap with its supervised counterparts and outperforms existing partially supervised and unsupervised methods. Additionally, ExMap can be seamlessly integrated with existing group robustness learning strategies. Finally, we demonstrate its potential in tackling the emerging issue of multiple shortcut mitigation\footnote{Code available at \url{https://github.com/rwchakra/exmap}}.

Solveig Thrun, Stine Hansen, Zijun Sun et al.

Regular mammography screening is essential for early breast cancer detection. Deep learning-based risk prediction methods have sparked interest to adjust screening intervals for high-risk groups. While early methods focused only on current mammograms, recent approaches leverage the temporal aspect of screenings to track breast tissue changes over time, requiring spatial alignment across different time points. Two main strategies for this have emerged: explicit feature alignment through deformable registration and implicit learned alignment using techniques like transformers, with the former providing more control. However, the optimal approach for explicit alignment in mammography remains underexplored. In this study, we provide insights into where explicit alignment should occur (input space vs. representation space) and if alignment and risk prediction should be jointly optimized. We demonstrate that jointly learning explicit alignment in representation space while optimizing risk estimation performance, as done in the current state-of-the-art approach, results in a trade-off between alignment quality and predictive performance and show that image-level alignment is superior to representation-level alignment, leading to better deformation field quality and enhanced risk prediction accuracy. The code is available at https://github.com/sot176/Longitudinal_Mammogram_Alignment.git.

Srishti Gautam, Ahcene Boubekki, Marina M. C. Höhne et al.

Explainable AI (XAI) has unfolded in two distinct research directions with, on the one hand, post-hoc methods that explain the predictions of a pre-trained black-box model and, on the other hand, self-explainable models (SEMs) which are trained directly to provide explanations alongside their predictions. While the latter is preferred in safety-critical scenarios, post-hoc approaches have received the majority of attention until now, owing to their simplicity and ability to explain base models without retraining. Current SEMs, instead, require complex architectures and heavily regularized loss functions, thus necessitating specific and costly training. To address this shortcoming and facilitate wider use of SEMs, we propose a simple yet efficient universal method called KMEx (K-Means Explainer), which can convert any existing pre-trained model into a prototypical SEM. The motivation behind KMEx is to enhance transparency in deep learning-based decision-making via class-prototype-based explanations that are diverse and trustworthy without retraining the base model. We compare models obtained from KMEx to state-of-the-art SEMs using an extensive qualitative evaluation to highlight the strengths and weaknesses of each model, further paving the way toward a more reliable and objective evaluation of SEMs (The code is available at https://github.com/SrishtiGautam/KMEx).

Muhammad Sarmad, Arnt-Børre Salberg, Michael Kampffmeyer

This paper presents DiffFuSR, a modular pipeline for super-resolving all 12 spectral bands of Sentinel-2 Level-2A imagery to a unified ground sampling distance (GSD) of 2.5 meters. The pipeline comprises two stages: (i) a diffusion-based super-resolution (SR) model trained on high-resolution RGB imagery from the NAIP and WorldStrat datasets, harmonized to simulate Sentinel-2 characteristics; and (ii) a learned fusion network that upscales the remaining multispectral bands using the super-resolved RGB image as a spatial prior. We introduce a robust degradation model and contrastive degradation encoder to support blind SR. Extensive evaluations of the proposed SR pipeline on the OpenSR benchmark demonstrate that the proposed method outperforms current SOTA baselines in terms of reflectance fidelity, spectral consistency, spatial alignment, and hallucination suppression. Furthermore, the fusion network significantly outperforms classical pansharpening approaches, enabling accurate enhancement of Sentinel-2's 20 m and 60 m bands. This study underscores the power of harmonized learning with generative priors and fusion strategies to create a modular framework for Sentinel-2 SR. Our code and models can be found at https://github.com/NorskRegnesentral/DiffFuSR.

Durgesh Kumar Singh, Qing Cao, Sarina Thomas et al.

Clinical guidelines recommend performing left ventricular (LV) linear measurements in B-mode echocardiographic images at the basal level -- typically at the mitral valve leaflet tips -- and aligned perpendicular to the LV long axis along a virtual scanline (SL). However, most automated methods estimate landmarks directly from B-mode images for the measurement task, where even small shifts in predicted points along the LV walls can lead to significant measurement errors, reducing their clinical reliability. A recent semi-automatic method, EnLVAM, addresses this limitation by constraining landmark prediction to a clinician-defined SL and training on generated Anatomical Motion Mode (AMM) images to predict LV landmarks along the same. To enable full automation, a contour-aware SL placement approach is proposed in this work, in which the LV contour is estimated using a weakly supervised B-mode landmark detector. SL placement is then performed by inferring the LV long axis and the basal level- mimicking clinical guidelines. Building on this foundation, we introduce \textit{WiseLVAM} -- a novel, fully automated yet manually adaptable framework for automatically placing the SL and then automatically performing the LV linear measurements in the AMM mode. \textit{WiseLVAM} utilizes the structure-awareness from B-mode images and the motion-awareness from AMM mode to enhance robustness and accuracy with the potential to provide a practical solution for the routine clinical application. The source code is publicly available at https://github.com/SFI-Visual-Intelligence/wiselvam.git.

Hyeongji Kim, Stine Hansen, Michael Kampffmeyer

Common prototype-based medical image few-shot segmentation (FSS) methods model foreground and background classes using class-specific prototypes. However, given the high variability of the background, a more promising direction is to focus solely on foreground modeling, treating the background as an anomaly -- an approach introduced by ADNet. Yet, ADNet faces three key limitations: dependence on a single prototype per class, a focus on binary classification, and fixed thresholds that fail to adapt to patient and organ variability. To address these shortcomings, we propose the Tied Prototype Model (TPM), a principled reformulation of ADNet with tied prototype locations for foreground and background distributions. Building on its probabilistic foundation, TPM naturally extends to multiple prototypes and multi-class segmentation while effectively separating non-typical background features. Notably, both extensions lead to improved segmentation accuracy. Finally, we leverage naturally occurring class priors to define an ideal target for adaptive thresholds, boosting segmentation performance. Taken together, TPM provides a fresh perspective on prototype-based FSS for medical image segmentation. The code can be found at https://github.com/hjk92g/TPM-FSS.

Qinghui Liu, Michael Kampffmeyer, Robert Jenssen et al.

We propose a novel architecture called the Multi-view Self-Constructing Graph Convolutional Networks (MSCG-Net) for semantic segmentation. Building on the recently proposed Self-Constructing Graph (SCG) module, which makes use of learnable latent variables to self-construct the underlying graphs directly from the input features without relying on manually built prior knowledge graphs, we leverage multiple views in order to explicitly exploit the rotational invariance in airborne images. We further develop an adaptive class weighting loss to address the class imbalance. We demonstrate the effectiveness and flexibility of the proposed method on the Agriculture-Vision challenge dataset and our model achieves very competitive results (0.547 mIoU) with much fewer parameters and at a lower computational cost compared to related pure-CNN based work. Code will be available at: github.com/samleoqh/MSCG-Net

Qinghui Liu, Michael Kampffmeyer, Robert Jessen et al.

Land cover classification of remote sensing images is a challenging task due to limited amounts of annotated data, highly imbalanced classes, frequent incorrect pixel-level annotations, and an inherent complexity in the semantic segmentation task. In this article, we propose a novel architecture called the dense dilated convolutions' merging network (DDCM-Net) to address this task. The proposed DDCM-Net consists of dense dilated image convolutions merged with varying dilation rates. This effectively utilizes rich combinations of dilated convolutions that enlarge the network's receptive fields with fewer parameters and features compared with the state-of-the-art approaches in the remote sensing domain. Importantly, DDCM-Net obtains fused local- and global-context information, in effect incorporating surrounding discriminative capability for multiscale and complex-shaped objects with similar color and textures in very high-resolution aerial imagery. We demonstrate the effectiveness, robustness, and flexibility of the proposed DDCM-Net on the publicly available ISPRS Potsdam and Vaihingen data sets, as well as the DeepGlobe land cover data set. Our single model, trained on three-band Potsdam and Vaihingen data sets, achieves better accuracy in terms of both mean intersection over union (mIoU) and F1-score compared with other published models trained with more than three-band data. We further validate our model on the DeepGlobe data set, achieving state-of-the-art result 56.2% mIoU with much fewer parameters and at a lower computational cost compared with related recent work. Code available at https://github.com/samleoqh/DDCM-Semantic-Segmentation-PyTorch

Daniel J. Trosten, Sigurd Løkse, Robert Jenssen et al.

Objective Function Mismatch (OFM) occurs when the optimization of one objective has a negative impact on the optimization of another objective. In this work we study OFM in deep clustering, and find that the popular autoencoder-based approach to deep clustering can lead to both reduced clustering performance, and a significant amount of OFM between the reconstruction and clustering objectives. To reduce the mismatch, while maintaining the structure-preserving property of an auxiliary objective, we propose a set of new auxiliary objectives for deep clustering, referred to as the Unsupervised Companion Objectives (UCOs). The UCOs rely on a kernel function to formulate a clustering objective on intermediate representations in the network. Generally, intermediate representations can include other dimensions, for instance spatial or temporal, in addition to the feature dimension. We therefore argue that the naïve approach of vectorizing and applying a vector kernel is suboptimal for such representations, as it ignores the information contained in the other dimensions. To address this drawback, we equip the UCOs with structure-exploiting tensor kernels, designed for tensors of arbitrary rank. The UCOs can thus be adapted to a broad class of network architectures. We also propose a novel, regression-based measure of OFM, allowing us to accurately quantify the amount of OFM observed during training. Our experiments show that the OFM between the UCOs and the main clustering objective is lower, compared to a similar autoencoder-based model. Further, we illustrate that the UCOs improve the clustering performance of the model, in contrast to the autoencoder-based approach. The code for our experiments is available at https://github.com/danieltrosten/tk-uco.

Ribana Roscher, Marc Rußwurm, Caroline Gevaert et al.

Recent developments and research in modern machine learning have led to substantial improvements in the geospatial field. Although numerous deep learning architectures and models have been proposed, the majority of them have been solely developed on benchmark datasets that lack strong real-world relevance. Furthermore, the performance of many methods has already saturated on these datasets. We argue that a shift from a model-centric view to a complementary data-centric perspective is necessary for further improvements in accuracy, generalization ability, and real impact on end-user applications. Furthermore, considering the entire machine learning cycle-from problem definition to model deployment with feedback-is crucial for enhancing machine learning models that can be reliable in unforeseen situations. This work presents a definition as well as a precise categorization and overview of automated data-centric learning approaches for geospatial data. It highlights the complementary role of data-centric learning with respect to model-centric in the larger machine learning deployment cycle. We review papers across the entire geospatial field and categorize them into different groups. A set of representative experiments shows concrete implementation examples. These examples provide concrete steps to act on geospatial data with data-centric machine learning approaches.

xujie zhang, Xiu Li, Michael Kampffmeyer et al.

Image-based Virtual Try-On (VITON) aims to transfer an in-shop garment image onto a target person. While existing methods focus on warping the garment to fit the body pose, they often overlook the synthesis quality around the garment-skin boundary and realistic effects like wrinkles and shadows on the warped garments. These limitations greatly reduce the realism of the generated results and hinder the practical application of VITON techniques. Leveraging the notable success of diffusion-based models in cross-modal image synthesis, some recent diffusion-based methods have ventured to tackle this issue. However, they tend to either consume a significant amount of training resources or struggle to achieve realistic try-on effects and retain garment details. For efficient and high-fidelity VITON, we propose WarpDiffusion, which bridges the warping-based and diffusion-based paradigms via a novel informative and local garment feature attention mechanism. Specifically, WarpDiffusion incorporates local texture attention to reduce resource consumption and uses a novel auto-mask module that effectively retains only the critical areas of the warped garment while disregarding unrealistic or erroneous portions. Notably, WarpDiffusion can be integrated as a plug-and-play component into existing VITON methodologies, elevating their synthesis quality. Extensive experiments on high-resolution VITON benchmarks and an in-the-wild test set demonstrate the superiority of WarpDiffusion, surpassing state-of-the-art methods both qualitatively and quantitatively.

Xujie Zhang, Ente Lin, Xiu Li et al.

This paper introduces MMTryon, a multi-modal multi-reference VIrtual Try-ON (VITON) framework, which can generate high-quality compositional try-on results by taking a text instruction and multiple garment images as inputs. Our MMTryon addresses three problems overlooked in prior literature: 1) Support of multiple try-on items. Existing methods are commonly designed for single-item try-on tasks (e.g., upper/lower garments, dresses). 2)Specification of dressing style. Existing methods are unable to customize dressing styles based on instructions (e.g., zipped/unzipped, tuck-in/tuck-out, etc.) 3) Segmentation Dependency. They further heavily rely on category-specific segmentation models to identify the replacement regions, with segmentation errors directly leading to significant artifacts in the try-on results. To address the first two issues, our MMTryon introduces a novel multi-modality and multi-reference attention mechanism to combine the garment information from reference images and dressing-style information from text instructions. Besides, to remove the segmentation dependency, MMTryon uses a parsing-free garment encoder and leverages a novel scalable data generation pipeline to convert existing VITON datasets to a form that allows MMTryon to be trained without requiring any explicit segmentation. Extensive experiments on high-resolution benchmarks and in-the-wild test sets demonstrate MMTryon's superiority over existing SOTA methods both qualitatively and quantitatively. MMTryon's impressive performance on multi-item and style-controllable virtual try-on scenarios and its ability to try on any outfit in a large variety of scenarios from any source image, opens up a new avenue for future investigation in the fashion community.

Jianqi Chen, Panwen Hu, Xiaojun Chang et al.

Recent advancements in human motion synthesis have focused on specific types of motions, such as human-scene interaction, locomotion or human-human interaction, however, there is a lack of a unified system capable of generating a diverse combination of motion types. In response, we introduce Sitcom-Crafter, a comprehensive and extendable system for human motion generation in 3D space, which can be guided by extensive plot contexts to enhance workflow efficiency for anime and game designers. The system is comprised of eight modules, three of which are dedicated to motion generation, while the remaining five are augmentation modules that ensure consistent fusion of motion sequences and system functionality. Central to the generation modules is our novel 3D scene-aware human-human interaction module, which addresses collision issues by synthesizing implicit 3D Signed Distance Function (SDF) points around motion spaces, thereby minimizing human-scene collisions without additional data collection costs. Complementing this, our locomotion and human-scene interaction modules leverage existing methods to enrich the system's motion generation capabilities. Augmentation modules encompass plot comprehension for command generation, motion synchronization for seamless integration of different motion types, hand pose retrieval to enhance motion realism, motion collision revision to prevent human collisions, and 3D retargeting to ensure visual fidelity. Experimental evaluations validate the system's ability to generate high-quality, diverse, and physically realistic motions, underscoring its potential for advancing creative workflows. Project page: https://windvchen.github.io/Sitcom-Crafter.

Haoyuan Li, Yanpeng Zhou, Tao Tang et al.

Recent advancements in multi-modal 3D pre-training methods have shown promising efficacy in learning joint representations of text, images, and point clouds. However, adopting point clouds as 3D representation fails to fully capture the intricacies of the 3D world and exhibits a noticeable gap between the discrete points and the dense 2D pixels of images. To tackle this issue, we propose UniGS, integrating 3D Gaussian Splatting (3DGS) into multi-modal pre-training to enhance the 3D representation. We first rely on the 3DGS representation to model the 3D world as a collection of 3D Gaussians with color and opacity, incorporating all the information of the 3D scene while establishing a strong connection with 2D images. Then, to achieve Language-Image-3D pertaining, UniGS starts with a pre-trained vision-language model to establish a shared visual and textual space through extensive real-world image-text pairs. Subsequently, UniGS employs a 3D encoder to align the optimized 3DGS with the Language-Image representations to learn unified multi-modal representations. To facilitate the extraction of global explicit 3D features by the 3D encoder and achieve better cross-modal alignment, we additionally introduce a novel Gaussian-Aware Guidance module that guides the learning of fine-grained representations of the 3D domain. Through extensive experiments across the Objaverse, ABO, MVImgNet and SUN RGBD datasets with zero-shot classification, text-driven retrieval and open-world understanding tasks, we demonstrate the effectiveness of UniGS in learning a more general and stronger aligned multi-modal representation. Specifically, UniGS achieves leading results across different 3D tasks with remarkable improvements over previous SOTA, Uni3D, including on zero-shot classification (+9.36%), text-driven retrieval (+4.3%) and open-world understanding (+7.92%).

Zehua Ma, Hanhui Li, Zhenyu Xie et al.

Generating 3D content from a single image remains a fundamentally challenging and ill-posed problem due to the inherent absence of geometric and textural information in occluded regions. While state-of-the-art generative models can synthesize auxiliary views to provide additional supervision, these views inevitably contain geometric inconsistencies and textural misalignments that propagate and amplify artifacts during 3D reconstruction. To effectively harness these imperfect supervisory signals, we propose an adaptive optimization framework guided by excess risk decomposition, termed ERGO. Specifically, ERGO decomposes the optimization losses in 3D Gaussian splatting into two components, i.e., excess risk that quantifies the suboptimality gap between current and optimal parameters, and Bayes error that models the irreducible noise inherent in synthesized views. This decomposition enables ERGO to dynamically estimate the view-specific excess risk and adaptively adjust loss weights during optimization. Furthermore, we introduce geometry-aware and texture-aware objectives that complement the excess-risk-derived weighting mechanism, establishing a synergistic global-local optimization paradigm. Consequently, ERGO demonstrates robustness against supervision noise while consistently enhancing both geometric fidelity and textural quality of the reconstructed 3D content. Extensive experiments on the Google Scanned Objects dataset and the OmniObject3D dataset demonstrate the superiority of ERGO over existing state-of-the-art methods.

Durgesh Singh, Ahcene Boubekki, Robert Jenssen et al.

The development of semi-supervised learning (SSL) has in recent years largely focused on the development of new consistency regularization or entropy minimization approaches, often resulting in models with complex training strategies to obtain the desired results. In this work, we instead propose a novel approach that explicitly incorporates the underlying clustering assumption in SSL through extending a recently proposed differentiable clustering module. Leveraging annotated data to guide the cluster centroids results in a simple end-to-end trainable deep SSL approach. We demonstrate that the proposed model improves the performance over the supervised-only baseline and show that our framework can be used in conjunction with other SSL methods to further boost their performance.

Durgesh K. Singh, Ahcene Boubekki, Qing Cao et al.

Linear measurements of the left ventricle (LV) in the Parasternal Long Axis (PLAX) view using B-mode echocardiography are crucial for cardiac assessment. These involve placing 4-6 landmarks along a virtual scanline (SL) perpendicular to the LV axis near the mitral valve tips. Manual placement is time-consuming and error-prone, while existing deep learning methods often misalign landmarks, causing inaccurate measurements. We propose a novel framework that enhances LV measurement accuracy by enforcing straight-line constraints. A landmark detector is trained on Anatomical M-Mode (AMM) images, computed in real time from B-mode videos, then transformed back to B-mode space. This approach addresses misalignment and reduces measurement errors. Experiments show improved accuracy over standard B-mode methods, and the framework generalizes well across network architectures. Our semi-automatic design includes a human-in-the-loop step where the user only places the SL, simplifying interaction while preserving alignment flexibility and clinical relevance.

Madi Matymov, Ba-Hien Tran, Michael Kampffmeyer et al.

Data Augmentation (DA) has become an essential tool to improve robustness and generalization of modern machine learning. However, when deciding on DA strategies it is critical to choose parameters carefully, and this can be a daunting task which is traditionally left to trial-and-error or expensive optimization based on validation performance. In this paper, we counter these limitations by proposing a novel framework for optimizing DA. In particular, we take a probabilistic view of DA, which leads to the interpretation of augmentation parameters as model (hyper)-parameters, and the optimization of the marginal likelihood with respect to these parameters as a Bayesian model selection problem. Due to its intractability, we derive a tractable Evidence Lower BOund (ELBO), which allows us to optimize augmentation parameters jointly with model parameters. We provide extensive theoretical results on variational approximation quality, generalization guarantees, invariance properties, and connections to empirical Bayes. Through experiments on computer vision tasks, we show that our approach improves calibration and yields robust performance over fixed or no augmentation. Our work provides a rigorous foundation for optimizing DA through Bayesian principles with significant potential for robust machine learning.

Kristoffer K. Wickstrøm, Thea Brüsch, Michael C. Kampffmeyer et al.

Incorporating uncertainty is crucial to provide trustworthy explanations of deep learning models. Recent works have demonstrated how uncertainty modeling can be particularly important in the unsupervised field of representation learning explainable artificial intelligence (R-XAI). Current R-XAI methods provide uncertainty by measuring variability in the importance score. However, they fail to provide meaningful estimates of whether a pixel is certainly important or not. In this work, we propose a new R-XAI method called REPEAT that addresses the key question of whether or not a pixel is \textit{certainly} important. REPEAT leverages the stochasticity of current R-XAI methods to produce multiple estimates of importance, thus considering each pixel in an image as a Bernoulli random variable that is either important or unimportant. From these Bernoulli random variables we can directly estimate the importance of a pixel and its associated certainty, thus enabling users to determine certainty in pixel importance. Our extensive evaluation shows that REPEAT gives certainty estimates that are more intuitive, better at detecting out-of-distribution data, and more concise.

Eirik A. Østmo, Kristoffer K. Wickstrøm, Keyur Radiya et al.

Contrast-enhanced Computed Tomography (CT) is important for diagnosis and treatment planning for various medical conditions. Deep learning (DL) based segmentation models may enable automated medical image analysis for detecting and delineating tumors in CT images, thereby reducing clinicians' workload. Achieving generalization capabilities in limited data domains, such as radiology, requires modern DL models to be trained with image augmentation. However, naively applying augmentation methods developed for natural images to CT scans often disregards the nature of the CT modality, where the intensities measure Hounsfield Units (HU) and have important physical meaning. This paper challenges the use of such intensity augmentations for CT imaging and shows that they may lead to artifacts and poor generalization. To mitigate this, we propose a CT-specific augmentation technique, called Random windowing, that exploits the available HU distribution of intensities in CT images. Random windowing encourages robustness to contrast-enhancement and significantly increases model performance on challenging images with poor contrast or timing. We perform ablations and analysis of our method on multiple datasets, and compare to, and outperform, state-of-the-art alternatives, while focusing on the challenge of liver tumor segmentation.

Durgesh Singh, Ahcène Boubekki, Robert Jenssen et al.

Semi-Supervised Learning (SSL) and Unsupervised Domain Adaptation (UDA) enhance the model performance by exploiting information from labeled and unlabeled data. The clustering assumption has proven advantageous for learning with limited supervision and states that data points belonging to the same cluster in a high-dimensional space should be assigned to the same category. Recent works have utilized different training mechanisms to implicitly enforce this assumption for the SSL and UDA. In this work, we take a different approach by explicitly involving a differentiable clustering module which is extended to leverage the supervised data to compute its centroids. We demonstrate the effectiveness of our straightforward end-to-end training strategy for SSL and UDA over extensive experiments and highlight its benefits, especially in low supervision regimes, both as a standalone model and as a regularizer for existing approaches.

Rogelio A Mancisidor, Robert Jenssen, Shujian Yu et al.

Multimodal learning with variational autoencoders (VAEs) requires estimating joint distributions to evaluate the evidence lower bound (ELBO). Current methods, the product and mixture of experts, aggregate single-modality distributions assuming independence for simplicity, which is an overoptimistic assumption. This research introduces a novel methodology for aggregating single-modality distributions by exploiting the principle of consensus of dependent experts (CoDE), which circumvents the aforementioned assumption. Utilizing the CoDE method, we propose a novel ELBO that approximates the joint likelihood of the multimodal data by learning the contribution of each subset of modalities. The resulting CoDE-VAE model demonstrates better performance in terms of balancing the trade-off between generative coherence and generative quality, as well as generating more precise log-likelihood estimations. CoDE-VAE further minimizes the generative quality gap as the number of modalities increases. In certain cases, it reaches a generative quality similar to that of unimodal VAEs, which is a desirable property that is lacking in most current methods. Finally, the classification accuracy achieved by CoDE-VAE is comparable to that of state-of-the-art multimodal VAE models.

Markus Heinonen, Ba-Hien Tran, Michael Kampffmeyer et al.

Introducing training-time augmentations is a key technique to enhance generalization and prepare deep neural networks against test-time corruptions. Inspired by the success of generative diffusion models, we propose a novel approach of coupling data mollification, in the form of image noising and blurring, with label smoothing to align predicted label confidences with image degradation. The method is simple to implement, introduces negligible overheads, and can be combined with existing augmentations. We demonstrate improved robustness and uncertainty quantification on the corrupted image benchmarks of CIFAR, TinyImageNet and ImageNet datasets.

Jonas Lederer, Michael Gastegger, Kristof T. Schütt et al.

In recent years, the prediction of quantum mechanical observables with machine learning methods has become increasingly popular. Message-passing neural networks (MPNNs) solve this task by constructing atomic representations, from which the properties of interest are predicted. Here, we introduce a method to automatically identify chemical moieties (molecular building blocks) from such representations, enabling a variety of applications beyond property prediction, which otherwise rely on expert knowledge. The required representation can either be provided by a pretrained MPNN, or learned from scratch using only structural information. Beyond the data-driven design of molecular fingerprints, the versatility of our approach is demonstrated by enabling the selection of representative entries in chemical databases, the automatic construction of coarse-grained force fields, as well as the identification of reaction coordinates.

Srishti Gautam, Marina M. -C. Höhne, Stine Hansen et al.

The recent trend of integrating multi-source Chest X-Ray datasets to improve automated diagnostics raises concerns that models learn to exploit source-specific correlations to improve performance by recognizing the source domain of an image rather than the medical pathology. We hypothesize that this effect is enforced by and leverages label-imbalance across the source domains, i.e, prevalence of a disease corresponding to a source. Therefore, in this work, we perform a thorough study of the effect of label-imbalance in multi-source training for the task of pneumonia detection on the widely used ChestX-ray14 and CheXpert datasets. The results highlight and stress the importance of using more faithful and transparent self-explaining models for automated diagnosis, thus enabling the inherent detection of spurious learning. They further illustrate that this undesirable effect of learning spurious correlations can be reduced considerably when ensuring label-balanced source domain datasets.

Kristoffer K. Wickstrøm, Daniel J. Trosten, Sigurd Løkse et al.

Despite the significant improvements that representation learning via self-supervision has led to when learning from unlabeled data, no methods exist that explain what influences the learned representation. We address this need through our proposed approach, RELAX, which is the first approach for attribution-based explanations of representations. Our approach can also model the uncertainty in its explanations, which is essential to produce trustworthy explanations. RELAX explains representations by measuring similarities in the representation space between an input and masked out versions of itself, providing intuitive explanations and significantly outperforming the gradient-based baseline. We provide theoretical interpretations of RELAX and conduct a novel analysis of feature extractors trained using supervised and unsupervised learning, providing insights into different learning strategies. Finally, we illustrate the usability of RELAX in multi-view clustering and highlight that incorporating uncertainty can be essential for providing low-complexity explanations, taking a crucial step towards explaining representations.

Zhenyu Xie, Zaiyu Huang, Fuwei Zhao et al.

Image-based virtual try-on is one of the most promising applications of human-centric image generation due to its tremendous real-world potential. Yet, as most try-on approaches fit in-shop garments onto a target person, they require the laborious and restrictive construction of a paired training dataset, severely limiting their scalability. While a few recent works attempt to transfer garments directly from one person to another, alleviating the need to collect paired datasets, their performance is impacted by the lack of paired (supervised) information. In particular, disentangling style and spatial information of the garment becomes a challenge, which existing methods either address by requiring auxiliary data or extensive online optimization procedures, thereby still inhibiting their scalability. To achieve a \emph{scalable} virtual try-on system that can transfer arbitrary garments between a source and a target person in an unsupervised manner, we thus propose a texture-preserving end-to-end network, the PAtch-routed SpaTially-Adaptive GAN (PASTA-GAN), that facilitates real-world unpaired virtual try-on. Specifically, to disentangle the style and spatial information of each garment, PASTA-GAN consists of an innovative patch-routed disentanglement module for successfully retaining garment texture and shape characteristics. Guided by the source person keypoints, the patch-routed disentanglement module first decouples garments into normalized patches, thus eliminating the inherent spatial information of the garment, and then reconstructs the normalized patches to the warped garment complying with the target person pose. Given the warped garment, PASTA-GAN further introduces novel spatially-adaptive residual blocks that guide the generator to synthesize more realistic garment details.

Qinghui Liu, Michael Kampffmeyer, Robert Jenssen et al.

Multi-modality data is becoming readily available in remote sensing (RS) and can provide complementary information about the Earth's surface. Effective fusion of multi-modal information is thus important for various applications in RS, but also very challenging due to large domain differences, noise, and redundancies. There is a lack of effective and scalable fusion techniques for bridging multiple modality encoders and fully exploiting complementary information. To this end, we propose a new multi-modality network (MultiModNet) for land cover mapping of multi-modal remote sensing data based on a novel pyramid attention fusion (PAF) module and a gated fusion unit (GFU). The PAF module is designed to efficiently obtain rich fine-grained contextual representations from each modality with a built-in cross-level and cross-view attention fusion mechanism, and the GFU module utilizes a novel gating mechanism for early merging of features, thereby diminishing hidden redundancies and noise. This enables supplementary modalities to effectively extract the most valuable and complementary information for late feature fusion. Extensive experiments on two representative RS benchmark datasets demonstrate the effectiveness, robustness, and superiority of the MultiModNet for multi-modal land cover classification.

Rogelio A. Mancisidor, Michael Kampffmeyer, Kjersti Aas et al.

Deep generative models with latent variables have been used lately to learn joint representations and generative processes from multi-modal data. These two learning mechanisms can, however, conflict with each other and representations can fail to embed information on the data modalities. This research studies the realistic scenario in which all modalities and class labels are available for model training, but where some modalities and labels required for downstream tasks are missing. We show, in this scenario, that the variational lower bound limits mutual information between joint representations and missing modalities. We, to counteract these problems, introduce a novel conditional multi-modal discriminative model that uses an informative prior distribution and optimizes a likelihood-free objective function that maximizes mutual information between joint representations and missing modalities. Extensive experimentation demonstrates the benefits of our proposed model, empirical results show that our model achieves state-of-the-art results in representative problems such as downstream classification, acoustic inversion, and image and annotation generation.