Saman Halgamuge

Maneesha Perera, Julian De Hoog, Kasun Bandara et al.

Distributed, small-scale solar photovoltaic (PV) systems are being installed at a rapidly increasing rate. This can cause major impacts on distribution networks and energy markets. As a result, there is a significant need for improved forecasting of the power generation of these systems at different time resolutions and horizons. However, the performance of forecasting models depends on the resolution and horizon. Forecast combinations (ensembles), that combine the forecasts of multiple models into a single forecast may be robust in such cases. Therefore, in this paper, we provide comparisons and insights into the performance of five state-of-the-art forecast models and existing forecast combinations at multiple resolutions and horizons. We propose a forecast combination approach based on particle swarm optimization (PSO) that will enable a forecaster to produce accurate forecasts for the task at hand by weighting the forecasts produced by individual models. Furthermore, we compare the performance of the proposed combination approach with existing forecast combination approaches. A comprehensive evaluation is conducted using a real-world residential PV power data set measured at 25 houses located in three locations in the United States. The results across four different resolutions and four different horizons show that the PSO-based forecast combination approach outperforms the use of any individual forecast model and other forecast combination counterparts, with an average Mean Absolute Scaled Error reduction by 3.81% compared to the best performing individual model. Our approach enables a solar forecaster to produce accurate forecasts for their application regardless of the forecast resolution or horizon.

Tamasha Malepathirana, Damith Senanayake, Saman Halgamuge

Catastrophic forgetting; the loss of old knowledge upon acquiring new knowledge, is a pitfall faced by deep neural networks in real-world applications. Many prevailing solutions to this problem rely on storing exemplars (previously encountered data), which may not be feasible in applications with memory limitations or privacy constraints. Therefore, the recent focus has been on Non-Exemplar based Class Incremental Learning (NECIL) where a model incrementally learns about new classes without using any past exemplars. However, due to the lack of old data, NECIL methods struggle to discriminate between old and new classes causing their feature representations to overlap. We propose NAPA-VQ: Neighborhood Aware Prototype Augmentation with Vector Quantization, a framework that reduces this class overlap in NECIL. We draw inspiration from Neural Gas to learn the topological relationships in the feature space, identifying the neighboring classes that are most likely to get confused with each other. This neighborhood information is utilized to enforce strong separation between the neighboring classes as well as to generate old class representative prototypes that can better aid in obtaining a discriminative decision boundary between old and new classes. Our comprehensive experiments on CIFAR-100, TinyImageNet, and ImageNet-Subset demonstrate that NAPA-VQ outperforms the State-of-the-art NECIL methods by an average improvement of 5%, 2%, and 4% in accuracy and 10%, 3%, and 9% in forgetting respectively. Our code can be found in https://github.com/TamashaM/NAPA-VQ.git.

Jayanie Bogahawatte, Sachith Seneviratne, Saman Halgamuge

Whole Slide Images (WSIs) are giga-pixel in scale and are typically partitioned into small instances in WSI classification pipelines for computational feasibility. However, obtaining extensive instance level annotations is costly, making few-shot weakly supervised WSI classification (FSWC) crucial for learning from limited slide-level labels. Recently, pre-trained vision-language models (VLMs) have been adopted in FSWC, yet they exhibit several limitations. Existing prompt tuning methods in FSWC substantially increase both the number of trainable parameters and inference overhead. Moreover, current methods discard instances with low alignment to text embeddings from VLMs, potentially leading to information loss. To address these challenges, we propose two key contributions. First, we introduce a new parameter efficient prompt tuning method by scaling and shifting features in text encoder, which significantly reduces the computational cost. Second, to leverage not only the pre-trained knowledge of VLMs, but also the inherent hierarchical structure of WSIs, we introduce a WSI representation learning approach with a soft hierarchical textual guidance strategy without utilizing hard instance filtering. Comprehensive evaluations on pathology datasets covering breast, lung, and ovarian cancer types demonstrate consistent improvements up-to 10.9%, 7.8%, and 13.8% respectively, over the state-of-the-art methods in FSWC. Our method reduces the number of trainable parameters by 18.1% on both breast and lung cancer datasets, and 5.8% on the ovarian cancer dataset, while also excelling at weakly-supervised tumor localization. Code at https://github.com/Jayanie/HIPSS.

Nisal Ranasinghe, Yu Xia, Sachith Seneviratne et al.

Neural networks are powerful function approximators, yet their ``black-box" nature often renders them opaque and difficult to interpret. While many post-hoc explanation methods exist, they typically fail to capture the underlying reasoning processes of the networks. A truly interpretable neural network would be trained similarly to conventional models using techniques such as backpropagation, but additionally provide insights into the learned input-output relationships. In this work, we introduce the concept of interpretability pipelineing, to incorporate multiple interpretability techniques to outperform each individual technique. To this end, we first evaluate several architectures that promise such interpretability, with a particular focus on two recent models selected for their potential to incorporate interpretability into standard neural network architectures while still leveraging backpropagation: the Growing Interpretable Neural Network (GINN) and Kolmogorov Arnold Networks (KAN). We analyze the limitations and strengths of each and introduce a novel interpretable neural network GINN-KAN that synthesizes the advantages of both models. When tested on the Feynman symbolic regression benchmark datasets, GINN-KAN outperforms both GINN and KAN. To highlight the capabilities and the generalizability of this approach, we position GINN-KAN as an alternative to conventional black-box networks in Physics-Informed Neural Networks (PINNs). We expect this to have far-reaching implications in the application of deep learning pipelines in the natural sciences. Our experiments with this interpretable PINN on 15 different partial differential equations demonstrate that GINN-KAN augmented PINNs outperform PINNs with black-box networks in solving differential equations and surpass the capabilities of both GINN and KAN.

Zhaoyuan Qiu, Ken Chen, Xiangwei Wang et al.

Existing instruction-based image editing models perform well with simple, single-step instructions but degrade in realistic scenarios that involve multiple, lengthy, and interdependent directives. A main cause is the scarcity of training data with complex multi-instruction annotations. However, it is costly to collect such data and retrain these models. To address this challenge, we propose MSRAMIE, a training-free agent framework built on Multimodal Large Language Model (MLLM). MSRAMIE takes existing editing models as plug-in components and handle multi-instruction tasks via structured multimodal reasoning. It orchestrates iterative interactions between an MLLM-based Instructor and an image editing Actor, introducing a novel reasoning topology that comprises the proposed Tree-of-States and Graph-of-References. During inference, complex instructions are decomposed into multiple editing steps which enable state transitions, cross-step information aggregation, and original input recall, which enables systematic exploration of the image editing space and flexible progressive output refinement. The visualizable inference topology further provides interpretable and controllable decision pathways. Experiments show that as the instruction complexity increases, MSRAMIE can improve instruction following over 15% and increases the probability of finishing all modifications in a single run over 100%, while preserving perceptual quality and maintaining visual consistency.

Asela Hevapathige, Yu Xia, Sachith Seneviratne et al.

Theory-guided machine learning has demonstrated that including authentic domain knowledge directly into model design improves performance, sample efficiency and out-of-distribution generalisation. Yet the process by which a formal domain theory is translated into architectural constraints remains entirely manual, specific to each domain formalism, and devoid of any formal correctness guarantee. This translation is non-transferable between domains, not verified, and does not scale. We propose the Theory Compiler: a system that accepts a typed, machine-readable domain theory as input and automatically produces an architecture whose function space is provably constrained to be consistent with that theory by construction, not by regularisation. We identify three foundational open problems whose resolution defines our research agenda: (1) designing a universal theory formalisation language with decidable type-checking; (2) constructing a compositionally correct compilation algorithm from theory primitives to architectural modules; and (3) establishing soundness and completeness criteria for formal verification. We further conjecture that compiled architectures match or exceed manually-designed counterparts in generalisation performance while requiring substantially less training data, a claim we ground in classical statistical learning theory. We argue that recent advances in formal machine learning theory, large language models, and the growth of an interdisciplinary research community have made this paradigm achievable for the first time.

Rashindrie Perera, Saman Halgamuge

In this paper, we look at cross-domain few-shot classification which presents the challenging task of learning new classes in previously unseen domains with few labelled examples. Existing methods, though somewhat effective, encounter several limitations, which we alleviate through two significant improvements. First, we introduce a lightweight parameter-efficient adaptation strategy to address overfitting associated with fine-tuning a large number of parameters on small datasets. This strategy employs a linear transformation of pre-trained features, significantly reducing the trainable parameter count. Second, we replace the traditional nearest centroid classifier with a discriminative sample-aware loss function, enhancing the model's sensitivity to the inter- and intra-class variances within the training set for improved clustering in feature space. Empirical evaluations on the Meta-Dataset benchmark showcase that our approach not only improves accuracy up to 7.7\% and 5.3\% on previously seen and unseen datasets, respectively, but also achieves the above performance while being at least $\sim3\times$ more parameter-efficient than existing methods, establishing a new state-of-the-art in cross-domain few-shot learning. Our code is available at https://github.com/rashindrie/DIPA.

Asela Hevapathige, Ahad N. Zehmakan, Asiri Wijesinghe et al.

Graph Neural Networks (GNNs) face fundamental limitations in expressivity and capturing structural heterogeneity. Standard message-passing architectures are constrained by the 1-dimensional Weisfeiler-Leman (1-WL) test, unable to distinguish graphs beyond degree sequences, and aggregate information uniformly from neighbors, failing to capture how nodes occupy different structural positions within higher-order patterns. While methods exist to achieve higher expressivity, they incur prohibitive computational costs and lack unified frameworks for flexibly encoding diverse structural properties. To address these limitations, we introduce Invariant-Stratified Propagation (ISP), a framework comprising both a novel WL variant (ISP-WL) and its efficient neural network implementation (ISPGNN). ISP stratifies nodes according to graph invariants, processing them in hierarchical strata that reveal structural distinctions invisible to 1-WL. Through hierarchical structural heterogeneity encoding, ISP quantifies differences in nodes' structural positions within higher-order patterns, distinguishing interactions where participants occupy different roles from those with uniform participation. We provide formal theoretical analysis establishing enhanced expressivity beyond 1-WL, convergence guarantees, and inherent resistance to oversmoothing. Extensive experiments across graph classification, node classification, and influence estimation demonstrate consistent improvements over standard architectures and state-of-the-art expressive baselines.

Nadarasar Bahavan, Sachith Seneviratne, Saman Halgamuge

The widespread use of deep learning classifiers necessitates Open-set recognition (OSR), which enables the identification of input data not only from classes known during training but also from unknown classes that might be present in test data. Many existing OSR methods are computationally expensive due to the reliance on complex generative models or suffer from high training costs. We investigate OSR from a representation-learning perspective, specifically through spherical embeddings. We introduce SphOR, a computationally efficient representation learning method that models the feature space as a mixture of von Mises-Fisher distributions. This approach enables the use of semantically ambiguous samples during training, to improve the detection of samples from unknown classes. We further explore the relationship between OSR performance and key representation learning properties which influence how well features are structured in high-dimensional space. Extensive experiments on multiple OSR benchmarks demonstrate the effectiveness of our method, producing state-of-the-art results, with improvements up-to 6% that validate its performance. Code at https://github.com/nadarasarbahavan/SpHOR

Sanjay Saha, Rashindrie Perera, Sachith Seneviratne et al.

The recent renaissance in generative models, driven primarily by the advent of diffusion models and iterative improvement in GAN methods, has enabled many creative applications. However, each advancement is also accompanied by a rise in the potential for misuse. In the arena of the deepfake generation, this is a key societal issue. In particular, the ability to modify segments of videos using such generative techniques creates a new paradigm of deepfakes which are mostly real videos altered slightly to distort the truth. This paradigm has been under-explored by the current deepfake detection methods in the academic literature. In this paper, we present a deepfake detection method that can address this issue by performing deepfake prediction at the frame and video levels. To facilitate testing our method, we prepared a new benchmark dataset where videos have both real and fake frame sequences with very subtle transitions. We provide a benchmark on the proposed dataset with our detection method which utilizes the Vision Transformer based on Scaling and Shifting to learn spatial features, and a Timeseries Transformer to learn temporal features of the videos to help facilitate the interpretation of possible deepfakes. Extensive experiments on a variety of deepfake generation methods show excellent results by the proposed method on temporal segmentation and classical video-level predictions as well. In particular, the paradigm we address will form a powerful tool for the moderation of deepfakes, where human oversight can be better targeted to the parts of videos suspected of being deepfakes. All experiments can be reproduced at: github.com/rgb91/temporal-deepfake-segmentation.

Maneesha Perera, Julian De Hoog, Kasun Bandara et al.

Regional solar power forecasting, which involves predicting the total power generation from all rooftop photovoltaic systems in a region holds significant importance for various stakeholders in the energy sector. However, the vast amount of solar power generation and weather time series from geographically dispersed locations that need to be considered in the forecasting process makes accurate regional forecasting challenging. Therefore, previous work has limited the focus to either forecasting a single time series (i.e., aggregated time series) which is the addition of all solar generation time series in a region, disregarding the location-specific weather effects or forecasting solar generation time series of each PV site (i.e., individual time series) independently using location-specific weather data, resulting in a large number of forecasting models. In this work, we propose two deep-learning-based regional forecasting methods that can effectively leverage both types of time series (aggregated and individual) with weather data in a region. We propose two hierarchical temporal convolutional neural network architectures (HTCNN) and two strategies to adapt HTCNNs for regional solar power forecasting. At first, we explore generating a regional forecast using a single HTCNN. Next, we divide the region into multiple sub-regions based on weather information and train separate HTCNNs for each sub-region; the forecasts of each sub-region are then added to generate a regional forecast. The proposed work is evaluated using a large dataset collected over a year from 101 locations across Western Australia to provide a day ahead forecast. We compare our approaches with well-known alternative methods and show that the sub-region HTCNN requires fewer individual networks and achieves a forecast skill score of 40.2% reducing a statistically significant error by 6.5% compared to the best counterpart.

Nisal Ranasinghe, Damith Senanayake, Sachith Seneviratne et al.

Traditional machine learning is generally treated as a black-box optimization problem and does not typically produce interpretable functions that connect inputs and outputs. However, the ability to discover such interpretable functions is desirable. In this work, we propose GINN-LP, an interpretable neural network to discover the form and coefficients of the underlying equation of a dataset, when the equation is assumed to take the form of a multivariate Laurent Polynomial. This is facilitated by a new type of interpretable neural network block, named the "power-term approximator block", consisting of logarithmic and exponential activation functions. GINN-LP is end-to-end differentiable, making it possible to use backpropagation for training. We propose a neural network growth strategy that will enable finding the suitable number of terms in the Laurent polynomial that represents the data, along with sparsity regularization to promote the discovery of concise equations. To the best of our knowledge, this is the first model that can discover arbitrary multivariate Laurent polynomial terms without any prior information on the order. Our approach is first evaluated on a subset of data used in SRBench, a benchmark for symbolic regression. We first show that GINN-LP outperforms the state-of-the-art symbolic regression methods on datasets generated using 48 real-world equations in the form of multivariate Laurent polynomials. Next, we propose an ensemble method that combines our method with a high-performing symbolic regression method, enabling us to discover non-Laurent polynomial equations. We achieve state-of-the-art results in equation discovery, showing an absolute improvement of 7.1% over the best contender, by applying this ensemble method to 113 datasets within SRBench with known ground-truth equations.

Haihang Wu, Wei Wang, Tamasha Malepathirana et al.

Neural growth is the process of growing a small neural network to a large network and has been utilized to accelerate the training of deep neural networks. One crucial aspect of neural growth is determining the optimal growth timing. However, few studies investigate this systematically. Our study reveals that neural growth inherently exhibits a regularization effect, whose intensity is influenced by the chosen policy for growth timing. While this regularization effect may mitigate the overfitting risk of the model, it may lead to a notable accuracy drop when the model underfits. Yet, current approaches have not addressed this issue due to their lack of consideration of the regularization effect from neural growth. Motivated by these findings, we propose an under/over fitting risk-aware growth timing policy, which automatically adjusts the growth timing informed by the level of potential under/overfitting risks to address both risks. Comprehensive experiments conducted using CIFAR-10/100 and ImageNet datasets show that the proposed policy achieves accuracy improvements of up to 1.3% in models prone to underfitting while achieving similar accuracies in models suffering from overfitting compared to the existing methods.

Jayanie Bogahawatte, Sachith Seneviratne, Maneesha Perera et al.

Adapting Large Language Models (LLMs) that are extensively trained on abundant text data, and customizing the input prompt to enable time series forecasting has received considerable attention. While recent work has shown great potential for adapting the learned prior of LLMs, the formulation of the prompt to finetune LLMs remains challenging as prompt should be aligned with time series data. Additionally, current approaches do not effectively leverage word token embeddings which embody the rich representation space learned by LLMs. This emphasizes the need for a robust approach to formulate the prompt which utilizes the word token embeddings while effectively representing the characteristics of the time series. To address these challenges, we propose NNCL-TLLM: Nearest Neighbor Contrastive Learning for Time series forecasting via LLMs. First, we generate time series compatible text prototypes such that each text prototype represents both word token embeddings in its neighborhood and time series characteristics via end-to-end finetuning. Next, we draw inspiration from Nearest Neighbor Contrastive Learning to formulate the prompt while obtaining the top-$k$ nearest neighbor time series compatible text prototypes. We then fine-tune the layer normalization and positional embeddings of the LLM, keeping the other layers intact, reducing the trainable parameters and decreasing the computational cost. Our comprehensive experiments demonstrate that NNCL-TLLM outperforms in few-shot forecasting while achieving competitive or superior performance over the state-of-the-art methods in long-term and short-term forecasting tasks.

Maneesha Perera, Julian De Hoog, Kasun Bandara et al.

Accurate forecasts of distributed solar generation are necessary to reduce negative impacts resulting from the increased uptake of distributed solar photovoltaic (PV) systems. However, the high variability of solar generation over short time intervals (seconds to minutes) caused by cloud movement makes this forecasting task difficult. To address this, using cloud images, which capture the second-to-second changes in cloud cover affecting solar generation, has shown promise. Recently, deep neural networks with "attention" that focus on important regions of an image have been applied with success in many computer vision applications. However, their use for forecasting cloud movement has not yet been extensively explored. In this work, we propose an attention-based convolutional long short-term memory network to forecast cloud movement and apply an existing self-attention-based method previously proposed for video prediction to forecast cloud movement. We investigate and discuss the impact of cloud forecasts from attention-based methods towards forecasting distributed solar generation, compared to cloud forecasts from non-attention-based methods. We further provide insights into the different solar forecast performances that can be achieved for high and low altitude clouds. We find that for clouds at high altitudes, the cloud predictions obtained using attention-based methods result in solar forecast skill score improvements of 5.86% or more compared to non-attention-based methods.

Xiangwei Wang, Wei Wang, Ken Chen et al.

Reinforcement Learning (RL) serves as a potent paradigm for enhancing reasoning capabilities in Large Language Models (LLMs), yet standard outcome-based approaches often suffer from reward sparsity and inefficient credit assignment. In this paper, we propose a novel framework designed to provide continuous reward signals, which introduces a Step-wise Marginal Information Gain (MIG) mechanism that quantifies the intrinsic value of reasoning steps against a Monotonic Historical Watermark, effectively filtering out training noise. To ensure disentangled credit distribution, we implement a Decoupled Masking Strategy, applying process-oriented rewards specifically to the chain-of-thought (CoT) and outcome-oriented rewards to the full completion. Additionally, we incorporate a Dual-Gated SFT objective to stabilize training with high-quality structural and factual signals. Extensive experiments across textual and multi-modal benchmarks (e.g., MATH, Super-CLEVR) demonstrate that our approach consistently outperforms baselines such as GRPO in both sample efficiency and final accuracy. Furthermore, our model exhibits superior out-of-distribution robustness, demonstrating promising zero-shot transfer capabilities to unseen and challenging reasoning tasks.

Nisal Ranasinghe, Dzung Do-Ha, Simon Maksour et al.

Amyotrophic lateral sclerosis (ALS) is a fatal neurodegenerative disorder characterized by motor neuron degeneration, with alterations in neural excitability serving as key indicators. Recent advancements in induced pluripotent stem cell (iPSC) technology have enabled the generation of human iPSC-derived neuronal cultures, which, when combined with multi-electrode array (MEA) electrophysiology, provide rich spatial and temporal electrophysiological data. Traditionally, MEA data is analyzed using handcrafted features based on potentially imperfect domain knowledge, which while useful may not fully capture all useful characteristics inherent in the data. Machine learning, particularly deep learning, has the potential to automatically learn relevant characteristics from raw data without solely relying on handcrafted feature extraction. However, handcrafted features remain critical for encoding domain knowledge and improving interpretability, especially with limited or noisy data. This study introduces FRAME-C, a knowledge-augmented machine learning pipeline that combines domain knowledge, raw spike waveform data, and deep learning techniques to classify MEA signals and identify ALS-specific phenotypes. FRAME-C leverages deep learning to learn important features from spike waveforms while incorporating handcrafted features such as spike amplitude, inter-spike interval, and spike duration, preserving key spatial and temporal information. We validate FRAME-C on both simulated and real MEA data from human iPSC-derived neuronal cultures, demonstrating superior performance over existing classification methods. FRAME-C shows over 11% improvement on real data and up to 25% on simulated data. We also show FRAME-C can evaluate handcrafted feature importance, providing insights into ALS phenotypes.

Nisal Ranasinghe, Damith Senanayake, Saman Halgamuge

The ability to discover meaningful, accurate, and concise mathematical equations that describe datasets is valuable across various domains. Equations offer explicit relationships between variables, enabling deeper insights into underlying data patterns. Most existing equation discovery methods rely on genetic programming, which iteratively searches the equation space but is often slow and prone to overfitting. By representing equations as directed acyclic graphs, we leverage the use of graph neural networks to learn the underlying semantics of equations, and generate new, previously unseen equations. Although graph generative models have been shown to be successful in discovering new types of graphs in many fields, there application in discovering equations remains largely unexplored. In this work, we propose Graph-EQ, a deep graph generative model designed for efficient equation discovery. Graph-EQ uses a conditional variational autoencoder (CVAE) to learn a rich latent representation of the equation space by training it on a large corpus of equations in an unsupervised manner. Instead of directly searching the equation space, we employ Bayesian optimization to efficiently explore this learned latent space. We show that the encoder-decoder architecture of Graph-Eq is able to accurately reconstruct input equations. Moreover, we show that the learned latent representation can be sampled and decoded into valid equations, including new and previously unseen equations in the training data. Finally, we assess Graph-Eq's ability to discover equations that best fit a dataset by exploring the latent space using Bayesian optimization. Latent space exploration is done on 20 dataset with known ground-truth equations, and Graph-Eq is shown to successfully discover the grountruth equation in the majority of datasets.

Deshani Geethika Poddenige, Sachith Seneviratne, Damith Senanayake et al.

Unsupervised representation learning has been widely explored across various modalities, including neural architectures, where it plays a key role in downstream applications like Neural Architecture Search (NAS). These methods typically learn an unsupervised representation space before generating/ sampling architectures for the downstream search. A common approach involves the use of Variational Autoencoders (VAEs) to map discrete architectures onto a continuous representation space, however, sampling from these spaces often leads to a high percentage of invalid or duplicate neural architectures. This could be due to the unnatural mapping of inherently discrete architectural space onto a continuous space, which emphasizes the need for a robust discrete representation of these architectures. To address this, we introduce a Vector Quantized Variational Autoencoder (VQ-VAE) to learn a discrete latent space more naturally aligned with the discrete neural architectures. In contrast to VAEs, VQ-VAEs (i) map each architecture into a discrete code sequence and (ii) allow the prior to be learned by any generative model rather than assuming a normal distribution. We then represent these architecture latent codes as numerical sequences and train a text-to-text model leveraging a Large Language Model to learn and generate sequences representing architectures. We experiment our method with Inception/ ResNet-like cell-based search spaces, namely NAS-Bench-101 and NAS-Bench-201. Compared to VAE-based methods, our approach improves the generation of valid and unique architectures by over 80% on NASBench-101 and over 8% on NASBench-201. Finally, we demonstrate the applicability of our method in NAS employing a sequence-modeling-based NAS algorithm.

Nadarasar Bahavan, Sanjay Saha, Ken Chen et al.

Facial forgery methods such as deepfakes can be misused for identity manipulation and spreading misinformation. They have evolved alongside advancements in generative AI, leading to new and more sophisticated forgery techniques that diverge from existing 'known' methods. Conventional deepfake detection methods use the closedset paradigm, thus limiting their applicability to detecting forgeries created using methods that are not part of the training dataset. In this paper, we propose a shift from the closed-set paradigm for deepfake detection. In the open-set paradigm, models are designed not only to identify images created by known facial forgery methods but also to identify and flag those produced by previously unknown methods as 'unknown' and not as unforged/real/unmanipulated. In this paper, we propose an open-set deepfake classification algorithm based on supervised contrastive learning. The open-set paradigm used in our model allows it to function as a more robust tool capable of handling emerging and unseen deepfake techniques, enhancing reliability and confidence, and complementing forensic analysis. In open-set paradigm, we identify three groups including the "unknown group that is neither considered known deepfake nor real. We investigate deepfake open-set classification across three scenarios, classifying deepfakes from unknown methods not as real, distinguishing real images from deepfakes, and classifying deepfakes from known methods, using the FaceForensics++ dataset as a benchmark. Our method achieves state of the art results in the first two tasks and competitive results in the third task.

Haihang Wu, Wei Wang, Tamasha Malepathirana et al.

Pruning can be an effective method of compressing large pre-trained models for inference speed acceleration. Previous pruning approaches rely on access to the original training dataset for both pruning and subsequent fine-tuning. However, access to the training data can be limited due to concerns such as data privacy and commercial confidentiality. Furthermore, with covariate shift (disparities between test and training data distributions), pruning and finetuning with training datasets can hinder the generalization of the pruned model to test data. To address these issues, pruning and finetuning the model with test time samples becomes essential. However, test-time model pruning and fine-tuning incur additional computation costs and slow down the model's prediction speed, thus posing efficiency issues. Existing pruning methods are not efficient enough for test time model pruning setting, since finetuning the pruned model is needed to evaluate the importance of removable components. To address this, we propose two variables to approximate the fine-tuned accuracy. We then introduce an efficient pruning method that considers the approximated finetuned accuracy and potential inference latency saving. To enhance fine-tuning efficiency, we propose an efficient knowledge distillation method that only needs to generate pseudo labels for a small set of finetuning samples one time, thereby reducing the expensive pseudo-label generation cost. Experimental results demonstrate that our method achieves a comparable or superior tradeoff between test accuracy and inference latency, with a 32% relative reduction in pruning and finetuning time compared to the best existing method.

Ken Chen, Sachith Seneviratne, Wei Wang et al.

Animating stylized avatars with dynamic poses and expressions has attracted increasing attention for its broad range of applications. Previous research has made significant progress by training controllable generative models to synthesize animations based on reference characteristics, pose, and expression conditions. However, the mechanisms used in these methods to control pose and expression often inadvertently introduce unintended features from the target motion, while also causing a loss of expression-related details, particularly when applied to stylized animation. This paper proposes a new method based on Stable Diffusion, called AniFaceDiff, incorporating a new conditioning module for animating stylized avatars. First, we propose a refined spatial conditioning approach by Facial Alignment to prevent the inclusion of identity characteristics from the target motion. Then, we introduce an Expression Adapter that incorporates additional cross-attention layers to address the potential loss of expression-related information. Our approach effectively preserves pose and expression from the target video while maintaining input image consistency. Extensive experiments demonstrate that our method achieves state-of-the-art results, showcasing superior image quality, preservation of reference features, and expression accuracy, particularly for out-of-domain animation across diverse styles, highlighting its versatility and strong generalization capabilities. This work aims to enhance the quality of virtual stylized animation for positive applications. To promote responsible use in virtual environments, we contribute to the advancement of detection for generative content by evaluating state-of-the-art detectors, highlighting potential areas for improvement, and suggesting solutions.

Damith Senanayake, Wei Wang, Shalin H. Naik et al.

Non-parametric dimensionality reduction techniques, such as t-SNE and UMAP, are proficient in providing visualizations for datasets of fixed sizes. However, they cannot incrementally map and insert new data points into an already provided data visualization. We present Self-Organizing Nebulous Growths (SONG), a parametric nonlinear dimensionality reduction technique that supports incremental data visualization, i.e., incremental addition of new data while preserving the structure of the existing visualization. In addition, SONG is capable of handling new data increments, no matter whether they are similar or heterogeneous to the already observed data distribution. We test SONG on a variety of real and simulated datasets. The results show that SONG is superior to Parametric t-SNE, t-SNE and UMAP in incremental data visualization. Specifically, for heterogeneous increments, SONG improves over Parametric t-SNE by 14.98 % on the Fashion MNIST dataset and 49.73% on the MNIST dataset regarding the cluster quality measured by the Adjusted Mutual Information scores. On similar or homogeneous increments, the improvements are 8.36% and 42.26% respectively. Furthermore, even when the above datasets are presented all at once, SONG performs better or comparable to UMAP, and superior to t-SNE. We also demonstrate that the algorithmic foundations of SONG render it more tolerant to noise compared to UMAP and t-SNE, thus providing greater utility for data with high variance, high mixing of clusters, or noise.

Wei Wang, Yuan Sun, Saman Halgamuge

Generative adversarial nets (GANs) are widely used to learn the data sampling process and their performance may heavily depend on the loss functions, given a limited computational budget. This study revisits MMD-GAN that uses the maximum mean discrepancy (MMD) as the loss function for GAN and makes two contributions. First, we argue that the existing MMD loss function may discourage the learning of fine details in data as it attempts to contract the discriminator outputs of real data. To address this issue, we propose a repulsive loss function to actively learn the difference among the real data by simply rearranging the terms in MMD. Second, inspired by the hinge loss, we propose a bounded Gaussian kernel to stabilize the training of MMD-GAN with the repulsive loss function. The proposed methods are applied to the unsupervised image generation tasks on CIFAR-10, STL-10, CelebA, and LSUN bedroom datasets. Results show that the repulsive loss function significantly improves over the MMD loss at no additional computational cost and outperforms other representative loss functions. The proposed methods achieve an FID score of 16.21 on the CIFAR-10 dataset using a single DCGAN network and spectral normalization.