Related papers: Discovering Concept Directions from Diffusion-base…

Convolutional neural networks (CNNs) are increasingly being used in critical systems, where robustness and alignment are crucial. In this context, the field of explainable artificial intelligence has proposed the generation of high-level…

Clustering continues to be a significant and challenging task. Recent studies have demonstrated impressive results by applying clustering to feature representations acquired through self-supervised learning, particularly on small datasets.…

Melanoma is a fatal skin cancer that is curable and has dramatically increasing survival rate when diagnosed at early stages. Learning-based methods hold significant promise for the detection of melanoma from dermoscopic images. However,…

Diffusion Language Models (DLMs) offer a promising parallel generation paradigm but suffer from slow inference due to numerous refinement steps and the inability to use standard KV caching. We introduce CDLM (Consistency Diffusion Language…

Action recognition and detection in the context of long untrimmed video sequences has seen an increased attention from the research community. However, annotation of complex activities is usually time consuming and challenging in practice.…

Time-series clustering is a fundamental tool for pattern discovery, yet existing explainability methods, primarily based on feature attribution or metadata, fail to identify the transitions that move an instance across cluster boundaries.…

Generating multiple counterfactual explanations for different modes within a class presents a significant challenge, as these modes are distinct yet converge under the same classification. Diffusion probabilistic models (DPMs) have…

The multimodal deep neural networks, represented by CLIP, have generated rich downstream applications owing to their excellent performance, thus making understanding the decision-making process of CLIP an essential research topic. Due to…

Large language models (LLMs) have achieved significant progress in natural language processing but face challenges in deployment due to high memory and computational requirements. Weight quantization is a common approach to address these…

Metaphorical imagination, the ability to connect seemingly unrelated concepts, is fundamental to human cognition and communication. While understanding linguistic metaphors has advanced significantly, grasping multimodal metaphors, such as…

Machine learning models in dynamic environments often suffer from concept drift, where changes in the data distribution degrade performance. While detecting this drift is a well-studied topic, explaining how and why the model's…

Learning concepts that are consistent with human perception is important for Deep Neural Networks to win end-user trust. Post-hoc interpretation methods lack transparency in the feature representations learned by the models. This work…

Diffusion Language Models (DLMs) have recently achieved significant success due to their any-order generation capabilities. However, existing inference methods typically rely on local, immediate-step metrics such as confidence or entropy…

*Concept-based explanations* offer a promising approach for explaining the predictions of deep neural networks in terms of high-level, human-understandable concepts. However, existing methods either do not establish a causal connection…

Recent advances in image generation have made diffusion models powerful tools for creating high-quality images. However, their iterative denoising process makes understanding and interpreting their semantic latent spaces more challenging…

Latent features learned by deep learning approaches have proven to be a powerful tool for machine learning. They serve as a data abstraction that makes learning easier by capturing regularities in data explicitly. Their benefits motivated…

Image clustering is one of the crucial techniques in multimedia analytics and knowledge discovery. Recently, the Deep clustering method (DC), characterized by its ability to perform feature learning and cluster assignment jointly, surpasses…

Diffusion-based image translation guided by semantic texts or a single target image has enabled flexible style transfer which is not limited to the specific domains. Unfortunately, due to the stochastic nature of diffusion models, it is…

Image generation tasks are traditionally undertaken using Convolutional Neural Networks (CNN) or Transformer architectures for feature aggregating and dispatching. Despite the frequent application of convolution and attention structures,…

Despite their remarkable performance on a wide range of visual tasks, machine learning technologies often succumb to data distribution shifts. Consequently, a range of recent work explores techniques for detecting these shifts.…