Related papers: Selective Aggregation of Attention Maps Improves D…

Diffusion-based Image Editing (DIE) is an emerging research hot-spot, which often applies a semantic mask to control the target area for diffusion-based editing. However, most existing solutions obtain these masks via manual operations or…

Diffusion transformer-based video generation models (DiTs) have recently attracted widespread attention for their excellent generation quality. However, their computational cost remains a major bottleneck-attention alone accounts for over…

Sparse attention methods exploit the inherent sparsity in attention to speed up the prefilling phase of long-context inference, mitigating the quadratic complexity of full attention computation. While existing sparse attention methods rely…

This paper presents an artistic and technical investigation into the attention mechanisms of video diffusion transformers. Inspired by early video artists who manipulated analog video signals to create new visual aesthetics, this study…

Over the past years, semantic segmentation, as many other tasks in computer vision, benefited from the progress in deep neural networks, resulting in significantly improved performance. However, deep architectures trained with…

Diffusion-based classifiers such as those relying on the Personalized PageRank and the Heat kernel, enjoy remarkable classification accuracy at modest computational requirements. Their performance however is affected by the extent to which…

Attention mechanisms, particularly channel attention, have become highly influential in numerous computer vision tasks. Despite their effectiveness, many existing methods primarily focus on optimizing performance through complex attention…

Mining precise class-aware attention maps, a.k.a, class activation maps, is essential for weakly supervised semantic segmentation. In this paper, we present L2G, a simple online local-to-global knowledge transfer framework for high-quality…

Deep Neural Network has shown great strides in the coarse-grained image classification task. It was in part due to its strong ability to extract discriminative feature representations from the images. However, the marginal visual difference…

Despite the rapid advancement of unsupervised learning in visual representation, it requires training on large-scale datasets that demand costly data collection, and pose additional challenges due to concerns regarding data privacy.…

We study the problem of generating abstractive summaries for opinionated text. We propose an attention-based neural network model that is able to absorb information from multiple text units to construct informative, concise, and fluent…

Explainable artificial intelligence (XAI) aims to make machine learning models more transparent. While many approaches focus on generating explanations post-hoc, interpretable approaches, which generate the explanations intrinsically…

Deep learning is widely applied in computer-aided pathological diagnosis, which alleviates the pathologist workload and provide timely clinical analysis. However, most models generally require large-scale annotated data for training, which…

Graph clustering is a fundamental task which discovers communities or groups in networks. Recent studies have mostly focused on developing deep learning approaches to learn a compact graph embedding, upon which classic clustering methods…

Contents generated by recent advanced Text-to-Image (T2I) diffusion models are sometimes too imaginative for existing off-the-shelf dense predictors to estimate due to the immitigable domain gap. We introduce DMP, a pipeline utilizing…

Pairwise dot product-based attention allows Transformers to exchange information between tokens in an input-dependent way, and is key to their success across diverse applications in language and vision. However, a typical Transformer model…

For automotive applications, the Graph Attention Network (GAT) is a prominently used architecture to include relational information of a traffic scenario during feature embedding. As shown in this work, however, one of the most popular GAT…

To resolve the semantic ambiguity in texts, we propose a model, which innovatively combines a knowledge graph with an improved attention mechanism. An existing knowledge base is utilized to enrich the text with relevant contextual concepts.…

Accurate medical image segmentation requires effective modeling of both long-range dependencies and fine-grained boundary details. While transformers mitigate the issue of insufficient semantic information arising from the limited receptive…

This paper investigates the role of attention heads in CLIP's image encoder. Building on interpretability studies, we conduct an exhaustive analysis and find that certain heads, distributed across layers, are detrimental to the resulting…