相关论文: Selective Aggregation of Attention Maps Improves D…

We propose the Multi-Head Density Adaptive Attention Mechanism (DAAM), a novel probabilistic attention framework that can be used for Parameter-Efficient Fine-tuning (PEFT), and the Density Adaptive Transformer (DAT), designed to enhance…

Attention--or attribution--maps methods are methods designed to highlight regions of the model's input that were discriminative for its predictions. However, different attention maps methods can highlight different regions of the input,…

Recent guidance methods in diffusion models steer reverse sampling by perturbing the model to construct an implicit weak model and guide generation away from it. Among these approaches, attention perturbation has demonstrated strong…

Recent studies have revealed that text-to-image diffusion models are vulnerable to backdoor attacks, where attackers implant stealthy textual triggers to manipulate model outputs. Previous backdoor detection methods primarily focus on the…

Providing interpretability of deep-learning models to non-experts, while fundamental for a responsible real-world usage, is challenging. Attribution maps from xAI techniques, such as Integrated Gradients, are a typical example of a…

The popularization of Text-to-Image (T2I) diffusion models enables the generation of high-quality images from text descriptions. However, generating diverse customized images with reference visual attributes remains challenging. This work…

Vision Transformers (ViTs) have become a dominant architecture in computer vision, yet their prediction process remains difficult to interpret because information is propagated through complex interactions across layers and attention heads.…

Large-scale text-to-image generative models have been a ground-breaking development in generative AI, with diffusion models showing their astounding ability to synthesize convincing images following an input text prompt. The goal of image…

While text-to-image models have achieved impressive capabilities in image generation and editing, their application across various modalities often necessitates training separate models. Inspired by existing method of single image editing…

Learning from a large corpus of data, pre-trained models have achieved impressive progress nowadays. As popular generative pre-training, diffusion models capture both low-level visual knowledge and high-level semantic relations. In this…

Multi-head attention has each of the attention heads collect salient information from different parts of an input sequence, making it a powerful mechanism for sequence modeling. Multilingual and multi-domain learning are common scenarios…

Multi-label classification has broad applications and depends on powerful representations capable of capturing multi-label interactions. We introduce \textit{Diff-Feat}, a simple but powerful framework that extracts intermediate features…

Recent studies emphasize the crucial role of data augmentation in enhancing the performance of object detection models. However,existing methodologies often struggle to effectively harmonize dataset diversity with semantic coordination.To…

Style-conditioned text-to-image (T2I) generation with diffusion models requires both stable character structure and consistent, fine-grained style expression across diverse prompts. Existing approaches either rely on text-only prompting,…

Recent developments in gradient-based attention modeling have seen attention maps emerge as a powerful tool for interpreting convolutional neural networks. Despite good localization for an individual class of interest, these techniques…

Diffusion models represent a new paradigm in text-to-image generation. Beyond generating high-quality images from text prompts, models such as Stable Diffusion have been successfully extended to the joint generation of semantic segmentation…

Gradient-based attention modeling has been used widely as a way to visualize and understand convolutional neural networks. However, exploiting these visual explanations during the training of generative adversarial networks (GANs) is an…

Vision Transformers (ViTs) have been shown to enhance visual recognition through modeling long-range dependencies with multi-head self-attention (MHSA), which is typically formulated as Query-Key-Value computation. However, the attention…

Recently, iteration-based stereo matching has shown great potential. However, these models optimize the disparity map using RNN variants. The discrete optimization process poses a challenge of information loss, which restricts the level of…

We introduce Attention Graphs, a new tool for mechanistic interpretability of Graph Neural Networks (GNNs) and Graph Transformers based on the mathematical equivalence between message passing in GNNs and the self-attention mechanism in…