Diffusion models are powerful generative models, and this capability can also be applied to discrimination. The inner activations of a pre-trained diffusion model can serve as features for discriminative tasks, namely...
ISBN:
(纸本)9798331314385
Diffusion models are powerful generative models, and this capability can also be applied to discrimination. The inner activations of a pre-trained diffusion model can serve as features for discriminative tasks, namely, diffusion feature. We discover that diffusion feature has been hindered by a hidden yet universal phenomenon that we call content shift. To be specific, there are content differences between features and the input image, such as the exact shape of a certain object. We locate the cause of content shift as one inherent characteristic of diffusion models, which suggests the broad existence of this phenomenon in diffusion feature. Further empirical study also indicates that its negative impact is not negligible even when content shift is not visually perceivable. Hence, we propose to suppress content shift to enhance the overall quality of diffusion features. Specifically, content shift is related to the information drift during the process of recovering an image from the noisy input, pointing out the possibility of turning off-the-shelf generation techniques into tools for content shift suppression. We further propose a practical guideline named GATE to efficiently evaluate the potential benefit of a technique and provide an implementation of our methodology. Despite the simplicity, the proposed approach has achieved superior results on various tasks and datasets, validating its potential as a generic booster for diffusion features. Our code is available at https://***/Darkbblue/diffusion-content-shift.
EEG emotion recognition is crucial in both human-machine interaction and healthcare. However, recognizing emotions across different subjects remains challenging due to individual variability. While existing multi-sour...
详细信息
For the hyperspectral image (HSI) denoising problem, a symmetric proximal alternating direction method multiplier (spADMM) is proposed to solve the sparse optimization problem which cannot be solved accurately by trad...
详细信息
Nine-degrees-of-freedom (9-DoF) object pose and size estimation is crucial for enabling augmented reality and robotic manipulation. Category-level methods have received extensive research attention due to their potent...
详细信息
Nine-degrees-of-freedom (9-DoF) object pose and size estimation is crucial for enabling augmented reality and robotic manipulation. Category-level methods have received extensive research attention due to their potential for generalization to intra-class unknown objects. However, these methods require manual collection and labeling of large-scale real-world training data. To address this problem, we introduce a diffusion-based paradigm for domain-generalized category-level 9-DoF object pose estimation. Our motivation is to leverage the latent generalization ability of the diffusion model to address the domain generalization challenge in object pose estimation. This entails training the model exclusively on rendered synthetic data to achieve generalization to real-world scenes. We propose an effective diffusion model to redefine 9-DoF object pose estimation from a generative perspective. Our model does not require any 3D shape priors during training or inference. By employing the Denoising Diffusion Implicit Model, we demonstrate that the reverse diffusion process can be executed in as few as 3 steps, achieving near real-time performance. Finally, we design a robotic grasping system comprising both hardware and software components. Through comprehensive experiments on two benchmark datasets and the real-world robotic system, we show that our method achieves state-of-the-art domain generalization performance.
The rapid evolution of the Internet of Underwater Things (IoUT) has led to the widespread adoption of autonomous underwater vehicle (AUV)-assisted underwater acoustic sensor networks (UASNs) for various applications s...
详细信息
As a powerful tool for studying molecular dynamics in bioscience,single-molecule fluorescence detection providesdynamical information buried in ensemble *** in the near-infrared(NIR)is particularly usefulbecause it of...
详细信息
As a powerful tool for studying molecular dynamics in bioscience,single-molecule fluorescence detection providesdynamical information buried in ensemble *** in the near-infrared(NIR)is particularly usefulbecause it offers higher signal-to-noise ratio and increased penetration depth in tissue compared with *** low quantum yield of most NIR fluorophores,however,makes the detection of single-moleculefluorescence ***,we use asymmetric plasmonic nano-antenna to enhance the fluorescence intensity ofAlEE1000,a typical NIR dye,by a factor up to *** asymmetric nano-antenna achieve such an enhancement mainlyby increasing the quantum yield(to~80%)rather than the local field,which degrades the molecules'*** coupled-mode-theory analysis reveals that the enhancements stem from resonance-matching between antennaand molecule and,more importantly,from optimizing the coupling between the near-and far-ield modes withdesigner asymmetric *** work provides a universal scheme for engineering single-molecule fluorescence inthe near-infrared regime.
Object detection tasks, crucial in safety-critical systems like autonomous driving, focus on pinpointing object locations. These detectors are known to be susceptible to backdoor attacks. However, existing backdoor te...
详细信息
Integrating prior knowledge of neurophysiology into neural network architecture enhances the performance of emotion decoding. While numerous techniques emphasize learning spatial and short-term temporal patterns, ther...
详细信息
Due to the high cost of Image Quality Assessment (IQA) datasets, achieving robust generalization remains challenging for prevalent deep learning-based IQA methods. To address this, this paper proposes a novel end-to-e...
Due to the high cost of Image Quality Assessment (IQA) datasets, achieving robust generalization remains challenging for prevalent deep learning-based IQA methods. To address this, this paper proposes a novel end-to-end blind IQA method: Causal-IQA. Specifically, we first analyze the causal mechanisms in IQA tasks and construct a causal graph to understand the interplay and confounding effects between distortion types, image contents, and subjective human ratings. Then, through shifting the focus from correlations to causality, Causal-IQA aims to improve the estimation accuracy of image quality scores by mitigating the confounding effects using a causality-based optimization strategy. This optimization strategy is implemented on the sample subsets constructed by a Counterfactual Division process based on the Backdoor Criterion. Extensive experiments illustrate the superiority of Causal-IQA.
暂无评论