Related papers: Mitigating Source and Detection Noises in Auto-cor…
Weak amplification is a signal enhancement technique which is used to measure tiny changes that otherwise cannot be determined because of technical limitations. It is based on the existence of a special type of interaction which couples a…
Weak-value amplification employs postselection to enhance the measurement of small parameters of interest. The amplification comes at the expense of reduced success probability, hindering the utility of this technique as a tool for…
Anomaly detection techniques are growing in importance at the Large Hadron Collider (LHC), motivated by the increasing need to search for new physics in a model-agnostic way. In this work, we provide a detailed comparative study between a…
The performance of deep neural networks scales with dataset size and label quality, rendering the efficient mitigation of low-quality data annotations crucial for building robust and cost-effective systems. Existing strategies to address…
We present a parameter estimation technique based on performing joint measurements of a weak interaction away from the weak-value-amplification approximation. Two detectors are used to collect full statistics of the correlations between two…
Absence of nearby light sources while capturing an image will degrade the visibility and quality of the captured image, making computer vision tasks difficult. In this paper, a color-wise attention network (CWAN) is proposed for low-light…
Separating audio mixtures into individual instrument tracks has been a long standing challenging task. We introduce a novel weakly supervised audio source separation approach based on deep adversarial learning. Specifically, our loss…
Standard weak measurement with an assistant pointer and single weak interaction constrains measurement precision and quantity of interaction parameters, and a compelling characterization of quantum effect featuring weak-value amplification…
We discuss the recently introduced concept of non-deterministic noiseless linear amplification, demonstrating that such an operation can only be performed perfectly with vanishing probability of success. We show that a weak measurement,…
Nearly thirty years ago the possibility of anomalous weak amplfication (AWA) was revealed by Aharonov, Albert and Vaidman [1]. Recently two papers presents two AWA schemes which are beyond the traditional proposal given by them [14, 15]. At…
A line of recent training-free methods for mitigating hallucinations in large vision-language models (LVLMs) operates by amplifying attention to visual tokens during autoregressive generation within a single forward pass. We refer to this…
Weak supervision (WS) is a rich set of techniques that produce pseudolabels by aggregating easily obtained but potentially noisy label estimates from a variety of sources. WS is theoretically well understood for binary classification, where…
Noise bias is a significant source of systematic error in weak gravitational lensing measurements that must be corrected to satisfy the stringent standards of modern imaging surveys in the era of precision cosmology. This paper reviews the…
We address the problem of weakly supervised object localization where only image-level annotations are available for training object detectors. Numerous methods have been proposed to tackle this problem through mining object proposals.…
The nonuniform and growing impact of adversarial noise across the layers of deep neural networks has been used in the literature, without a formal mathematical justification, to detect adversarial inputs and improve robustness. In this…
A universal amplification scheme of ultra-small phase based on weak measurements is given and a weak measurements amplification based laser interferometer gravitational-wave observatory (WMA-LIGO) is suggested. The WMA-LIGO has potential to…
Unsupervised representation learning seeks to recover latent generative factors, yet standard methods relying on statistical independence often fail to capture causal dependencies. A central challenge is identifiability: as established in…
Audio deepfake is so sophisticated that the lack of effective detection methods is fatal. While most detection systems primarily rely on low-level acoustic features or pretrained speech representations, they frequently neglect high-level…
Weakly supervised Audio-Visual Video Parsing (AVVP) aims to recognize and temporally localize audio, visual, and audio-visual events in videos using only coarse-grained labels. Faced with the challenging task settings, existing research…
Self-supervised speech models are a rapidly developing research topic in fake audio detection. Many pre-trained models can serve as feature extractors, learning richer and higher-level speech features. However,when fine-tuning pre-trained…