Related papers: Comparing Optimization Targets for Contrast-Consis…
The mainstream researche in deep metric learning can be divided into two genres: proxy-based and pair-based methods. Proxy-based methods have attracted extensive attention due to the lower training complexity and fast network convergence.…
Depth completion involves estimating a dense depth image from sparse depth measurements, often guided by a color image. While linear upsampling is straight forward, it results in artifacts including depth pixels being interpolated in empty…
Deep anomaly detection methods learn representations that separate between normal and anomalous images. Although self-supervised representation learning is commonly used, small dataset sizes limit its effectiveness. It was previously shown…
Reliable detection of out-of-distribution (OOD) inputs is increasingly understood to be a precondition for deployment of machine learning systems. This paper proposes and investigates the use of contrastive training to boost OOD detection…
Radio interferometry has always faced the problem of incomplete sampling of the Fourier plane. A possible remedy can be found in the promising new theory of compressed sensing (CS), which allows for the accurate recovery of sparse signals…
Understanding how Multimodal Large Language Models (MLLMs) process low-level visual features is critical for evaluating their perceptual abilities and has not been systematically characterized. Inspired by human psychophysics, we introduce…
Learning to segment images purely by relying on the image-text alignment from web data can lead to sub-optimal performance due to noise in the data. The noise comes from the samples where the associated text does not correlate with the…
Given a dataset of finitely many elements $\mathcal{T} = \{\mathbf{x}_i\}_{i = 1}^N$, the goal of dataset condensation (DC) is to construct a synthetic dataset $\mathcal{S} = \{\tilde{\mathbf{x}}_j\}_{j = 1}^M$ which is significantly…
Miscalibration - a mismatch between a model's confidence and its correctness - of Deep Neural Networks (DNNs) makes their predictions hard to rely on. Ideally, we want networks to be accurate, calibrated and confident. We show that, as…
This paper studies the task of best counter-argument retrieval given an input argument. Following the definition that the best counter-argument addresses the same aspects as the input argument while having the opposite stance, we aim to…
We propose a novel deformation corrected compressed sensing (DC-CS) framework to recover dynamic magnetic resonance images from undersampled measurements. We introduce a generalized formulation that is capable of handling a wide class of…
Learning good representations involves capturing the diverse ways in which data samples relate. Contrastive loss - an objective matching related samples - underlies methods from self-supervised to multimodal learning. Contrastive losses,…
In recent years, Compressed Sensing (CS) has gained significant interest as a technique for acquiring high-resolution sensory data using fewer measurements than traditional Nyquist sampling requires. At the same time, autonomous robotic…
The effectiveness of contrastive learning technology in natural language processing tasks is yet to be explored and analyzed. How to construct positive and negative samples correctly and reasonably is the core challenge of contrastive…
The Information Contrastive (I-Con) framework revealed that over 23 representation learning methods implicitly minimize KL divergence between data and learned distributions that encode similarities between data points. However, a KL-based…
Packet loss concealment (PLC) is challenging in concealing missing contents both plausibly and naturally when there are only limited available context to use. Recently deep-learning based PLC algorithms have demonstrated their superiority…
In this paper, we propose an optimization-based method for robust phase retrieval problem where the goal is to estimate an unknown signal from a quadratic measurement corrupted by outliers. To enhance the robustness of existing optimization…
In recent years, the performance of face verification and recognition systems based on deep convolutional neural networks (DCNNs) has significantly improved. A typical pipeline for face verification includes training a deep network for…
Correntropy is a local similarity measure defined in kernel space and the maximum correntropy criterion (MCC) has been successfully applied in many areas of signal processing and machine learning in recent years. The kernel function in…
Existing losses used in deep metric learning (DML) for image retrieval often lead to highly non-uniform intra-class and inter-class representation structures across test classes and data distributions. When combined with the common practice…