Related papers: ReSi: A Comprehensive Benchmark for Representation…
Neural Radiance Field (NeRF) research has attracted significant attention recently, with 3D modelling, virtual/augmented reality, and visual effects driving its application. While current NeRF implementations can produce high quality visual…
Conditional density estimation is a general framework for solving various problems in machine learning. Among existing methods, non-parametric and/or kernel-based methods are often difficult to use on large datasets, while methods based on…
Finding best architectures of learning machines, such as deep neural networks, is a well-known technical and theoretical challenge. Recent work by Mellor et al (2021) showed that there may exist correlations between the accuracies of…
Representational similarity metrics typically force all units to be matched, making them susceptible to noise and outliers common in neural representations. We extend the soft-matching distance to a partial optimal transport setting that…
Despite the centrality of the notion of representation in neuroscience, the field lacks a unified framework for the concepts used to characterize representation, leading to disparate use of both terminology and measures associated with it.…
Conducting efficient performance estimations of neural architectures is a major challenge in neural architecture search (NAS). To reduce the architecture training costs in NAS, one-shot estimators (OSEs) amortize the architecture training…
Neuro-symbolic AI is an effective method for improving the overall performance of AI models by combining the advantages of neural networks and symbolic learning. However, there are differences between the two in terms of how they process…
Deep metric learning for vision is trained by optimizing a representation network to map (non-)matching image pairs to (non-)similar representations. During testing, which typically corresponds to image retrieval, both database and query…
Most existing neural architecture search (NAS) algorithms are dedicated to and evaluated by the downstream tasks, e.g., image classification in computer vision. However, extensive experiments have shown that, prominent neural architectures,…
Neural architecture search (NAS) aims to automatically design deep neural networks of satisfactory performance. Wherein, architecture performance predictor is critical to efficiently value an intermediate neural architecture. But for the…
The development of face recognition algorithms by academic and commercial organizations is growing rapidly due to the onset of deep learning and the widespread availability of training data. Though tests of face recognition algorithm…
This paper proposes integrating semantics-oriented similarity representation into RankingMatch, a recently proposed semi-supervised learning method. Our method, dubbed ReRankMatch, aims to deal with the case in which labeled and unlabeled…
Hand-crafted image quality metrics, such as PSNR and SSIM, are commonly used to evaluate model privacy risk under reconstruction attacks. Under these metrics, reconstructed images that are determined to resemble the original one generally…
Neural responses encode information that is useful for a variety of downstream tasks. A common approach to understand these systems is to build regression models or ``decoders'' that reconstruct features of the stimulus from neural…
Selecting an optimal set of icons is a crucial step in the pipeline of visual design to structure and navigate through content. However, designing the icons sets is usually a difficult task for which expert knowledge is required. In this…
Self-supervised learning has emerged as a powerful paradigm for label-free model pretraining, particularly in the video domain, where manual annotation is costly and time-intensive. However, existing self-supervised approaches employ…
Recent information retrieval (IR) models are pre-trained and instruction-tuned on massive datasets and tasks, enabling them to perform well on a wide range of tasks and potentially generalize to unseen tasks with instructions. However,…
This work investigates the problem of instance-level image retrieval re-ranking with the constraint of memory efficiency, ultimately aiming to limit memory usage to 1KB per image. Departing from the prevalent focus on performance…
A multitude of (dis)similarity measures between neural network representations have been proposed, resulting in a fragmented research landscape. Most of these measures fall into one of two categories. First, measures such as linear…
Magnetic Resonance Imaging (MRI) is a crucial imaging modality for viewing internal body structures. This research work analyses the performance of popular GAN models for accurate and precise MRI reconstruction by enhancing image quality…