Related papers: FairNVT: Improving Fairness via Noise Injection in…

Graph Neural Networks (GNNs) have demonstrated exceptional efficacy in relational learning tasks, including node classification and link prediction. However, their application raises significant fairness concerns, as GNNs can perpetuate and…

Vision Transformers have attracted a lot of attention recently since the successful implementation of Vision Transformer (ViT) on vision tasks. With vision Transformers, specifically the multi-head self-attention modules, networks can…

In this work we demonstrate the vulnerability of vision transformers (ViTs) to gradient-based inversion attacks. During this attack, the original data batch is reconstructed given model weights and the corresponding gradients. We introduce…

Large-scale fine-grained image retrieval (FGIR) aims to retrieve images belonging to the same subcategory as a given query by capturing subtle differences in a large-scale setting. Recently, Vision Transformers (ViT) have been employed in…

Language models are prone to dataset biases, known as shortcuts and spurious correlations in data, which often result in performance drop on new data. We present a new debiasing framework called ``FairFlow'' that mitigates dataset biases by…

Unsupervised representation learning of speech has been of keen interest in recent years, which is for example evident in the wide interest of the ZeroSpeech challenges. This work presents a new method for learning frame level…

This paper presents fairlib, an open-source framework for assessing and improving classification fairness. It provides a systematic framework for quickly reproducing existing baseline models, developing new methods, evaluating models with…

The approximation and convergence properties of implicit neural representations (INRs) are known to be highly sensitive to parameter initialization strategies. While several data-driven initialization methods demonstrate significant…

Variational Neural Machine Translation (VNMT) is an attractive framework for modeling the generation of target translations, conditioned not only on the source sentence but also on some latent random variables. The latent variable modeling…

The increasing availability of advanced image editing tools has led to a significant rise in manipulated digital content, posing serious challenges for digital forensics and information security. This study presents a transfer…

Normalizing Flows (NFs) learn invertible mappings between the data and a Gaussian distribution. Prior works usually suffer from two limitations. First, they add random noise to training samples or VAE latents as data augmentation,…

The growing capability and accessibility of machine learning has led to its application to many real-world domains and data about people. Despite the benefits algorithmic systems may bring, models can reflect, inject, or exacerbate implicit…

In recent years, the development of deep learning has been pushing image denoising to a new level. Among them, self-supervised denoising is increasingly popular because it does not require any prior knowledge. Most of the existing…

It is now well understood that machine learning models, trained on data without due care, often exhibit unfair and discriminatory behavior against certain populations. Traditional algorithmic fairness research has mainly focused on…

Despite the popularity of transformers in practice, their architectures are empirically designed and neither mathematically justified nor interpretable. Moreover, as indicated by many empirical studies, some components of transformer…

A novel Face Pyramid Vision Transformer (FPVT) is proposed to learn a discriminative multi-scale facial representations for face recognition and verification. In FPVT, Face Spatial Reduction Attention (FSRA) and Dimensionality Reduction…

Due to its deficiency in prior knowledge (inductive bias), Vision Transformer (ViT) requires pre-training on large-scale datasets to perform well. Moreover, the growing layers and parameters in ViT models impede their applicability to…

Existing visual change detectors usually adopt CNNs or Transformers for feature representation learning and focus on learning effective representation for the changed regions between images. Although good performance can be obtained by…

Neural machine translation (NMT) typically adopts the encoder-decoder framework. A good understanding of the characteristics and functionalities of the encoder and decoder can help to explain the pros and cons of the framework, and design…

Fairness-aware machine learning seeks to maximise utility in generating predictions while avoiding unfair discrimination based on sensitive attributes such as race, sex, religion, etc. An important line of work in this field is enforcing…