Related papers: DASH: Visual Analytics for Debiasing Image Classif…
Synthetic data is emerging as a substitute for authentic data to solve ethical and legal challenges in handling authentic face data. The current models can create real-looking face images of people who do not exist. However, it is a known…
While semi-supervised learning (SSL) has received tremendous attentions in many machine learning tasks due to its successful use of unlabeled data, existing SSL algorithms use either all unlabeled examples or the unlabeled examples with a…
Aesthetic image analysis is the study and assessment of the aesthetic properties of images. Current computational approaches to aesthetic image analysis either provide accurate or interpretable results. To obtain both accuracy and…
Vision-Language Navigation requires the agent to follow natural language instructions to reach a specific target. The large discrepancy between seen and unseen environments makes it challenging for the agent to generalize well. Previous…
The need for large amounts of training and validation data is a huge concern in scaling AI algorithms for autonomous driving. Semantic Image Synthesis (SIS), or label-to-image translation, promises to address this issue by translating…
Published studies have suggested the bias of automated face-based gender classification algorithms across gender-race groups. Specifically, unequal accuracy rates were obtained for women and dark-skinned people. To mitigate the bias of…
Computer vision has flourished in recent years thanks to Deep Learning advancements, fast and scalable hardware solutions and large availability of structured image data. Convolutional Neural Networks trained on supervised tasks with…
Recent advances in AI-driven image generation have introduced new challenges for verifying the authenticity of digital evidence in forensic investigations. Modern generative models can produce visually consistent forgeries that evade…
We propose a visual analytics system to help a user analyze and steer zero-shot learning models. Zero-shot learning has emerged as a viable scenario for categorizing data that consists of no labeled examples, and thus a promising approach…
Throughout application domains, we now rely extensively on algorithmic systems to engage with ever-expanding datasets of information. Despite their benefits, these systems are often complex (comprising of many intricate tools, e.g.,…
State-of-the-art object detection models are frequently trained offline using available datasets, such as ImageNet: large and overly diverse data that are unbalanced and hard to cluster semantically. This kind of training drops the object…
Pretrained visual-language models have made significant advancements in multimodal tasks, including image-text retrieval. However, a major challenge in image-text matching lies in language bias, where models predominantly rely on language…
Building facial analysis systems that generalize to extreme variations in lighting and facial expressions is a challenging problem that can potentially be alleviated using natural-looking synthetic data. Towards that, we propose LEGAN, a…
Data augmentation (DA) enhances model generalization in computer vision but may introduce biases, impacting class accuracy unevenly. Our study extends this inquiry, examining DA's class-specific bias across various datasets, including those…
As a fundamental visual attribute, image complexity significantly influences both human perception and the performance of computer vision models. However, accurately assessing and quantifying image complexity remains a challenging task. (1)…
Scene graph generation is a sophisticated task because there is no specific recognition pattern (e.g., "looking at" and "near" have no conspicuous difference concerning vision, whereas "near" could occur between entities with different…
Zero-shot classification is a promising paradigm to solve an applicable problem when the training classes and test classes are disjoint. Achieving this usually needs experts to externalize their domain knowledge by manually specifying a…
Creating virtual humans with embodied, human-like perceptual and actuation constraints has the promise to provide an integrated simulation platform for many scientific and engineering applications. We present Dynamic and Autonomous…
A recent study has shown that large-scale visual datasets are very biased: they can be easily classified by modern neural networks. However, the concrete forms of bias among these datasets remain unclear. In this study, we propose a…
Adequate sampling space coverage is the keystone to effectively train trustworthy Machine Learning models. Unfortunately, real data do carry several inherent risks due to the many potential biases they exhibit when gathered without a proper…