Related papers: An Empirical Study into Annotator Agreement, Groun…
Neural Machine Translation (NMT) models have shown remarkable performance but remain largely opaque in their decision making processes. The interpretability of these models, especially their internal attention mechanisms, is critical for…
In the context of text classification, the financial burden of annotation exercises for creating training data is a critical issue. Active learning techniques, particularly those rooted in uncertainty sampling, offer a cost-effective…
Human-annotated preference data play an important role in aligning large language models (LLMs). In this paper, we study two connected questions: how to monitor the quality of human preference annotators and how to incentivize them to…
Recent advances in data-centric artificial intelligence highlight inherent limitations in object recognition datasets. One of the primary issues stems from the semantic gap problem, which results in complex many-to-many mappings between…
This study adapts the Consensual Assessment Technique (CAT) for Large Language Models (LLMs), introducing a novel methodology for poetry evaluation. Using a 90-poem dataset with a ground truth based on publication venue, we demonstrate that…
Modern machine learning models for computer vision exceed humans in accuracy on specific visual recognition tasks, notably on datasets like ImageNet. However, high accuracy can be achieved in many ways. The particular decision function…
Pedestrian detection is among the most safety-critical features of driver assistance systems for autonomous vehicles. One of the most complex detection challenges is that of partial occlusion, where a target object is only partially…
This paper addresses the often overlooked issue of fairness in the autonomous driving domain, particularly in vision-based perception and prediction systems, which play a pivotal role in the overall functioning of Autonomous Vehicles (AVs).…
Recent large vision-language models (LVLMs) can generate vision-text multimodal chain-of-thought (MCoT) traces after reinforcement fine-tuning (RFT). However, we observe that the visual information incorporated in MCoT is often inaccurate,…
Large language models have demonstrated parallel and even superior translation performance compared to neural machine translation (NMT) systems. However, existing comparative studies between them mainly rely on automated metrics, raising…
GQA~\citep{hudson2019gqa} is a dataset for real-world visual reasoning and compositional question answering. We found that many answers predicted by the best vision-language models on the GQA dataset do not match the ground-truth answer but…
By computing the rank correlation between attention weights and feature-additive explanation methods, previous analyses either invalidate or support the role of attention-based explanations as a faithful and plausible measure of salience.…
Research into the detection of human activities from wearable sensors is a highly active field, benefiting numerous applications, from ambulatory monitoring of healthcare patients via fitness coaching to streamlining manual work processes.…
Confounding is a significant obstacle to unbiased estimation of causal effects from observational data. For settings with high-dimensional covariates -- such as text data, genomics, or the behavioral social sciences -- researchers have…
The evaluation of Handwritten Text Recognition (HTR) models during their development is straightforward: because HTR is a supervised problem, the usual data split into training, validation, and test data sets allows the evaluation of models…
We present a model that jointly learns the denotations of words together with their groundings using a truth-conditional semantics. Our model builds on the neurosymbolic approach of Mao et al. (2019), learning to ground objects in the CLEVR…
Vision Transformer(ViT) is one of the most widely used models in the computer vision field with its great performance on various tasks. In order to fully utilize the ViT-based architecture in various applications, proper visualization…
Visual Commonsense Reasoning (VCR) remains a significant yet challenging research problem in the realm of visual reasoning. A VCR model generally aims at answering a textual question regarding an image, followed by the rationale prediction…
Image captioning remains a fundamental task for vision language understanding, yet ground-truth supervision still relies predominantly on human-annotated references. Because human annotations reflect subjective preferences and expertise,…
Training image captioning models using teacher forcing results in very generic samples, whereas more distinctive captions can be very useful in retrieval applications or to produce alternative texts describing images for accessibility.…