English
Related papers

Related papers: Attribute Diversity Determines the Systematicity G…

200 papers

Visual Question Answering (VQA) models often perform poorly on out-of-distribution data and struggle on domain generalization. Due to the multi-modal nature of this task, multiple factors of variation are intertwined, making generalization…

Computer Vision and Pattern Recognition · Computer Science 2023-06-02 Zhuowan Li , Xingrui Wang , Elias Stengel-Eskin , Adam Kortylewski , Wufei Ma , Benjamin Van Durme , Alan Yuille

The question of whether deep neural networks are good at generalising beyond their immediate training experience is of critical importance for learning-based approaches to AI. Here, we consider tests of out-of-sample generalisation that…

Artificial Intelligence · Computer Science 2020-02-20 Felix Hill , Andrew Lampinen , Rosalia Schneider , Stephen Clark , Matthew Botvinick , James L. McClelland , Adam Santoro

Deep ensembles perform better than a single network thanks to the diversity among their members. Recent approaches regularize predictions to increase diversity; however, they also drastically decrease individual members' performances. In…

Machine Learning · Computer Science 2021-01-15 Alexandre Rame , Matthieu Cord

Combining multiple perceptual inputs and performing combinatorial reasoning in complex scenarios is a sophisticated cognitive function in humans. With advancements in multi-modal large language models, recent benchmarks tend to evaluate…

Computer Vision and Pattern Recognition · Computer Science 2025-03-11 Chao Wang , Luning Zhang , Zheng Wang , Yang Zhou

Several studies have recently pointed that existing Visual Question Answering (VQA) models heavily suffer from the language prior problem, which refers to capturing superficial statistical correlations between the question type and the…

Computer Vision and Pattern Recognition · Computer Science 2022-07-26 Yudong Han , Liqiang Nie , Jianhua Yin , Jianlong Wu , Yan Yan

Visual question answering (VQA) systems are emerging from a desire to empower users to ask any natural language question about visual content and receive a valid answer in response. However, close examination of the VQA problem reveals an…

Artificial Intelligence · Computer Science 2016-08-30 Danna Gurari , Kristen Grauman

Curriculum learning techniques are a viable solution for improving the accuracy of automatic models, by replacing the traditional random training with an easy-to-hard strategy. However, the standard curriculum methodology does not…

Computer Vision and Pattern Recognition · Computer Science 2020-09-23 Petru Soviany

We consider concept generalization at a large scale in the diverse and natural visual spectrum. Established computational modes (i.e., rule-based or similarity-based) are primarily studied isolated and focus on confined and abstract problem…

Artificial Intelligence · Computer Science 2022-11-29 Yu-Zhe Shi , Manjie Xu , John E. Hopcroft , Kun He , Joshua B. Tenenbaum , Song-Chun Zhu , Ying Nian Wu , Wenjuan Han , Yixin Zhu

Currently, data and model size dominate the narrative in the training of super-large, powerful models. However, there has been a lack of exploration on the effect of other attributes of the training dataset on model performance. We…

Machine Learning · Computer Science 2025-01-22 Kavita Selva , Satita Vittayaareekul , Brando Miranda

We present a neuro-symbolic visual question answering (VQA) pipeline for CLEVR, which is a well-known dataset that consists of pictures showing scenes with objects and questions related to them. Our pipeline covers (i) training neural…

Artificial Intelligence · Computer Science 2022-05-17 Thomas Eiter , Nelson Higuera , Johannes Oetsch , Michael Pritz

The ability to estimate the perceptual error between images is an important problem in computer vision with many applications. Although it has been studied extensively, however, no method currently exists that can robustly predict visual…

Computer Vision and Pattern Recognition · Computer Science 2018-06-07 Ekta Prashnani , Hong Cai , Yasamin Mostofi , Pradeep Sen

The increasing capture and analysis of large-scale longitudinal health data offer opportunities to improve healthcare and advance medical understanding. However, a critical gap exists between (a) -- the observation of patterns and…

Human-Computer Interaction · Computer Science 2025-08-26 Arran Zeyu Wang , David Borland , David Gotz

Contrastive vision-language models (VLMs), like CLIP, have gained popularity for their versatile applicability to various downstream tasks. Despite their successes in some tasks, like zero-shot object recognition, they perform surprisingly…

Computer Vision and Pattern Recognition · Computer Science 2025-04-17 Simon Schrodi , David T. Hoffmann , Max Argus , Volker Fischer , Thomas Brox

Humans are highly efficient learners, with the ability to grasp the meaning of a new concept from just a few examples. Unlike popular computer vision systems, humans can flexibly leverage the compositional structure of the visual world,…

Computer Vision and Pattern Recognition · Computer Science 2021-05-21 Yanli Zhou , Brenden M. Lake

Inferring objects and their relationships from an image in the form of a scene graph is useful in many applications at the intersection of vision and language. We consider a challenging problem of compositional generalization that emerges…

Computer Vision and Pattern Recognition · Computer Science 2021-10-04 Boris Knyazev , Harm de Vries , Cătălina Cangea , Graham W. Taylor , Aaron Courville , Eugene Belilovsky

Datasets for training object recognition systems are steadily increasing in size. This paper investigates the question of whether existing detectors will continue to improve as data grows, or saturate in performance due to limited model…

Computer Vision and Pattern Recognition · Computer Science 2015-03-06 Xiangxin Zhu , Carl Vondrick , Charless Fowlkes , Deva Ramanan

We investigate 17 benchmarks (e.g. SugarCREPE, VALSE) commonly used for measuring compositional understanding capabilities of vision-language models (VLMs). We scrutinize design choices in their construction, including data source (e.g.…

Computer Vision and Pattern Recognition · Computer Science 2025-06-11 Vishaal Udandarao , Mehdi Cherti , Shyamgopal Karthik , Jenia Jitsev , Samuel Albanie , Matthias Bethge

The standard approach for neural topic modeling uses a variational autoencoder (VAE) framework that jointly minimizes the KL divergence between the estimated posterior and prior, in addition to the reconstruction loss. Since neural topic…

Computation and Language · Computer Science 2023-05-29 Raymond Li , Felipe González-Pizarro , Linzi Xing , Gabriel Murray , Giuseppe Carenini

Post-training is routinely evaluated through aggregate benchmark scores that treat multi-hop reasoning as a single capability -- as if a model that answers more questions correctly must be better at assembling facts. We show that this…

Artificial Intelligence · Computer Science 2026-05-27 Zhe Yu , Wenpeng Xing , Yunzhao Wei , Jie Chen , Hongzhi Wang , Xuyang Teng , Meng Han

While humans can solve a visual puzzle that requires logical reasoning by observing only few samples, it would require training over large amount of data for state-of-the-art deep reasoning models to obtain similar performance on the same…

Machine Learning · Computer Science 2020-07-24 Youngsung Kim , Jinwoo Shin , Eunho Yang , Sung Ju Hwang