English
Related papers

Related papers: From Patches to Objects: Exploiting Spatial Reason…

200 papers

It is known that representations from self-supervised pre-training can perform on par, and often better, on various downstream tasks than representations from fully-supervised pre-training. This has been shown in a host of settings such as…

Computer Vision and Pattern Recognition · Computer Science 2022-08-02 David Torpey , Richard Klein

Learning to perform abstract reasoning often requires decomposing the task in question into intermediate subgoals that are not specified upfront, but need to be autonomously devised by the learner. In Raven Progressive Matrices (RPM), the…

Artificial Intelligence · Computer Science 2024-03-08 Jakub Kwiatkowski , Krzysztof Krawiec

Self-supervised pretraining in remote sensing is mostly done using mid-spatial resolution (MR) image datasets due to their high availability. Given the release of high-resolution (HR) datasets, we ask how HR datasets can be included in…

Computer Vision and Pattern Recognition · Computer Science 2026-05-05 John Waithaka , Gustave Bwirayesu , Moise Busogi

When approaching the semantic segmentation of overhead imagery in the decimeter spatial resolution range, successful strategies usually combine powerful methods to learn the visual appearance of the semantic classes (e.g. convolutional…

Computer Vision and Pattern Recognition · Computer Science 2018-08-24 Michele Volpi , Devis Tuia

The need for a large amount of labeled data in the supervised setting has led recent studies to utilize self-supervised learning to pre-train deep neural networks using unlabeled data. Many self-supervised training strategies have been…

Computer Vision and Pattern Recognition · Computer Science 2022-04-06 Mojtaba Bahrami , Mahsa Ghorbani , Nassir Navab

Deep neural networks excel at comprehending complex visual signals, delivering on par or even superior performance to that of human experts. However, ad-hoc visual explanations of model decisions often reveal an alarming level of reliance…

Computer Vision and Pattern Recognition · Computer Science 2021-05-03 Dong Wang , Yuewei Yang , Chenyang Tao , Zhe Gan , Liqun Chen , Fanjie Kong , Ricardo Henao , Lawrence Carin

This paper addresses the problem of self-supervised video representation learning from a new perspective -- by video pace prediction. It stems from the observation that human visual system is sensitive to video pace, e.g., slow motion, a…

Computer Vision and Pattern Recognition · Computer Science 2020-09-07 Jiangliu Wang , Jianbo Jiao , Yun-Hui Liu

Despite the rapid advancement in the field of image recognition, the processing of high-resolution imagery remains a computational challenge. However, this processing is pivotal for extracting detailed object insights in areas ranging from…

Computer Vision and Pattern Recognition · Computer Science 2024-05-14 A V Subramanyam , Niyati Singal , Vinay K Verma

In training machine learning models for land cover semantic segmentation there is a stark contrast between the availability of satellite imagery to be used as inputs and ground truth data to enable supervised learning. While thousands of…

Computer Vision and Pattern Recognition · Computer Science 2022-03-14 Michail Tarasiou , Stefanos Zafeiriou

Representation learning approaches typically rely on images of objects captured from a single perspective that are transformed using affine transformations. Additionally, self-supervised learning, a successful paradigm of representation…

Computer Vision and Pattern Recognition · Computer Science 2022-08-17 Omiros Pantazis , Mathew Salvaris

Spatial reasoning remains a fundamental challenge for Vision-Language Models (VLMs), with current approaches struggling to achieve robust performance despite recent advances. We identify that this limitation stems from a critical gap:…

Computer Vision and Pattern Recognition · Computer Science 2025-10-10 Hongxing Li , Dingming Li , Zixuan Wang , Yuchen Yan , Hang Wu , Wenqi Zhang , Yongliang Shen , Weiming Lu , Jun Xiao , Yueting Zhuang

Understanding the spatial relations between objects in images is a surprisingly challenging task. A chair may be "behind" a person even if it appears to the left of the person in the image (depending on which way the person is facing). Two…

Computer Vision and Pattern Recognition · Computer Science 2019-09-02 Kaiyu Yang , Olga Russakovsky , Jia Deng

Latent representation learned from multi-layered neural networks via hierarchical feature abstraction enables recent success of deep learning. Under the deep learning framework, generalization performance highly depends on the learned…

Machine Learning · Computer Science 2016-11-07 Hyo-Eun Kim , Sangheum Hwang , Kyunghyun Cho

Multimodal deep learning utilizing imaging and diagnostic reports has made impressive progress in the field of medical imaging diagnostics, demonstrating a particularly strong capability for auxiliary diagnosis in cases where sufficient…

Computer Vision and Pattern Recognition · Computer Science 2024-08-21 Hao Yang , Hong-Yu Zhou , Cheng Li , Weijian Huang , Jiarun Liu , Yong Liang , Guangming Shi , Hairong Zheng , Qiegen Liu , Shanshan Wang

This study investigates the spatial reasoning capabilities of vision-language models (VLMs) through Chain-of-Thought (CoT) prompting and reinforcement learning. We begin by evaluating the impact of different prompting strategies and find…

Computer Vision and Pattern Recognition · Computer Science 2025-07-21 Binbin Ji , Siddharth Agrawal , Qiance Tang , Yvonne Wu

Recent work in vision-and-language pretraining has investigated supervised signals from object detection data to learn better, fine-grained multimodal representations. In this work, we take a step further and explore how we can tap into…

Computation and Language · Computer Science 2023-10-20 Emanuele Bugliarello , Aida Nematzadeh , Lisa Anne Hendricks

Vision and Language Pretraining has become the prevalent approach for tackling multimodal downstream tasks. The current trend is to move towards ever larger models and pretraining datasets. This computational headlong rush does not seem…

Computer Vision and Pattern Recognition · Computer Science 2022-10-06 Mustafa Shukor , Guillaume Couairon , Matthieu Cord

Zero-shot learning (ZSL) aims to recognize unseen image categories by learning an embedding space between image and semantic representations. For years, among existing works, it has been the center task to learn the proper mapping matrices…

Computer Vision and Pattern Recognition · Computer Science 2018-03-20 Yan Li , Junge Zhang , Jianguo Zhang , Kaiqi Huang

Recurrent feedback connections in the mammalian visual system have been hypothesized to play a role in synthesizing input in the theoretical framework of analysis by synthesis. The comparison of internally synthesized representation with…

Computer Vision and Pattern Recognition · Computer Science 2017-05-23 Hao Wang , Xingyu Lin , Yimeng Zhang , Tai Sing Lee

Although self-supervised learning enables us to bootstrap the training by exploiting unlabeled data, the generic self-supervised methods for natural images do not sufficiently incorporate the context. For medical images, a desirable method…

Image and Video Processing · Electrical Eng. & Systems 2022-07-08 Li Sun , Ke Yu , Kayhan Batmanghelich