中文
相关论文

相关论文: Structured learning and detailed interpretation of…

200 篇论文

This paper presents a novel yet intuitive approach to unsupervised feature learning. Inspired by the human visual system, we explore whether low-level motion-based grouping cues can be used to learn an effective visual representation.…

计算机视觉与模式识别 · 计算机科学 2017-04-13 Deepak Pathak , Ross Girshick , Piotr Dollár , Trevor Darrell , Bharath Hariharan

Interpretation of deep learning models is a very challenging problem because of their large number of parameters, complex connections between nodes, and unintelligible feature representations. Despite this, many view interpretability as a…

机器学习 · 计算机科学 2021-03-05 Michael Tsang , James Enouen , Yan Liu

Semantic Image Interpretation is the task of extracting a structured semantic description from images. This requires the detection of visual relationships: triples (subject,relation,object) describing a semantic relation between a subject…

机器学习 · 计算机科学 2019-10-02 Ivan Donadello , Luciano Serafini

Semantic object parsing is a fundamental task for understanding objects in detail in computer vision community, where incorporating multi-level contextual information is critical for achieving such fine-grained pixel-level recognition.…

计算机视觉与模式识别 · 计算机科学 2015-11-17 Xiaodan Liang , Xiaohui Shen , Donglai Xiang , Jiashi Feng , Liang Lin , Shuicheng Yan

Human-object interaction (HOI) detection is an important part of understanding human activities and visual scenes. The long-tailed distribution of labeled instances is a primary challenge in HOI detection, promoting research in few-shot and…

计算机视觉与模式识别 · 计算机科学 2023-08-14 Zikun Zhuang , Ruihao Qian , Chi Xie , Shuang Liang

Learning representations of spatial references in natural language is a key challenge in tasks like autonomous navigation and robotic manipulation. Recent work has investigated various neural architectures for learning multi-modal…

计算与语言 · 计算机科学 2020-10-08 Tsung-Yen Yang , Andrew S. Lan , Karthik Narasimhan

In this paper, we study the problem of generating structured objects that conform to a complex schema, with intricate dependencies between the different components (facets) of the object. The facets of the object (attributes, fields,…

软件工程 · 计算机科学 2024-12-02 Amir Tavanaei , Kee Kiat Koo , Hayreddin Ceker , Shaobai Jiang , Qi Li , Julien Han , Karim Bouyarmane

The neural mechanisms supporting flexible relational inferences, especially in novel situations, are a major focus of current research. In the complementary learning systems framework, pattern separation in the hippocampus allows rapid…

神经元与认知 · 定量生物学 2021-05-20 Jacob Russin , Maryam Zolfaghar , Seongmin A. Park , Erie Boorman , Randall C. O'Reilly

Vision-Language Models (VLMs) have demonstrated remarkable performance across a variety of real-world tasks. However, existing VLMs typically process visual information by serializing images, a method that diverges significantly from the…

计算机视觉与模式识别 · 计算机科学 2026-02-10 Yueyan Li , Chenggong Zhao , Zeyuan Zang , Caixia Yuan , Xiaojie Wang

Configural processing, the perception of spatial relationships among an object's components, is crucial for object recognition. However, the teleology and underlying neurocomputational mechanisms of such processing are still elusive,…

计算机视觉与模式识别 · 计算机科学 2024-07-30 Hojin Jang , Pawan Sinha , Xavier Boix

An evolving area of research in deep learning is the study of architectures and inductive biases that support the learning of relational feature representations. In this paper, we address the challenge of learning representations of…

机器学习 · 计算机科学 2024-09-30 Awni Altabaa , John Lafferty

Prototypical part neural networks (ProtoPartNNs), namely PROTOPNET and its derivatives, are an intrinsically interpretable approach to machine learning. Their prototype learning scheme enables intuitive explanations of the form, this…

计算机视觉与模式识别 · 计算机科学 2023-09-27 Zachariah Carmichael , Suhas Lohit , Anoop Cherian , Michael Jones , Walter Scheirer

Structured learning is appropriate when predicting structured outputs such as trees, graphs, or sequences. Most prior work requires the training set to consist of complete trees, graphs or sequences. Specifying such detailed ground truth…

机器学习 · 计算机科学 2012-07-03 Xinghua Lou , Fred Hamprecht

Transformer-based language models exhibit complex and distributed behavior, yet their internal computations remain poorly understood. Existing mechanistic interpretability methods typically treat attention heads and multilayer perceptron…

机器学习 · 计算机科学 2025-11-26 Areeb Ahmad , Abhinav Joshi , Ashutosh Modi

A cognitive model of human learning provides information about skills a learner must acquire to perform accurately in a task domain. Cognitive models of learning are not only of scientific interest, but are also valuable in adaptive online…

机器学习 · 计算机科学 2018-06-22 Devendra Singh Chaplot , Christopher MacLellan , Ruslan Salakhutdinov , Kenneth Koedinger

We present an approach to minimally supervised relation extraction that combines the benefits of learned representations and structured learning, and accurately predicts sentence-level relation mentions given only proposition-level…

计算与语言 · 计算机科学 2019-11-20 Fan Bai , Alan Ritter

The advancement of robots, particularly those functioning in complex human-centric environments, relies on control solutions that are driven by machine learning. Understanding how learning-based controllers make decisions is crucial since…

机器学习 · 计算机科学 2023-11-14 Tsun-Hsuan Wang , Wei Xiao , Tim Seyde , Ramin Hasani , Daniela Rus

This paper presents a novel deep learning architecture to classify structured objects in datasets with a large number of visually similar categories. We model sequences of images as linear-chain CRFs, and jointly learn the parameters from…

计算机视觉与模式识别 · 计算机科学 2019-11-19 Eran Goldman , Jacob Goldberger

Learning object-centric representations of complex scenes is a promising step towards enabling efficient abstract reasoning from low-level perceptual features. Yet, most deep learning approaches learn distributed representations that do not…

Large pre-trained language models achieve state-of-the-art results when fine-tuned on downstream NLP tasks. However, they almost exclusively focus on text-only representation, while neglecting cell-level layout information that is important…

计算与语言 · 计算机科学 2021-05-25 Chenliang Li , Bin Bi , Ming Yan , Wei Wang , Songfang Huang , Fei Huang , Luo Si