Papers Systematic Generalization
“Systematic Generalization” 태그가 달린 논문 126편 · 필터 해제
Not All Neuro-Symbolic Concepts Are Created Equal: Analysis and Mitigation of Reasoning Shortcuts
Neuro-Symbolic (NeSy) predictive models hold the promise of improved compliance with given constraints, systematic generalization, and interpretability, as they allow to infer labels that are consistent with some prior k…
AllSystematic GeneralizationCoarse-to-Fine Contrastive Learning in Image-Text-Graph Space for Improved Vision-Language Compositionality
Contrastively trained vision-language models have achieved remarkable progress in vision and language representation learning, leading to state-of-the-art models for various downstream multimodal tasks. However, recent r…
AttributeContrastive LearningImage RetrievalRelation+2SlotDiffusion: Object-Centric Generative Modeling with Diffusion Models
Object-centric learning aims to represent visual data with a set of object entities (a.k.a. slots), providing structured representations that enable systematic generalization. Leveraging advanced architectures like Trans…
Image GenerationObjectObject DiscoverySemantic Segmentation+3HICO-DET-SG and V-COCO-SG: New Data Splits for Evaluating the Systematic Generalization Performance of Human-Object Interaction Detection Models
Human-Object Interaction (HOI) detection is a task to localize humans and objects in an image and predict the interactions in human-object pairs. In real-world scenarios, HOI detection models need systematic generalizati…
Human-Object Interaction DetectionSystematic GeneralizationOn the Generalization of Learned Structured Representations
Despite tremendous progress over the past decade, deep learning methods generally fall short of human-level systematic generalization. It has been argued that explicitly capturing the underlying structure of data should …
Out-of-Distribution GeneralizationRepresentation LearningSystematic GeneralizationNeural Compositional Rule Learning for Knowledge Graph Reasoning
Learning logical rules is critical to improving reasoning in KGs. This is due to their ability to provide logical and interpretable explanations when used for predictions, as well as their ability to generalize to other …
Knowledge Graph CompletionSystematic GeneralizationWhat makes a language easy to deep-learn? Deep neural networks and humans similarly benefit from compositional structure
Deep neural networks drive the success of natural language processing. A fundamental property of language is its compositional structure, allowing humans to systematically produce forms for new meanings. For humans, lang…
Language ModelingLanguage ModellingLarge Language ModelMemorization+1An Investigation into Pre-Training Object-Centric Representations for Reinforcement Learning
Unsupervised object-centric representation (OCR) learning has recently drawn attention as a new paradigm of visual representation. This is because of its potential of being an effective pre-training technique for various…
ObjectOptical Character Recognition (OCR)Out-of-Distribution GeneralizationProperty Prediction+4Mutual Exclusivity Training and Primitive Augmentation to Induce Compositionality
Recent datasets expose the lack of the systematic generalization ability in standard sequence-to-sequence models. In this work, we analyze this behavior of seq2seq models and identify two contributing factors: a lack of …
Data AugmentationInductive BiasSystematic GeneralizationA Short Survey of Systematic Generalization
This survey includes systematic generalization and a history of how machine learning addresses it. We aim to summarize and organize the related information of both conventional and recent improvements. We first look at t…
SurveySystematic GeneralizationVisual Question Answering (VQA)Neural Systematic Binder
The key to high-level cognition is believed to be the ability to systematically manipulate and compose knowledge pieces. While token-like structured knowledge representations are naturally provided in text, it is elusive…
DisentanglementObjectScene GenerationSystematic GeneralizationAchieving and Understanding Out-of-Distribution Generalization in Systematic Reasoning in Small-Scale Transformers
Out-of-distribution generalization (OODG) is a longstanding challenge for neural networks. This challenge is quite apparent in tasks with well-defined variables and rules, where explicit use of the rules could solve prob…
Out-of-Distribution GeneralizationSystematic GeneralizationVIMA: General Robot Manipulation with Multimodal Prompts
Prompt-based learning has emerged as a successful paradigm in natural language processing, where a single general-purpose language model can be instructed to perform any task specified by input prompts. Yet task specific…
Imitation LearningLanguage ModellingRobot ManipulationSystematic Generalization+1Neural-Symbolic Recursive Machine for Systematic Generalization
Current learning models often struggle with human-like systematic generalization, particularly in learning compositional rules from limited data and extrapolating them to novel combinations. We introduce the Neural-Symbo…
Arithmetic ReasoningMachine TranslationSemantic ParsingSystematic GeneralizationEnhancing Interpretability and Interactivity in Robot Manipulation: A Neurosymbolic Approach
In this paper we present a neurosymbolic architecture for coupling language-guided visual reasoning with robot manipulation. A non-expert human user can prompt the robot using unconstrained natural language, providing a …
Referring ExpressionRobot ManipulationSystematic GeneralizationVisual Grounding+2Systematic Generalization and Emergent Structures in Transformers Trained on Structured Tasks
Transformer networks have seen great success in natural language processing and machine vision, where task objectives such as next word prediction and image classification benefit from nuanced context sensitivity across …
image-classificationImage ClassificationSystematic GeneralizationOn a Built-in Conflict between Deep Learning and Systematic Generalization
In this paper, we hypothesize that internal function sharing is one of the reasons to weaken o.o.d. or systematic generalization in deep learning for classification tasks. Under equivalent prediction, a model partitions …
Deep LearningSystematic GeneralizationMeta-Referential Games to Learn Compositional Learning Behaviours
Human beings use compositionality to generalise from past experiences to novel experiences. We assume a separation of our experiences into fundamental atomic components that can be recombined in novel ways to support our…
Meta-LearningSystematic GeneralizationSystematicity Emerges in Transformers when Abstract Grammatical Roles Guide Attention
Systematicity is thought to be a key inductive bias possessed by humans that is lacking in standard natural language processing systems such as those utilizing transformers. In this work, we investigate the extent to whi…
Inductive BiasSystematic GeneralizationEBMs vs. CL: Exploring Self-Supervised Visual Pretraining for Visual Question Answering
The availability of clean and diverse labeled data is a major roadblock for training models on complex tasks such as visual question answering (VQA). The extensive work on large vision-and-language models has shown that …
Contrastive LearningOut of Distribution (OOD) DetectionQuestion AnsweringSelf-Supervised Learning+3