paper-with-me

홈 › Papers

Exploring the Effect of Primitives for Compositional Generalization in Vision-and-Language

2023-01-01 · CVPR 2023 1 · Chuanhao Li, Zhen Li, Chenchen Jing, Yunde Jia, Yuwei Wu

Compositionality is one of the fundamental properties of human cognition (Fodor & Pylyshyn, 1988). Compositional generalization is critical to simulate the compositional capability of humans, and has received much attention in the vision-and-language (V&L) community. It is essential to understand the effect of the primitives, including words, image regions, and video frames, to improve the compositional generalization capability. In this paper, we explore the effect of primitives for compositional generalization in V&L. Specifically, we present a self-supervised learning based framework that equips V&L methods with two characteristics: semantic equivariance and semantic invariance. With the two characteristics, the methods understand primitives by perceiving the effect of primitive changes on sample semantics and ground-truth. Experimental results on two tasks: temporal video grounding and visual question answering, demonstrate the effectiveness of our framework.

📄 PDF Abstract BibTeX

Code (1)

NeverMoreLCH/SSL2CG 공식 구현 pytorch

Tasks

Question AnsweringSelf-Supervised LearningVideo GroundingVisual Question Answering

Similar Papers 제목 키워드 기반

Exploring Compositionality in Vision Transformers using Wavelet Representations

2025-12-30 · Akshad Shyam Purushottamdas, Pranav K Nayak, Divya Mehul Rajparia, Deekshith Patel 외 arxiv

While insights into the workings of the transformer model have largely emerged by analysing their behaviour on language tasks, this work investigates the representations learnt by the Vision Transformer (ViT) encoder thr…

Representation Learning

Multi-Sourced Compositional Generalization in Visual Question Answering

2025-05-29 · Chuanhao Li, Wenbo Ye, Zhen Li, Yuwei Wu 외

Compositional generalization is the ability of generalizing novel compositions from seen primitives, and has received much attention in vision-and-language (V\&L) recently. Due to the multi-modal nature of V\&L tasks, th…

Question AnsweringVisual Question AnsweringVisual Question Answering (VQA)

Exploring Continual Learning of Compositional Generalization in NLI

2024-03-07 · Xiyan Fu, Anette Frank

Compositional Natural Language Inference has been explored to assess the true abilities of neural models to perform NLI. Yet, current evaluations assume models to have full access to all primitive inferences in advance, …

Continual LearningNatural Language Inference

Algorithmic Primitives and Compositional Geometry of Reasoning in Language Models

2025-10-13 · Samuel Lippl, Thomas McGee, Kimberly Lopez, Ziwen Pan 외 arxiv

How do latent and inference time computations enable large language models (LLMs) to solve multi-step reasoning? We introduce a framework for tracing and steering algorithmic primitives that underlie model reasoning. Our…

Measuring Compositionality in Representation Learning

2019-02-19 · ICLR 2019 5 · Jacob Andreas

Many machine learning algorithms represent input data with vector embeddings or discrete codes. When inputs exhibit compositional structure (e.g. objects built from parts or procedures from subroutines), it is natural to…

BIG-bench Machine LearningRepresentation Learning