paper-with-me

홈 › Papers

Compositional Mixture Representations for Vision and Text

2022-06-13 · Stephan Alaniz, Marco Federici, Zeynep Akata

Learning a common representation space between vision and language allows deep networks to relate objects in the image to the corresponding semantic meaning. We present a model that learns a shared Gaussian mixture representation imposing the compositionality of the text onto the visual domain without having explicit location supervision. By combining the spatial transformer with a representation learning approach we learn to split images into separately encoded patches to associate visual and textual representations in an interpretable manner. On variations of MNIST and CIFAR10, our model is able to perform weakly supervised object detection and demonstrates its ability to extrapolate to unseen combination of objects.

📄 PDF Abstract BibTeX arXiv:2206.06404

Code (0)

등록된 구현이 없습니다.

Tasks

object-detectionObject DetectionRepresentation LearningWeakly Supervised Object Detection

Methods 이 논문이 사용한 방법론

Spatial Transformer A Spatial Transformer is an image model block that explicitly allows the spatial manipulation of data within a [convolutional neural…

Similar Papers 제목 키워드 기반

Illiterate DALL$\cdot$E Learns to Compose

2021-09-29 · ICLR 2022 4 · Gautam Singh, Fei Deng, Sungjin Ahn

DALL$\cdot$E has shown an impressive ability of composition-based systematic generalization in image generation. This is possible because it utilizes the dataset of text-image pairs where the text provides the source of …

DecoderImage GenerationSystematic Generalization

When and How Does CLIP Enable Domain and Compositional Generalization?

2025-02-13 · Elias Kempf, Simon Schrodi, Max Argus, Thomas Brox

The remarkable generalization performance of contrastive vision-language models like CLIP is often attributed to the diversity of their training distributions. However, key questions remain unanswered: Can CLIP generaliz…

DiversityDomain Generalization

Not Only Text: Exploring Compositionality of Visual Representations in Vision-Language Models

2025-03-21 · CVPR 2025 1 · Davide Berasi, Matteo Farina, Massimiliano Mancini, Elisa Ricci 외

Vision-Language Models (VLMs) learn a shared feature space for text and images, enabling the comparison of inputs of different modalities. While prior works demonstrated that VLMs organize natural language representation…

Aitchison Embeddings for Learning Compositional Graph Representations

2026-05-01 · Nikolaos Nakis, Chrysoula Kosma, Panagiotis Promponas, Michail Chatzianastasis 외 arxiv

Representation learning is central to graph machine learning, powering tasks such as link prediction and node classification. However, most graph embeddings are hard to interpret, offering limited insight into how learne…

Representation LearningNode ClassificationLink PredictionGraph Embedding

Preserving Multi-Modal Capabilities of Pre-trained VLMs for Improving Vision-Linguistic Compositionality

2024-10-07 · Youngtaek Oh, Jae Won Cho, Dong-Jin Kim, In So Kweon 외

In this paper, we propose a new method to enhance compositional understanding in pre-trained vision and language models (VLMs) without sacrificing performance in zero-shot multi-modal tasks. Traditional fine-tuning appro…