Low-shot Object Learning with Mutual Exclusivity Bias
Not on the map. Why?
Abstract (arXiv)
This paper introduces Low-shot Object Learning with Mutual Exclusivity Bias (LSME), the first computational framing of mutual exclusivity bias, a phenomenon commonly observed in infants during word learning. We provide a novel dataset, comprehensive baselines, and a state-of-the-art method to enable the ML community to tackle this challenging learning task. The goal of LSME is to analyze an RGB image of a scene containing multiple objects and correctly associate a previously-unknown object instance with a provided category label. This association is then used to perform low-shot learning to test category generalization. We provide a data generation pipeline for the LSME problem and conduct a thorough analysis of the factors that contribute to its difficulty. Additionally, we evaluate the performance of multiple baselines, including state-of-the-art foundation models. Finally, we present a baseline approach that outperforms state-of-the-art models in terms of low-shot accuracy.
Key facts. Cited by 2 papers in the map (data through 13 Oct 2026). Builds on 40 of its 54 references that are in the map. First posted on arXiv 6 Dec 2023.
Builds on
40 of 54 references.
References · 40
- 2021Learning Transferable Visual Models From Natural Language Supervisioncited by 33,588
- 2021High-Resolution Image Synthesis with Latent Diffusion Modelscited by 18,777
- 2020A Simple Framework for Contrastive Learning of Visual Representationscited by 12,009
- 2023DINOv2: Learning Robust Visual Features without Supervisioncited by 7,857
- 2018Representation Learning with Contrastive Predictive Codingcited by 7,712
- 2019Momentum Contrast for Unsupervised Visual Representation Learningcited by 7,492
- 2021Masked Autoencoders Are Scalable Vision Learnerscited by 7,364
- 2021Emerging Properties in Self-Supervised Vision Transformerscited by 6,915
- 2022Photorealistic Text-to-Image Diffusion Models with Deep Language Understandingcited by 6,339
- 2015ShapeNet: An Information-Rich 3D Model Repositorycited by 2,889
- 2020Improved Baselines with Momentum Contrastive Learningcited by 2,285
- 2019Habitat: A Platform for Embodied AI Researchcited by 1,169
28 more
- 2023ImageBind: One Embedding Space To Bind Them Allcited by 1,168
- 2021SimMIM: A Simple Framework for Masked Image Modelingcited by 1,150
- 2020Object-Centric Learning with Slot Attentioncited by 869
- 2021Common Objects in 3D: Large-Scale Learning and Evaluation of Real-life 3D Category Reconstructioncited by 648
- 2020Dense Contrastive Learning for Self-Supervised Visual Pre-Trainingcited by 512
- 2022Kubric: A scalable dataset generatorcited by 375
- 2018ABC: A Big CAD Model Dataset For Geometric Deep Learningcited by 341
- 2021Towards Open World Object Detectioncited by 297
- 2018Few-Shot Learning via Embedding Adaptation with Set-to-Set Functionscited by 294
- 2020ThreeDWorld: A Platform for Interactive Multi-Modal Physical Simulationcited by 249
- 2014Towards Open World Recognitioncited by 226
- 2022Generalized Category Discoverycited by 209
- 2023Cut and Learn for Unsupervised Object Detection and Instance Segmentationcited by 187
- 2022CroCo: Self-Supervised Pre-training for 3D Vision Tasks by Cross-View Completioncited by 159
- 2020Unsupervised Learning of Dense Visual Representationscited by 147
- 2021Using Shape to Categorize: Low-Shot Learning with an Explicit Shape Biascited by 116
- 2022FreeSOLO: Learning to Segment Objects without Annotationscited by 102
- 2020Grounded Language Learning Fast and Slowcited by 54
- 2022Open-World Instance Segmentation: Exploiting Pseudo Ground Truth From Learned Pairwise Affinitycited by 41
- 2020OS2D: One-Stage One-Shot Object Detection by Matching Anchor Featurescited by 35
- 2023MEWL: Few-shot multimodal word learning with referential uncertaintycited by 17
- 2022Learning to Discover and Detect Objectscited by 11
- 2022Dense Siamese Network for Dense Unsupervised Learningcited by 8
- 2020Exploit Clues from Views: Self-Supervised and Regularized Learning for Multiview Object Recognitioncited by 6
- 2021Supervised Momentum Contrastive Learning for Few-Shot Classificationcited by 6
- 2022Learning Dense Object Descriptors from Multiple Views for Low-shot Category Generalizationcited by 6
- 2023LSFSL: Leveraging Shape Information in Few-shot Learningcited by 4
- 2023Self-supervised Learning by View Synthesiscited by 1
Built on by
Citing papers per year: 2024: 1; 2025: 1.
2 papers.