Novel Concepts
51 papers with code • 0 benchmarks • 0 datasets
Measures the ability of models to uncover an underlying concept that unites several ostensibly disparate entities, which hopefully would not co-occur frequently. This provides a limited test of a model's ability to creatively construct the necessary abstraction to make sense of a situation that it cannot have memorized in training.
Source: BIG-bench
Benchmarks
These leaderboards are used to track progress in Novel Concepts
Most implemented papers
PaLM: Scaling Language Modeling with Pathways
lucidrains/CoCa-pytorch
•
•
Google Research 2022
To further our understanding of the impact of scale on few-shot learning, we trained a 540-billion parameter, densely activated, Transformer language model, which we call Pathways Language Model PaLM.
Dynamic Few-Shot Visual Learning without Forgetting
gidariss/FewShotWithoutForgetting
•
•
CVPR 2018
In this context, the goal of our work is to devise a few-shot visual learning system that during test time it will be able to efficiently learn novel categories from only a few training data while at the same time it will not forget the initial categories on which it was trained (here called base categories).
Revisit Systematic Generalization via Meaningful Learning
shininglab/systematic-generalization-via-meaningful-learning
•
•
Humans can systematically generalize to novel compositions of existing concepts.
DER: Dynamically Expandable Representation for Class Incremental Learning
Rhyssiyan/DER-ClassIL.pytorch
•
•
CVPR 2021
We address the problem of class incremental learning, which is a core step towards achieving adaptive vision intelligence.
Scaling Language Models: Methods, Analysis & Insights from Training Gopher
Language modelling provides a step towards intelligent communication systems by harnessing large repositories of written human knowledge to better predict and understand the world.
Training Compute-Optimal Large Language Models
We investigate the optimal model size and number of tokens for training a transformer language model under a given compute budget.
Is CLIP the main roadblock for fine-grained open-world perception?
Modern applications increasingly demand flexible computer vision models that adapt to novel concepts not encountered during training.
Learning like a Child: Fast Novel Visual Concept Learning from Sentence Descriptions of Images
In particular, we propose a transposed weight sharing scheme, which not only improves performance on image captioning, but also makes the model more suitable for the novel concept learning task.
Deep Compositional Captioning: Describing Novel Object Categories without Paired Training Data
Current deep caption models can only describe objects contained in paired image-sentence corpora, despite the fact that they are pre-trained with large object recognition datasets, namely ImageNet.
Zero-Shot Object Detection: Learning to Simultaneously Recognize and Localize Novel Concepts
We hypothesize that this setting is ill-suited for real-world applications where unseen objects appear only as a part of a complex scene, warranting both the `recognition' and `localization' of an unseen category.
