Concept Generalization in Visual Representation Learning
By Mert Bulent Sariyildiz, Yannis Kalantidis, Diane Larlus, Alahari Karteek. 2020
54 citations recorded by the source corpus.
Measuring concept generalization, i.e., the extent to which models trained on a set of (seen) visual concepts can be leveraged to recognize a new set of (unseen) concepts, is a popular way of evaluating visual representations, especially in a self-supervised learning framework. Nonetheless, the choice of unseen concepts for such an evaluation is usually made arbitrarily, and independently from the seen concepts used to train representations, thus ignoring any semantic relationships between the two. In this paper, we argue that the semantic relationships between seen and unseen concepts affect generalization performance and propose ImageNet-CoG,1 a novel benchmark on the ImageNet-21K (IN-21K) dataset that enables measuring concept generalization in a principled way. Our benchmark leverages expert knowledge that comes from WordNet in order to define a sequence of unseen IN-21K concept sets that are semantically more and more distant from the ImageNet-1K (IN-1K) subset, a ubiquitous training set. This allows us to benchmark visual representations learned on IN-1K out-of-the box. We conduct a large-scale study encompassing 31 convolution and transformer-based models and show how different architectures, levels of supervision, regularization techniques and use of web data impact the concept generalization performance.
Subfields: Artificial Intelligence, Computer Vision and Pattern Recognition, Representation & Self-Supervised Learning
How researchers see this paper
The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.
In Artificial Intelligence
- Armand Joulin
- Ishan Misra
- Piotr Bojanowski
- Herv'e J'egou
- Mathilde Caron
- Hugo Touvron
- Julien Mairal
- Jianfeng Gao
In Computer Vision and Pattern Recognition
- Luc Van Gool
- Dacheng Tao
- Andrew Zisserman
- Andrea Vedaldi
- Trevor Darrell
- Cordelia Schmid
- Ming-Hsuan Yang
- Ishan Misra
In Representation & Self-Supervised Learning
- Ishan Misra
- Armand Joulin
- Piotr Bojanowski
- Mathilde Caron
- Herv'e J'egou
- Julien Mairal
- Hugo Touvron
- Yann LeCun
Citations in the corpus
- Emerging Properties in Self-Supervised Vision Transformers (2021, positive): “We observe that for ViT architectures, self-supervised pretraining transfers better than features trained with supervision, which is consistent with observations made on convolutional networks [9, 26, 51].”
- Discriminability-Transferability Trade-Off: An Information-Theoretic Perspective (2022, background): “The transferability of deep representations has been studied from various perspectives [23, 36, 11, 43, 52, 24, 3, 7].”