Concept Generalization in Visual Representation Learning

Measuring concept generalization, i.e., the extent to which models trained on a set of (seen) visual concepts can be used to recognize a new set of (unseen) concepts, is a popular way of evaluating visual representations, especially when they are learned with self-supervised learning. Nonetheless, the choice of which unseen concepts to use 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 semantic relationships between seen and unseen concepts affect generalization performance and propose ImageNet-CoG, a novel benchmark on the ImageNet 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 ImageNet concept sets that are semantically more and more distant from the ImageNet-1K subset, a ubiquitous training set. This allows us to benchmark visual representations learned on ImageNet-1K out-of-the box: we analyse a number of such models from supervised, semi-supervised and self-supervised approaches under the prism of concept generalization, and show how our benchmark is able to uncover a number of interesting insights. We will provide resources for the benchmark at


Measuring the Interpretability of Unsupervised Representations via Quantized Reverse Probing

Self-supervised visual representation learning has recently attracted si...

Self-Supervised Learning of Video-Induced Visual Invariances

We propose a general framework for self-supervised learning of transfera...

Simplicial Embeddings in Self-Supervised Learning and Downstream Classification

We introduce Simplicial Embeddings (SEMs) as a way to constrain the enco...

Measuring Visual Generalization in Continuous Control from Pixels

Self-supervised learning and data augmentation have significantly reduce...

Benchmarking Representation Learning for Natural World Image Collections

Recent progress in self-supervised learning has resulted in models that ...

Hierarchically Robust Representation Learning

With the tremendous success of deep learning in visual tasks, the repres...

Meta Compositional Referring Expression Segmentation

Referring expression segmentation aims to segment an object described by...

Please sign up or login with your details

Forgot password? Click here to reset