Representation Learning by Learning to Count
We introduce a novel method for representation learning that uses an artificial supervision signal based on counting visual primitives. This supervision signal is obtained from an equivariance relation, which does not require any manual annotation. We relate transformations of images to transformations of the representations. More specifically, we look for the representation that satisfies such relation rather than the transformations that match a given representation. In this paper, we use two image transformations in the context of counting: scaling and tiling. The first transformation exploits the fact that the number of visual primitives should be invariant to scale. The second transformation allows us to equate the total number of visual primitives in each tile to that in the whole image. These two transformations are combined in one constraint and used to train a neural network with a contrastive loss. The proposed task produces representations that perform on par or exceed the state of the art in transfer learning benchmarks.
Code (2)
Tasks
RelationRepresentation LearningSelf-Supervised Image ClassificationTransfer LearningSimilar Papers 제목 키워드 기반
A Practical Method for Generating String Counterfactuals
Interventions targeting the representation space of language models (LMs) have emerged as an effective means to influence model behavior. Such methods are employed, for example, to eliminate or alter the encoding of demo…
counterfactualData AugmentationOn-Off Pattern Encoding and Path-Count Encoding as Deep Neural Network Representations
Understanding the encoded representation of Deep Neural Networks (DNNs) has been a fundamental yet challenging objective. In this work, we focus on two possible directions for analyzing representations of DNNs by studyin…
image-classificationImage ClassificationCounting Grid Aggregation for Event Retrieval and Recognition
Event retrieval and recognition in a large corpus of videos necessitates a holistic fixed-size visual representation at the video clip level that is comprehensive, compact, and yet discriminative. It shall comprehensivel…
RetrievalAtlasNLP: A Country-Aware Atlas of Dataset Representation in NLP
Understanding which countries are represented in NLP datasets is essential for identifying gaps, targeting data collection, measuring progress, and informing AI policy. However, geographic metadata is very rarely availab…
Counterfactual Basis Extension and Representational Geometry: An MDL-Constrained Model of Conceptual Growth
Concept learning becomes possible only when existing representations fail to account for experience. Most models of learning and inference, however, presuppose a fixed representational basis within which belief updating …