6 papers
Forgetting, plasticity, and co-observation: a third facet of continual learning
Timm Hess, Abhishek Jha, Gido M. van de Ven +1
Efficient continual learning remains a fundamental challenge for deep neural networks. While catastrophic forgetting and loss of plasticity are widely considered the primary obstac…
Self-Supervised Learning with a Multi-Task Latent Space Objective
Pierre-François De Plaen, Abhishek Jha, Luc Van Gool +2
We propose a multi-task formulation of self-predictive Siamese SSL in which each spatial transformation defines a distinct latent-space alignment task, solved by a dedicated predic…
Unsupervised Parameter Efficient Source-free Post-pretraining
Abhishek Jha, Tinne Tuytelaars, Yuki M. Asano
Following the success in NLP, the best vision models are now in the billion parameter ranges. Adapting these large models to a target distribution has become computationally and ec…
Analysis of Spatial augmentation in Self-supervised models in the purview of training and test distributions
Abhishek Jha, Tinne Tuytelaars
In this paper, we present an empirical study of typical spatial augmentation techniques used in self-supervised representation learning methods (both contrastive and non-contrastiv…
The Common Stability Mechanism behind most Self-Supervised Learning Approaches
Abhishek Jha, Matthew B. Blaschko, Yuki M. Asano +1
Last couple of years have witnessed a tremendous progress in self-supervised learning (SSL), the success of which can be attributed to the introduction of useful inductive biases i…
Barlow constrained optimization for Visual Question Answering
Abhishek Jha, Badri N. Patro, Luc Van Gool +1
Visual question answering is a vision-and-language multimodal task, that aims at predicting answers given samples from the question and image modalities. Most recent methods focus…