Search Results for author:
Found 6 papers, 5 papers with code
Bringing Back the Context: Camera Trap Species Identification as Link Prediction on Multimodal Knowledge Graphs
In this work, we leverage the structured context associated with the camera trap images to improve out-of-distribution generalization for the task of species identification in camera traps.
Learning Fractals by Gradient Descent
Fractals are geometric shapes that can display complex and self-similar patterns found in nature (e. g., clouds and plants).
Visual Query Tuning: Towards Effective Usage of Intermediate Representations for Parameter and Memory Efficient Transfer Learning
Through introducing a handful of learnable ``query'' tokens to each layer, VQT leverages the inner workings of Transformers to ``summarize'' rich intermediate features of each layer, which can then be used to train the prediction heads of downstream tasks.
On the Importance and Applicability of Pre-Training for Federated Learning
To make our findings applicable to situations where pre-trained models are not directly available, we explore pre-training with synthetic data or even with clients' data in a decentralized manner, and found that they can already improve FL notably.
EXTENDING CONDITIONAL CONVOLUTION STRUCTURES FOR ENHANCING MULTITASKING CONTINUAL LEARNING
Although CondConv is effective for the performance enhancement of a deep model, it is currently applied to individual tasks only.
Ranked #1 on
Continual Learning
on Flowers (Fine-grained 6 Tasks)
Compacting, Picking and Growing for Unforgetting Continual Learning
First, it can avoid forgetting (i. e., learn new tasks while remembering all previous tasks).
