Search Results for author:
Found 9 papers, 2 papers with code
Towards Label-Efficient Incremental Learning: A Survey
The current dominant paradigm when building a machine learning model is to iterate over a dataset over and over until convergence.
Are Labels Needed for Incremental Instance Learning?
We propose VINIL, a self-incremental learner that can learn object instances sequentially, ii.
Human-Object Interaction Detection via Weak Supervision
iii) We evaluate Align-Former on HICO-DET [5] and V-COCO [13], and show that Align-Former outperforms existing image-level supervised HO-I detectors by a large margin (4. 71% mAP improvement from 16. 14% to 20. 85% on HICO-DET [5]).
Structured Visual Search via Composition-aware Learning
The structure is in the form of a 2D composition that encodes the position and the category of the objects.
Self-Selective Context for Interaction Recognition
Our experiments show that SSC leads to an important increase in interaction recognition performance, while using much fewer parameters.
Diagnosing Rarity in Human-Object Interaction Detection
To that end, in this paper, we propose to diagnose rarity in HOI detection.
Continual Learning of Object Instances
Our extensive experiments on three large-scale datasets, using two different architectures for five different continual learning methods, reveal that Normalised cross-entropy and synthetic transfer leads to less forgetting in existing techniques.
Re-evaluating Automatic Metrics for Image Captioning
The task of generating natural language descriptions from images has received a lot of attention in recent years.
