However, this measure of performance conceals significant differences in how different classes and images are impacted by model compression techniques.
Neural network pruning techniques have demonstrated it is possible to remove the majority of weights in a network with surprisingly little degradation to top-1 test set accuracy.
Viral diseases are major sources of poor yields for cassava, the 2nd largest provider of carbohydrates in Africa. At least 80% of small-holder farmer households in Sub-Saharan Africa grow cassava.
This paper presents experiments extending the work of Ba et al. (2014) on recurrent neural models for attention into less constrained visual environments, specifically fine-grained categorization on the Stanford Dogs data set.
In other cases the semantic embedding space is established by an independent natural language processing task, and then the image transformation into that space is learned in a second stage.
Ranked #5 on Few-Shot Image Classification on ImageNet - 0-Shot
Modern visual recognition systems are often limited in their ability to scale to large numbers of object categories.
Ranked #3 on Zero-Shot Action Recognition on Kinetics