Search Results for author:
Found 5 papers, 4 papers with code
Humans Beat Deep Networks at Recognizing Objects in Unusual Poses, Given Enough Time
Deep learning is closing the gap with humans on several object recognition benchmarks.
Effective pruning of web-scale datasets based on complexity of concept clusters
Using a simple and intuitive complexity measure, we are able to reduce the training cost to a quarter of regular training.
Sieve: Multimodal Dataset Pruning Using Image Captioning Models
We propose a pruning signal, Sieve, that employs synthetic captions generated by image-captioning models pretrained on small, diverse, and well-aligned image-text pairs to evaluate the alignment of noisy image-text pairs.
SemDeDup: Data-efficient learning at web-scale through semantic deduplication
Analyzing a subset of LAION, we show that SemDeDup can remove 50% of the data with minimal performance loss, effectively halving training time.
Progress and limitations of deep networks to recognize objects in unusual poses
We show that classifying these images is still a challenge for all networks tested, with an average accuracy drop of 29. 5% compared to when the objects are presented upright.
