Search Results for author:
Found 11 papers, 3 papers with code
Quality Estimation for Image Captions Based on Large-scale Human Evaluations
Automatic image captioning has improved significantly over the last few years, but the problem is far from being solved, with state of the art models still often producing low quality captions when used in the wild.
PACTran: PAC-Bayesian Metrics for Estimating the Transferability of Pretrained Models to Classification Tasks
With the increasing abundance of pretrained models in recent years, the problem of selecting the best pretrained checkpoint for a particular downstream classification task has been gaining increased attention.
Ranked #5 on
Transferability
on classification benchmark
CausalLM is not optimal for in-context learning
Recent empirical evidence indicates that transformer based in-context learning performs better when using a prefix language model (prefixLM), in which in-context samples can all attend to each other, compared to causal language models (causalLM), which use auto-regressive attention that prohibits in-context samples to attend to future samples.
Informative Image Captioning with External Sources of Information
An image caption should fluently present the essential information in a given image, including informative, fine-grained entity mentions and the manner in which these entities interact.
Reinforcing an Image Caption Generator Using Off-Line Human Feedback
Human ratings are currently the most accurate way to assess the quality of an image captioning model, yet most often the only used outcome of an expensive human rating evaluation is a few overall statistics over the evaluation dataset.
Improving Text Generation Evaluation with Batch Centering and Tempered Word Mover Distance
Recent advances in automatic evaluation metrics for text have shown that deep contextualized word representations, such as those generated by BERT encoders, are helpful for designing metrics that correlate well with human judgements.
Bridging the Gap Between Practice and PAC-Bayes Theory in Few-Shot Meta-Learning
Despite recent advances in its theoretical understanding, there still remains a significant gap in the ability of existing PAC-Bayesian theories on meta-learning to explain performance improvements in the few-shot learning setting, where the number of training examples in the target tasks is severely limited.
Improving Robust Generalization by Direct PAC-Bayesian Bound Minimization
Recent research in robust optimization has shown an overfitting-like phenomenon in which models trained against adversarial attacks exhibit higher robustness on the training set compared to the test set.
