Search Results for author:
Found 10 papers, 5 papers with code
Consistency and Uncertainty: Identifying Unreliable Responses From Black-Box Vision-Language Models for Selective Visual Question Answering
We find that neighborhood consistency can be used to identify model responses to visual questions that are likely unreliable, even in adversarial settings or settings that are out-of-distribution to the proxy model.
Self-Training Large Language Models for Improved Visual Program Synthesis With Visual Reinforcement
We propose a method where we exploit existing annotations for a vision-language task to improvise a coarse reward signal for that task, treat the LLM as a policy, and apply reinforced self-training to improve the visual program synthesis ability of the LLM for that task.
Q: How to Specialize Large Vision-Language Models to Data-Scarce VQA Tasks? A: Self-Train on Unlabeled Images!
We introduce SelTDA (Self-Taught Data Augmentation), a strategy for finetuning large VLMs on small-scale VQA datasets.
Contrastive Alignment of Vision to Language Through Parameter-Efficient Transfer Learning
We find that a minimal set of parameter updates ($<$7%) can achieve the same performance as full-model training, and updating specific components ($<$1% of parameters) can match 75% of full-model training.
Single-Stream Multi-Level Alignment for Vision-Language Pretraining
Self-supervised vision-language pretraining from pure images and text with a contrastive loss is effective, but ignores fine-grained alignment due to a dual-stream architecture that aligns image and text representations only on a global level.
Where is the bottleneck in long-tailed classification?
A commonly held belief in deep-learning based long-tailed classification is that the representations learned from long-tailed data are ”good enough” and the performance bottleneck is the classification head atop the representation learner.
Exploiting BERT For Multimodal Target Sentiment Classification Through Input Space Translation
Our approach increases the amount of text available to the language model and distills the object-level information in complex images.
One Label, One Billion Faces: Usage and Consistency of Racial Categories in Computer Vision
Using the insight that a classifier can learn the racial system encoded by a dataset, we conduct an empirical study of computer vision datasets supplying categorical race labels for face images to determine the cross-dataset consistency and generalization of racial categories.
Families In Wild Multimedia: A Multimodal Database for Recognizing Kinship
Thus, to narrow the gap between research and reality and enhance the power of kinship recognition systems, we extend FIW with multimedia (MM) data (i. e., video, audio, and text captions).
Recognizing Families In the Wild: White Paper for the 4th Edition Data Challenge
Recognizing Families In the Wild (RFIW): an annual large-scale, multi-track automatic kinship recognition evaluation that supports various visual kin-based problems on scales much higher than ever before.
