We present a series of two studies conducted to understand user’s affective states during voice-based human-machine interactions. Emphasis is placed on the cases of communication errors or failures.
Ajay Divakaran
SRI Author
Broadening AI Ethics Narratives: An Indic Arts View
In this paper, we investigate uncovering the unique socio-cultural perspectives embedded in human-made art, which in turn, can be valuable in expanding the horizon of AI ethics.
Generating and Evaluating Explanations of Attended and Error-Inducing Input Regions for VQA Models
Abstract Attention maps, a popular heatmap-based explanation method for Visual Question Answering (VQA), are supposed to help users understand the model by highlighting portions of the image/question used by the model to infer answers. However, we see that users are often misled by current attention map visualizations that point to relevant regions despite the model […]
Challenges in Procedural Multimodal Machine Comprehension: A Novel Way to Benchmark
We identify three critical biases stemming from the question-answer generation process and memorization capabilities of large deep models.
Ajay Divakaran
Senior Technical Director, Vision and Learning Laboratory, Center for Vision Technologies
Comprehension Based Question Answering Using Bloom’s Taxonomy
Abstract Current pre-trained language models have lots of knowledge, but a more limited ability to use that knowledge. Bloom’s Taxonomy helps educators teach children how to use knowledge by categorizing comprehension skills, so we use it to analyze and improve the comprehension skills of large pre-trained language models. Our experiments focus on zero-shot question answering, […]
Modular Adaptation for Cross-Domain Few-Shot Learning
Abstract Adapting pre-trained representations has become the go-to recipe for learning new downstream tasks with limited examples. While literature has demonstrated great successes via representation learning, in this work, we show that substantial performance improvement of downstream tasks can also be achieved by appropriate designs of the adaptation process. Specifically, we propose a modular adaptation […]
Confidence Calibration for Domain Generalization under Covariate Shift
Abstract Existing calibration algorithms address the problem of covariate shift via unsupervised domain adaptation. However, these methods suffer from the following limitations: 1) they require unlabeled data from the target domain, which may not be available at the stage of calibration in real-world applications and 2) their performance depends heavily on the disparity between the […]
Hybrid Consistency Training with Prototype Adaptation for Few-Shot Learning
Abstract Few-Shot Learning (FSL) aims to improve a model’s generalization capability in low data regimes. Recent FSL works have made steady progress via metric learning, meta learning, representation learning, etc. However, FSL remains challenging due to the following longstanding difficulties. 1) The seen and unseen classes are disjoint, resulting in a distribution shift between training […]
