We present a series of two studies conducted to understand user’s affective states during voice-based human-machine interactions.
Broadening AI Ethics Narratives: An Indic Arts View
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.
Model-Free Generative Replay For Lifelong Reinforcement Learning: Application To Starcraft-2
We evaluate our proposed algorithms on three different scenarios comprising tasks from the Starcraft 2 and Minigrid domains.
Generating and Evaluating Explanations of Attended and Error-Inducing Input Regions for VQA Models
Error maps can indicate when a correctly attended region may be processed incorrectly leading to an incorrect answer, and hence, improve users’ understanding of those cases.
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
Our experiments focus on zero-shot question answering, using the taxonomy to provide proximal context that helps the model answer questions by being relevant to those questions.
Modular Adaptation for Cross-Domain Few-Shot Learning
While literature has demonstrated great successes via representation learning, in this work, we show that improvement of downstream tasks can also be achieved by appropriate designs of the adaptation process.
Confidence Calibration for Domain Generalization under Covariate Shift
We present novel calibration solutions via domain generalization. Our core idea is to leverage multiple calibration domains to reduce the effective distribution disparity between the target and calibration domains for improved calibration transfer without needing any data from the target domain.