Ramprasaath R. Selvaraju
Visual Explanations from Deep Networks
SOrTing VQA Models: Improving Consistency via Gradient Alignment
Trick or Treat: Thematic Reinforcement for Artistic Typography
The Semantic Paintbrush: Interactive 3D Mapping and Recognition in Large Outdoor Spaces
Align before Fuse: Vision and Language Representation Learning with Momentum Distillation
Diverse Beam Search: Decoding Diverse Solutions from Neural Sequence Models
SQuINTing at VQA Models: Interrogating VQA Models with Sub-Questions
Taking a HINT: Leveraging Explanations to Make Vision and Language Models More Grounded
Choose Your Neuron: Incorporating Domain Knowledge into Deep Networks through Neuron Importance
Grad-CAM: Visual Explanations from Deep Networks via Gradient-based Localization
CASTing Your Model: Learning to Localize Improves Self-Supervised Representations
Counting Everyday Objects in Everyday Scenes
Choose Your Neuron: Incorporating Domain Knowledge into Deep Networks through Neuron Importance