-
CASTing Your Model: Learning to Localize Improves Self-Supervised Representations
Recent advances in self-supervised learning (SSL) have largely closed th...
12/08/2020 ∙ by Ramprasaath R. Selvaraju, et al. ∙
13
∙
share
read it
-
SOrT-ing VQA Models : Contrastive Gradient Learning for Improved Consistency
Recent research in Visual Question Answering (VQA) has revealed state-of...
10/20/2020 ∙ by Sameer Dharur, et al. ∙
9
∙
share
read it
-
SQuINTing at VQA Models: Interrogating VQA Models with Sub-Questions
Existing VQA datasets contain questions with varying levels of complexit...
01/20/2020 ∙ by Ramprasaath R. Selvaraju, et al. ∙
44
∙
share
read it
-
Trick or TReAT: Thematic Reinforcement for Artistic Typography
An approach to make text visually appealing and memorable is semantic re...
03/19/2019 ∙ by Purva Tendulkar, et al. ∙
23
∙
share
read it
-
Taking a HINT: Leveraging Explanations to Make Vision and Language Models More Grounded
Many vision and language models suffer from poor visual grounding - ofte...
02/11/2019 ∙ by Ramprasaath R. Selvaraju, et al. ∙
26
∙
share
read it
-
Choose Your Neuron: Incorporating Domain Knowledge through Neuron-Importance
Individual neurons in convolutional neural networks supervised for image...
08/08/2018 ∙ by Ramprasaath R. Selvaraju, et al. ∙
16
∙
share
read it
-
Grad-CAM: Why did you say that?
We propose a technique for making Convolutional Neural Network (CNN)-bas...
11/22/2016 ∙ by Ramprasaath R. Selvaraju, et al. ∙
0
∙
share
read it
-
Grad-CAM: Visual Explanations from Deep Networks via Gradient-based Localization
We propose a technique for producing "visual explanations" for decisions...
10/07/2016 ∙ by Ramprasaath R. Selvaraju, et al. ∙
0
∙
share
read it
-
Counting Everyday Objects in Everyday Scenes
We are interested in counting the number of instances of object classes ...
04/12/2016 ∙ by Prithvijit Chattopadhyay, et al. ∙
0
∙
share
read it
