6.2k citations · 7.5k across the 13 of their papers we have counts for
15 papers
TAG: Boosting Text-VQA via Text-aware Visual Question-answer Generation
Jun Wang, Mingfei Gao, Yuqian Hu +5
Text-VQA aims at answering questions that require understanding the textual cues in an image. Despite the great progress of existing Text-VQA methods, their performance suffers fro…
Can domain adaptation make object recognition work for everyone?
Viraj Prabhu, Ramprasaath R. Selvaraju, Judy Hoffman +1
Despite the rapid progress in deep visual recognition, modern computer vision datasets significantly overrepresent the developed world and models trained on such datasets underperf…
CLIP-Lite: Information Efficient Visual Representation Learning with Language Supervision
Aman Shrivastava, Ramprasaath R. Selvaraju, Nikhil Naik +1
We propose CLIP-Lite, an information efficient method for visual representation learning by feature alignment with textual annotations. Compared to the previously proposed CLIP mod…
PreViTS: Contrastive Pretraining with Video Tracking Supervision
Brian Chen, Ramprasaath R. Selvaraju, Shih-Fu Chang +2
Videos are a rich source for self-supervised learning (SSL) of visual representations due to the presence of natural temporal transformations of objects. However, current methods t…
Align before Fuse: Vision and Language Representation Learning with Momentum Distillation
Junnan Li, Ramprasaath R. Selvaraju, Akhilesh Deepak Gotmare +3
Large-scale vision and language representation learning has shown promising improvements on various vision-language tasks. Most existing methods employ a transformer-based multimod…
CASTing Your Model: Learning to Localize Improves Self-Supervised Representations
Ramprasaath R. Selvaraju, Karan Desai, Justin Johnson +1
Recent advances in self-supervised learning (SSL) have largely closed the gap with supervised ImageNet pretraining. Despite their success these methods have been primarily applied…
SOrT-ing VQA Models : Contrastive Gradient Learning for Improved Consistency
Sameer Dharur, Purva Tendulkar, Dhruv Batra +2
Recent research in Visual Question Answering (VQA) has revealed state-of-the-art models to be inconsistent in their understanding of the world -- they answer seemingly difficult qu…
SQuINTing at VQA Models: Introspecting VQA Models with Sub-Questions
Ramprasaath R. Selvaraju, Purva Tendulkar, Devi Parikh +4
Existing VQA datasets contain questions with varying levels of complexity. While the majority of questions in these datasets require perception for recognizing existence, propertie…
Trick or TReAT: Thematic Reinforcement for Artistic Typography
Purva Tendulkar, Kalpesh Krishna, Ramprasaath R. Selvaraju +1
An approach to make text visually appealing and memorable is semantic reinforcement - the use of visual cues alluding to the context or theme in which the word is being used to rei…
Taking a HINT: Leveraging Explanations to Make Vision and Language Models More Grounded
Ramprasaath R. Selvaraju, Stefan Lee, Yilin Shen +5
Many vision and language models suffer from poor visual grounding - often falling back on easy-to-learn language priors rather than basing their decisions on visual concepts in the…
Choose Your Neuron: Incorporating Domain Knowledge through Neuron-Importance
Ramprasaath R. Selvaraju, Prithvijit Chattopadhyay, Mohamed Elhoseiny +4
Individual neurons in convolutional neural networks supervised for image-level classification tasks have been shown to implicitly learn semantically meaningful concepts ranging fro…
Grad-CAM: Why did you say that?
Ramprasaath R Selvaraju, Abhishek Das, Ramakrishna Vedantam +3
We propose a technique for making Convolutional Neural Network (CNN)-based models more transparent by visualizing input regions that are 'important' for predictions -- or visual ex…
Diverse Beam Search: Decoding Diverse Solutions from Neural Sequence Models
Ashwin K Vijayakumar, Michael Cogswell, Ramprasath R. Selvaraju +4
Neural sequence models are widely used to model time-series data. Equally ubiquitous is the usage of beam search (BS) as an approximate inference algorithm to decode output sequenc…
Grad-CAM: Visual Explanations from Deep Networks via Gradient-based Localization
Ramprasaath R. Selvaraju, Michael Cogswell, Abhishek Das +3
We propose a technique for producing "visual explanations" for decisions from a large class of CNN-based models, making them more transparent. Our approach - Gradient-weighted Clas…
Counting Everyday Objects in Everyday Scenes
Prithvijit Chattopadhyay, Ramakrishna Vedantam, Ramprasaath R. Selvaraju +2
We are interested in counting the number of instances of object classes in natural, everyday images. Previous counting approaches tackle the problem in restricted domains such as c…