306 citations · 347 across the 7 of their papers we have counts for
9 papers
Benchmarking Object Detectors with COCO: A New Path Forward
Shweta Singh, Aayan Yadav, Jitesh Jain +3
The Common Objects in Context (COCO) dataset has been instrumental in benchmarking object detectors over the past decade. Like every dataset, COCO contains subtle errors and imperf…
Hyperbolic Image-Text Representations
Karan Desai, Maximilian Nickel, Tanmay Rajpurohit +2
Visual and linguistic concepts naturally organize themselves in a hierarchy, where a textual concept "dog" entails all images that contain dogs. Despite being intuitive, current la…
Learning Visual Representations via Language-Guided Sampling
Mohamed El Banani, Karan Desai, Justin Johnson
Although an object may appear in numerous contexts, we often describe it in a limited number of ways. Language allows us to abstract away visual variation to represent and communic…
RedCaps: web-curated image-text data created by the people, for the people
Karan Desai, Gaurav Kaul, Zubin Aysola +1
Large datasets of paired images and text have become increasingly popular for learning generic representations for vision and vision-and-language tasks. Such datasets have been bui…
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…
VirTex: Learning Visual Representations from Textual Annotations
Karan Desai, Justin Johnson
The de-facto approach to many vision tasks is to start from pretrained visual representations, typically learned via supervised training on ImageNet. Recent methods have explored u…
Continual Reinforcement Learning in 3D Non-stationary Environments
Vincenzo Lomonaco, Karan Desai, Eugenio Culurciello +1
High-dimensional always-changing environments constitute a hard challenge for current reinforcement learning techniques. Artificial agents, nowadays, are often trained off-line in…
Probabilistic Neural-symbolic Models for Interpretable Visual Question Answering
Ramakrishna Vedantam, Karan Desai, Stefan Lee +3
We propose a new class of probabilistic neural-symbolic models, that have symbolic functional programs as a latent, stochastic variable. Instantiated in the context of visual quest…
nocaps: novel object captioning at scale
Harsh Agrawal, Karan Desai, Yufei Wang +7
Image captioning models have achieved impressive results on datasets containing limited visual concepts and large amounts of paired image-caption training data. However, if these m…