1 code implementation • 4 Jan 2024 • Oindrila Saha, Grant van Horn, Subhransu Maji
By prompting LLMs in various ways, we generate descriptions that capture visual appearance, habitat, and geographic regions and pair them with existing attributes such as the taxonomic structure of the categories.
1 code implementation • 25 Sep 2023 • Oindrila Saha, Subhransu Maji
For example, under a linear-evaluation scheme, the classification accuracy of a ResNet50 trained on ImageNet using DetCon, a self-supervised learning approach, improves from 35. 4% to 42. 0% on the Caltech-UCSD Birds, from 35. 5% to 44. 1% on the FGVC Aircraft, and from 29. 7% to 37. 4% on the Stanford Cars.
no code implementations • 11 Apr 2022 • Oindrila Saha, Zezhou Cheng, Subhransu Maji
A significant bottleneck in training deep networks for part segmentation is the cost of obtaining detailed annotations.
no code implementations • CVPR 2022 • Oindrila Saha, Zezhou Cheng, Subhransu Maji
Motivated by this we present an alternative approach based on contrastive learning and compare their performance on standard few-shot part segmentation benchmarks.
no code implementations • 31 Aug 2020 • Sandeep Mishra, Oindrila Saha
This information when utilized in a biologically inspired fashion can contribute in better prediction performance without the use of models with huge number of parameters.
2 code implementations • NeurIPS 2020 • Oindrila Saha, Aditya Kusupati, Harsha Vardhan Simhadri, Manik Varma, Prateek Jain
Standard Convolutional Neural Networks (CNNs) designed for computer vision tasks tend to have large intermediate activation maps.
Ranked #27 on Face Detection on WIDER Face (Medium)
no code implementations • 7 Feb 2019 • Oindrila Saha, Rachana Sathish, Debdoot Sheet
This paper proposes a method for the automated segmentation of retinal lesions and optic disk in fundus images using a deep fully convolutional neural network for semantic segmentation.