Akshita Guptaअक्षिता गुप्ता

I am a research engineer at Inception Institute of Artificial Intelligence. At IIAI, I work on research projects dealing with Object Detection, Generative Adversarial Networks and Zero-Shot Learning problems. I also work on industrial projects which try to solve Texture Classification, Object Detection and Object Counting problems.

I was fortunate to spend a semester during my undergraduate studies at Indian Institute of Technology Roorkee, where I was supervised by Dr. Balasubramanian Raman. Parrallel to my semester at IIT, I was selected as a outreachy intern, with Mozilla (2018), where I was supervised by Emma Irwin. I completed my B.Tech in Computer Science Engineering from DIT University.

Email  /  Google Scholar  /  Twitter  /  Github  /  CV

profile photo
What's New

[Sep 2021]    Serving as a reviewer CVPR 2022.
[Jul 2021]    One paper accepted at ICCV 2021.
[Feb 2021]    Serving as a reviewer ICCV 2021.
[Feb 2021]    Serving as a reviewer for ML Reproducibility Challenge 2020.
[Jan 2021]    Paper out on arxiv: Generative Multi-Label Zero-Shot Learning
[Jul  2020]    One paper accepted at ECCV’20.
[Aug 2019]    A Large-scale Instance Segmentation Dataset for Aerial Images (iSAID) is available for download.
[Aug 2018]   One paper accepted at Interspeech, chime workshop 2018.
[May 2018]   Selected as a Outreachy intern, with Mozilla.

Research

I'm interested in developing models which can learn with limited data and few, zero or one training sample(s). Much of my current research is about developing generative models for improving the feature synthesis space for unseen concepts.

Discriminative Region-based Multi-Label Zero-Shot Learning
Sanath Narayan*, Akshita Gupta*, Salman Khan, Fahad Shahbaz Khan,
Ling Shao, Mubarak Shah
(* denotes equal contribution) ICCV , 2021
paper (Coming Soon) / code
Generative Multi-Label Zero-Shot Learning
Akshita Gupta*, Sanath Narayan*, Salman Khan, Fahad Shahbaz Khan,
Ling Shao, Joost van de Weijer
(* denotes equal contribution) arxiv (Under Submission TPAMI) , 2021
paper / code
  • Description: Developed a generative model that constructs multi-label features for (generalized) zero-shot learning.
  • Outcome: Improved state-of-the-art performances on NUS-WIDE, OpenImages and MS-COCO by 3.3%, 4.3% and 15.7% mAP score.
Latent Embedding Feedback and Discriminative Features for Zero-Shot Classification
Sanath Narayan*, Akshita Gupta*, Fahad Shahbaz Khan, Cees G. M. Snoek, Ling Shao
(* denotes equal contribution) ECCV, 2020
paper / code
  • Description: Developed a generative feature synthesizing framework for zero-shot learning.
  • Outcome: Improved state-of-the-art performances on CUB, FLO, SUN, and AWA by 4.6%, 7.1%, 1.7%, and 3.1% harmonic mean by enforcing semantic consistency at all stages of zero-shot learning.
iSAID: A Large-scale Dataset for Instance Segmentation in Aerial Images
Syed Waqas Zamir, Aditya Arora, Akshita Gupta, Salman Khan, Guolei Sun, Fahad Shahbaz Khan, Fan Zhu, Ling Shao, Gui-Song Xia, Xiang Bai
CVPR Workshop, 2019 (Oral Presentation)
code / dataset
  • Description: Improved state of the art object detector (Mask-RCNN and PANet) for aerial imagery.
  • Outcome: Proposed a large scale instance segmentation and object detection dataset (iSAID) with benchmarking on mask-RCNN and PANet.
Acoustic features fusion using attentive multi-channel deep architecture
Gaurav Bhatt, Akshita Gupta, Aditya Arora, Balasubramanian Raman
Interspeech Workshop, 2018
code
  • Description: Developed an attention based framework for acoustic scene recognition and audio tagging.
  • Outcome: Improved the equal error rate by atleast 3% over the Dcase challenge results.
Research Experience
Research Engineer, Inception Institute of Artificial Intelligence
Dec 2018 - present
Supervisors: Dr Sanath Narayan, Dr Fahad Shahbaz khan

  • I worked on classification problem with its application as a rock & texture classification which achieved a state of the art results on a new handcrafted collected data.
  • I worked on object detection and object counting problem with its application in aerial imagery for detection aerial objects and counting cars in the parking lot.
  • Build instance segmentation and object detection models for aerial and satellite imagery. Explored and combined different deep learning models like PAnet and mask-RCNN. Published at CVPR-W Oral 2019.
  • Currently, working on generative models for improving the recognition of unseen concepts in few and zero shot domains with multi and single label datasets.

Research & Development Intern, Mozilla, Outreachy
May 2018 – Aug 2018
Supervisor: Emma Irwin

Developed an open source analytics dashboard prototype with the metrics to evaluate diversity and inclusion across different communities.

Undergraduate Researcher, Indian Institute of Technology
May 2018 – Dec 18
Supervisor: Dr R Balasubramanian

Worked on acoustic scene recognition and audio tagging using attention networks. Paper accepted in Interspeech-W 2018.

Research Intern, Indian Institute of Technology
May 2017 – Jul 2017
Supervisor: Dr R Balasubramanian

Worked on Basic Machine Learning techniques such as Support Vector Machines, K-Means Clustering and K-Nearest Neighbors and used these as a baseline for Acoustic Scene Classification. Setting up code environments, implemented models which were use for problems of Detection and Classification of Acoustic Scenes and Events. Worked on Audio Processing related challenges to minimise Equal Error rate.


I borrowed this website layout from here!