Aditya Panda

I am currently a final year doctoral student at Indian Statistical Institute. During the last few years, I mainly worked on data efficient deep learning approaches. Specifically I explored the different aspects of the problem Compositional Zero-Shot Learning (CZSL). Compositional Zero-Shot Learning, focusses on recognizing new state-object compositions from limited training data. We worked on approaches using graph convolutional networks, and transformer networks to tackle challenges in the closed-world, open-world, and partially supervised CZSL problems. Before my PhD, I completed my M. Tech degree in Computer Science from ISI, Kolkata. Prior to that I pursued my undergraduate studies in Electronics and Tele-Communication Engineering from Jadavpur University, Kolkata.

Email  /  Google Scholar  /  CV  /  Semantic Scholar /  Orcid Id /  IEEE Author Profile

profile photo

Publication List

clean-usnob Knowledge Guided Transformer Network for Compositional Zero-shot Learning
Aditya Panda, Dipti Prasad Mukherjee
ACM Transactions on Multimedia Computing, Communications and Applications, 2024

In this work, we proposed a Knowledge-Guided Transformer Network to model the partial associations between visual features of state and object, to better tackle the intra-class variability in unseen state-objcet compositional images.


Link/ bibtex
clean-usnob Compositional Zero-Shot Learning using Multi-Branch Graph Convolution and Cross-layer Knowledge Sharing
Aditya Panda, Dipti Prasad Mukherjee
Pattern Recognition, 2024

In this work, we proposed Graph Convolutional Network based approach in attempt to solve the open-world CZSL problem..


Link/ bibtex
clean-usnob Isolating Features of Object and Its State for Compositional Zero-Shot
Aditya Panda, Bikash Santra, Dipti Prasad Mukherjee
IEEE Transactions on Emerging Topics in Computational Intelligence, 2023

In this work, we attempt to better tackle the intra-class variability in unseen state-objcet compositional images by using a Sequential Learning approach.


Link/ bibtex
clean-usnob Bi-Modal Compositional Network for Feature Disentanglement
Aditya Panda, Bikash Santra, Dipti Prasad Mukherjee
IEEE International Conference on Image Processing (ICIP), 2022

In this work, we attempt to disentangle the visual features of state and object in a state-objcet compositional images.


Link/ bibtex
clean-usnob Monocular 3D human pose estimation by multiple hypothesis prediction and joint angle supervision
Aditya Panda, Dipti Prasad Mukherjee
IEEE International Conference on Image Processing (ICIP), 2021
Link/ bibtex
Particle swarm optimization with a modified learning strategy and blending crossover
Aditya Panda, Rammohan Mallipeddi, Swagatam Das
IEEE Symposium Series on Computational Intelligence (SSCI), 2017
Link/ bibtex
Static learning particle swarm optimization with enhanced exploration and exploitation using adaptive swarm size
Aditya Panda, Srijan Ghoshal, Amit Konar, Bonny Banerjee, Atulya K Nagar
IEEE Congress on Evolutionary Computation (CEC), 2016
Link/ bibtex

Manuscripts Under Review

Prompt-Driven Network for Compositional Zero-Shot Learning
Aditya Panda, Dipti Prasad Mukherjee
Communicated to an IEEE Transaction
Partially Supervised Compositional Zero-Shot Learning by Locality Preserving Neighbourhood Aggregation
Aditya Panda, Dipti Prasad Mukherjee
Communicated to an IEEE Transaction

Academic Services


The source code for this website is used from here.