Departments
- Autonomous Motion
- Empirical Inference
- Haptic Intelligence
- Modern Magnetic Systems
- Perceiving Systems
- Physical Intelligence
- Robotic Materials
- Social Foundations of Computation
- Theory of Inhomogeneous Condensed Matter
Research Groups
- Autonomous Vision
- Autonomous Learning
- Bioinspired Autonomous Miniature Robots
- Biomimetic Materials and Machines
- Dynamic Locomotion
- Embodied Vision
- Human Aspects of Machine Learning
- Intelligent Control Systems
- Learning and Dynamical Systems
- Locomotion in Biorobotic and Somatic Systems
- Micro, Nano, and Molecular Systems
- Movement Generation and Control
- Neural Capture and Synthesis
- Organizational Leadership and Diversity
- Physics for Inference and Optimization
- Probabilistic Learning Group
- Probabilistic Numerics
- Rationality Enhancement
- Robust Machine Learning
- Nanorobotic Biosensors
- Smart Nanoplasmonics
1 result
(View BibTeX file of all listed publications)
2019
ProtoGAN: Towards Few Shot Learning for Action Recognition
Dwivedi, S. K., Gupta, V., Mitra, R., Ahmed, S., Jain, A.
Proc. International Conference on Computer Vision (ICCV) Workshops, October 2019 (manual)
Few-shot learning (FSL) for action recognition is a challenging task of recognizing novel action categories which are represented by few instances in the training data. In a more generalized FSL setting (G-FSL), both seen as well as novel action categories need to be recognized. Conventional classifiers suffer due to inadequate data in FSL setting and inherent bias towards seen action categories in G-FSL setting. In this paper, we address this problem by proposing a novel ProtoGAN framework which synthesizes additional examples for novel categories by conditioning a conditional generative adversarial network with class prototype vectors. These class prototype vectors are learnt using a Class Prototype Transfer Network (CPTN) from examples of seen categories. Our synthesized examples for a novel class are semantically similar to real examples belonging to that class and is used to train a model exhibiting better generalization towards novel classes. We support our claim by performing extensive experiments on three datasets: UCF101, HMDB51 and Olympic-Sports. To the best of our knowledge, we are the first to report the results for G-FSL and provide a strong benchmark for future research. We also outperform the state-of-the-art method in FSL for all the aforementioned datasets.
ps
2019
ps
Dwivedi, S. K., Gupta, V., Mitra, R., Ahmed, S., Jain, A.
ProtoGAN: Towards Few Shot Learning for Action Recognition
Proc. International Conference on Computer Vision (ICCV) Workshops, October 2019 (manual)