K. J. Joseph
Current Organizations / Institutes
The organizations/institutes from the scholar's latest article
Research Subjects
K. J. Joseph has a total of 25 co-authors. Here are the top co-authors by number of shared publications:
- Vineeth Nallure Balasubramanian
IIT Hyderabad
5 shared publications - Arjun Ashok
Indian Institute of Technology Hyderabad
2 shared publications - Akash Ghosh
Indian Institute of Technology Patna, Patna, India
1 shared publication Amit Srivastava
ANURAG, Defense Research and Development Organization
1 shared publicationArghya Pal
IIT Hyderabad INDIA
1 shared publication- Chris Tensmeyer
Adobe Research
1 shared publication
Latest Publications
- 15 September 2026
- Published by Springer Nature
- p. 120-137
Text-Conditioned Background Generation for Editable Multi-layer Documents
- 15 September 2026
- Published by Springer Nature
- p. 120-137
Text-Conditioned Background Generation for Editable Multi-layer Documents
- Open Access
- 27 October 2025
- Published by Association for Computing Machinery (ACM)
- p. 14342-14343
Reasoning and Planning for Multimodal Large Language Models: A Multilingual and Cross-Domain Exploration
- 27 October 2025
- Published by Association for Computing Machinery (ACM)
- p. 14342-14343
Open AccessReasoning and Planning for Multimodal Large Language Models: A Multilingual and Cross-Domain Exploration
- 30 October 2022
- Published by Springer Nature
- p. 105-122
Class-Incremental Learning with Cross-Space Clustering and Controlled Transfer
- 30 October 2022
- Published by Springer Nature
- p. 105-122
Class-Incremental Learning with Cross-Space Clustering and Controlled Transfer
- Open Access
Class-Incremental Learning with Cross-Space Clustering and Controlled Transfer
In class-incremental learning, the model is expected to learn new classes continually while maintaining knowledge on previous classes. The challenge here lies in preserving the model's ability to effectively represent prior classes in the feature space, while adapting it to represent incoming new classes. We propose two distillation-based objectives for class incremental learning that leverage the structure of the feature space to maintain accuracy on previous classes, as well as enable learning the new classes. In our first objective, termed cross-space clustering (CSC), we propose to use the feature space structure of the previous model to characterize directions of optimization that maximally preserve the class: directions that all instances of a specific class should collectively optimize towards, and those that they should collectively optimize away from. Apart from minimizing forgetting, this indirectly encourages the model to cluster all instances of a class in the current feature space, and gives rise to a sense of herd-immunity, allowing all samples of a class to jointly combat the model from forgetting the class. Our second objective termed controlled transfer (CT) tackles incremental learning from an understudied perspective of inter-class transfer. CT explicitly approximates and conditions the current model on the semantic similarities between incrementally arriving classes and prior classes. This allows the model to learn classes in such a way that it maximizes positive forward transfer from similar prior classes, thus increasing plasticity, and minimizes negative backward transfer on dissimilar prior classes, whereby strengthening stability. We perform extensive experiments on two benchmark datasets, adding our method (CSCCT) on top of three prominent class-incremental learning methods. We observe consistent performance improvement on a variety of experimental settings.
Open AccessClass-Incremental Learning with Cross-Space Clustering and Controlled Transfer
In class-incremental learning, the model is expected to learn new classes continually while maintaining knowledge on previous classes. The challenge here lies in preserving the model's ability to effectively represent prior classes in the feature space, while adapting it to represent incoming new classes. We propose two distillation-based objectives for class incremental learning that leverage the structure of the feature space to maintain accuracy on previous classes, as well as enable learning the new classes. In our first objective, termed cross-space clustering (CSC), we propose to use the feature space structure of the previous model to characterize directions of optimization that maximally preserve the class: directions that all instances of a specific class should collectively optimize towards, and those that they should collectively optimize away from. Apart from minimizing forgetting, this indirectly encourages the model to cluster all instances of a class in the current feature space, and gives rise to a sense of herd-immunity, allowing all samples of a class to jointly combat the model from forgetting the class. Our second objective termed controlled transfer (CT) tackles incremental learning from an understudied perspective of inter-class transfer. CT explicitly approximates and conditions the current model on the semantic similarities between incrementally arriving classes and prior classes. This allows the model to learn classes in such a way that it maximizes positive forward transfer from similar prior classes, thus increasing plasticity, and minimizes negative backward transfer on dissimilar prior classes, whereby strengthening stability. We perform extensive experiments on two benchmark datasets, adding our method (CSCCT) on top of three prominent class-incremental learning methods. We observe consistent performance improvement on a variety of experimental settings.
- 2 November 2021
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Pattern Analysis and Machine Intelligence
- Vol. 44 (12) , 9209-9216
Incremental Object Detection via Meta-Learning
In a real-world setting, object instances from new classes can be continuously encountered by object detectors. When existing object detectors are applied to such scenarios, their performance on old classes deteriorates significantly. A few efforts have been reported to address this limitation, all of which apply variants of knowledge distillation to avoid catastrophic forgetting. We note that although distillation helps to retain previous learning, it obstructs fast adaptability to new tasks, which is a critical requirement for incremental learning. In this pursuit, we propose a meta-learning approach that learns to reshape model gradients, such that information across incremental tasks is optimally shared. This ensures a seamless information transfer via a meta-learned gradient preconditioning that minimizes forgetting and maximizes knowledge transfer. In comparison to existing meta-learning methods, our approach is task-agnostic, allows incremental addition of new-classes and scales to high-capacity models for object detection. We evaluate our approach on a variety of incremental learning settings defined on PASCAL-VOC and MS COCO datasets, where our approach performs favourably well against state-of-the-art methods. Code and trained models: https://github.com/JosephKJ/iOD .
- 2 November 2021
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Pattern Analysis and Machine Intelligence
- Vol. 44 (12) , 9209-9216
Incremental Object Detection via Meta-Learning
In a real-world setting, object instances from new classes can be continuously encountered by object detectors. When existing object detectors are applied to such scenarios, their performance on old classes deteriorates significantly. A few efforts have been reported to address this limitation, all of which apply variants of knowledge distillation to avoid catastrophic forgetting. We note that although distillation helps to retain previous learning, it obstructs fast adaptability to new tasks, which is a critical requirement for incremental learning. In this pursuit, we propose a meta-learning approach that learns to reshape model gradients, such that information across incremental tasks is optimally shared. This ensures a seamless information transfer via a meta-learned gradient preconditioning that minimizes forgetting and maximizes knowledge transfer. In comparison to existing meta-learning methods, our approach is task-agnostic, allows incremental addition of new-classes and scales to high-capacity models for object detection. We evaluate our approach on a variety of incremental learning settings defined on PASCAL-VOC and MS COCO datasets, where our approach performs favourably well against state-of-the-art methods. Code and trained models: https://github.com/JosephKJ/iOD .
- Open Access
C4Synth: Cross-Caption Cycle-Consistent Text-to-Image Synthesis
Generating an image from its description is a challenging task worth solving because of its numerous practical applications ranging from image editing to virtual reality. All existing methods use one single caption to generate a plausible image. A single caption by itself, can be limited, and may not be able to capture the variety of concepts and behavior that may be present in the image. We propose two deep generative models that generate an image by making use of multiple captions describing it. This is achieved by ensuring 'Cross-Caption Cycle Consistency' between the multiple captions and the generated image(s). We report quantitative and qualitative results on the standard Caltech-UCSD Birds (CUB) and Oxford-102 Flowers datasets to validate the efficacy of the proposed approach.
Open AccessC4Synth: Cross-Caption Cycle-Consistent Text-to-Image Synthesis
Generating an image from its description is a challenging task worth solving because of its numerous practical applications ranging from image editing to virtual reality. All existing methods use one single caption to generate a plausible image. A single caption by itself, can be limited, and may not be able to capture the variety of concepts and behavior that may be present in the image. We propose two deep generative models that generate an image by making use of multiple captions describing it. This is achieved by ensuring 'Cross-Caption Cycle Consistency' between the multiple captions and the generated image(s). We report quantitative and qualitative results on the standard Caltech-UCSD Birds (CUB) and Oxford-102 Flowers datasets to validate the efficacy of the proposed approach.