77 citations · 155 across the 20 of their papers we have counts for
20 papers
S3C: Self-Supervised Stochastic Classifiers for Few-Shot Class-Incremental Learning
Jayateja Kalla, Soma Biswas
Few-shot class-incremental learning (FSCIL) aims to learn progressively about new classes with very few labeled samples, without forgetting the knowledge of already learnt classes.…
Test Time Adaptation for Blind Image Quality Assessment
Subhadeep Roy, Shankhanil Mitra, Soma Biswas +1
While the design of blind image quality assessment (IQA) algorithms has improved significantly, the distribution shift between the training and testing scenarios often leads to a p…
SATA: Source Anchoring and Target Alignment Network for Continual Test Time Adaptation
Goirik Chakrabarty, Manogna Sreenivas, Soma Biswas
Adapting a trained model to perform satisfactorily on continually changing testing domains/environments is an important and challenging task. In this work, we propose a novel frame…
Pred&Guide: Labeled Target Class Prediction for Guiding Semi-Supervised Domain Adaptation
Megh Manoj Bhalerao, Anurag Singh, Soma Biswas
Semi-supervised domain adaptation aims to classify data belonging to a target domain by utilizing a related label-rich source domain and very few labeled examples of the target dom…
Test-time Training for Data-efficient UCDR
Soumava Paul, Titir Dutta, Aheli Saha +2
Image retrieval under generalized test scenarios has gained significant momentum in literature, and the recently proposed protocol of Universal Cross-domain Retrieval is a pioneer…
Novel Class Discovery without Forgetting
K J Joseph, Sujoy Paul, Gaurav Aggarwal +4
Humans possess an innate ability to identify and differentiate instances that they are not familiar with, by leveraging and adapting the knowledge that they have acquired so far. I…
Spacing Loss for Discovering Novel Categories
K J Joseph, Sujoy Paul, Gaurav Aggarwal +4
Novel Class Discovery (NCD) is a learning paradigm, where a machine learning model is tasked to semantically group instances from unlabeled data, by utilizing labeled instances fro…
SITA: Single Image Test-time Adaptation
Ansh Khurana, Sujoy Paul, Piyush Rai +2
In Test-time Adaptation (TTA), given a source model, the goal is to adapt it to make better predictions for test instances from a different distribution than the source. Crucially,…
Universal Cross-Domain Retrieval: Generalizing Across Classes and Domains
Soumava Paul, Titir Dutta, Soma Biswas
In this work, for the first time, we address the problem of universal cross-domain retrieval, where the test data can belong to classes or domains which are unseen during training.…
SML: Semantic Meta-learning for Few-shot Semantic Segmentation
Ayyappa Kumar Pambala, Titir Dutta, Soma Biswas
The significant amount of training data required for training Convolutional Neural Networks has become a bottleneck for applications like semantic segmentation. Few-shot semantic s…
A Novel Incremental Cross-Modal Hashing Approach
Devraj Mandal, Soma Biswas
Cross-modal retrieval deals with retrieving relevant items from one modality, when provided with a search query from another modality. Hashing techniques, where the data is represe…
A Novel Self-Supervised Re-labeling Approach for Training with Noisy Labels
Devraj Mandal, Shrisha Bharadwaj, Soma Biswas
The major driving force behind the immense success of deep learning models is the availability of large datasets along with their clean labels. Unfortunately, this is very difficul…
Label Prediction Framework for Semi-Supervised Cross-Modal Retrieval
Devraj Mandal, Pramod Rao, Soma Biswas
Cross-modal data matching refers to retrieval of data from one modality, when given a query from another modality. In general, supervised algorithms achieve better retrieval perfor…
Unified Generator-Classifier for Efficient Zero-Shot Learning
Ayyappa Kumar Pambala, Titir Dutta, Soma Biswas
Generative models have achieved state-of-the-art performance for the zero-shot learning problem, but they require re-training the classifier every time a new object category is enc…
Multi-class Novelty Detection Using Mix-up Technique
Supritam Bhattacharjee, Devraj Mandal, Soma Biswas
Multi-class novelty detection is increasingly becoming an important area of research due to the continuous increase in the number of object categories. It tries to answer the perti…
Semi-Supervised Cross-Modal Retrieval with Label Prediction
Devraj Mandal, Pramod Rao, Soma Biswas
Due to abundance of data from multiple modalities, cross-modal retrieval tasks with image-text, audio-image, etc. are gaining increasing importance. Of the different approaches pro…
Preserving Semantic Relations for Zero-Shot Learning
Yashas Annadani, Soma Biswas
Zero-shot learning has gained popularity due to its potential to scale recognition models without requiring additional training data. This is usually achieved by associating catego…
Sliding Dictionary Based Sparse Representation For Action Recognition
Yashas Annadani, D L Rakshith, Soma Biswas
The task of action recognition has been in the forefront of research, given its applications in gaming, surveillance and health care. In this work, we propose a simple, yet very ef…
Temporally Coherent Bayesian Models for Entity Discovery in Videos by Tracklet Clustering
Adway Mitra, Soma Biswas, Chiranjib Bhattacharyya
A video can be represented as a sequence of tracklets, each spanning 10-20 frames, and associated with one entity (eg. a person). The task of \emph{Entity Discovery} in videos can…
Digital Curvatures Applied to 3D Object Analysis and Recognition: A Case Study
Li Chen, Soma Biswas
In this paper, we propose using curvatures in digital space for 3D object analysis and recognition. Since direct adjacency has only six types of digital surface points in local con…