Search Results for author: Soma Biswas

Found 25 papers, 7 papers with code

Adaptive Margin Diversity Regularizer for handling Data Imbalance in Zero-Shot SBIR

no code implementations ECCV 2020 Titir Dutta, Anurag Singh, Soma Biswas

Extensive experiments and analysis justifies the effectiveness of the proposed AMDReg for mitigating the effect of data imbalance for generalization to unseen classes in ZS-SBIR.

Retrieval Sketch-Based Image Retrieval

Leveraging Out-of-Domain Data for Domain-Specific Prompt Tuning in Multi-Modal Fake News Detection

no code implementations27 Nov 2023 Debarshi Brahma, Amartya Bhattacharya, Suraj Nagaje Mahadev, Anmol Asati, Vikas Verma, Soma Biswas

First, to compute generalizable features, we modify the Vision-Language Model, CLIP to extract features that helps to align the representations of the images and corresponding text captions of both the in-domain and out-of-domain data in a label-aware manner.

Fake News Detection Language Modelling +1

Robust Feature Learning and Global Variance-Driven Classifier Alignment for Long-Tail Class Incremental Learning

1 code implementation2 Nov 2023 Jayateja Kalla, Soma Biswas

This paper introduces a two-stage framework designed to enhance long-tail class incremental learning, enabling the model to progressively learn new classes, while mitigating catastrophic forgetting in the context of long-tailed data distributions.

Class Incremental Learning Incremental Learning

pSTarC: Pseudo Source Guided Target Clustering for Fully Test-Time Adaptation

no code implementations2 Sep 2023 Manogna Sreenivas, Goirik Chakrabarty, Soma Biswas

This method draws inspiration from target clustering techniques and exploits the source classifier for generating pseudo-source samples.

Clustering Test

Test Time Adaptation for Blind Image Quality Assessment

2 code implementations ICCV 2023 Subhadeep Roy, Shankhanil Mitra, Soma Biswas, Rajiv Soundararajan

In this work, we introduce two novel quality-relevant auxiliary tasks at the batch and sample levels to enable TTA for blind IQA.

Blind Image Quality Assessment Test

S3C: Self-Supervised Stochastic Classifiers for Few-Shot Class-Incremental Learning

1 code implementation5 Jul 2023 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.

Few-Shot Class-Incremental Learning Incremental Learning

SATA: Source Anchoring and Target Alignment Network for Continual Test Time Adaptation

no code implementations20 Apr 2023 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.


Pred&Guide: Labeled Target Class Prediction for Guiding Semi-Supervised Domain Adaptation

1 code implementation22 Nov 2022 Megh Manoj Bhalerao, Anurag Singh, Soma Biswas

Here, we propose a novel framework, Pred&Guide, which leverages the inconsistency between the predicted and the actual class labels of the few labeled target examples to effectively guide the domain adaptation in a semi-supervised setting.

Semi-supervised Domain Adaptation Unsupervised Domain Adaptation

Test-time Training for Data-efficient UCDR

1 code implementation19 Aug 2022 Soumava Paul, Titir Dutta, Aheli Saha, Abhishek Samanta, Soma Biswas

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 in this direction.

Domain Adaptation Image Classification +5

Novel Class Discovery without Forgetting

no code implementations21 Jul 2022 K J Joseph, Sujoy Paul, Gaurav Aggarwal, Soma Biswas, Piyush Rai, Kai Han, Vineeth N Balasubramanian

Inspired by this, we identify and formulate a new, pragmatic problem setting of NCDwF: Novel Class Discovery without Forgetting, which tasks a machine learning model to incrementally discover novel categories of instances from unlabeled data, while maintaining its performance on the previously seen categories.

Novel Class Discovery

Spacing Loss for Discovering Novel Categories

1 code implementation22 Apr 2022 K J Joseph, Sujoy Paul, Gaurav Aggarwal, Soma Biswas, Piyush Rai, Kai Han, Vineeth N Balasubramanian

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 from a disjoint set of classes.

Novel Class Discovery

SITA: Single Image Test-time Adaptation

no code implementations4 Dec 2021 Ansh Khurana, Sujoy Paul, Piyush Rai, Soma Biswas, Gaurav Aggarwal

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.


Universal Cross-Domain Retrieval: Generalizing Across Classes and Domains

2 code implementations ICCV 2021 Soumava Paul, Titir Dutta, Soma Biswas

Towards that goal, we propose SnMpNet (Semantic Neighbourhood and Mixture Prediction Network), which incorporates two novel losses to account for the unseen classes and domains encountered during testing.


SML: Semantic Meta-learning for Few-shot Semantic Segmentation

no code implementations14 Sep 2020 Ayyappa Kumar Pambala, Titir Dutta, Soma Biswas

In addition, we propose to use the well established technique, ridge regression, to not only bring in the class-level semantic information, but also to effectively utilise the information available from multiple images present in the training data for prototype computation.

Few-Shot Semantic Segmentation Meta-Learning +2

A Novel Incremental Cross-Modal Hashing Approach

no code implementations3 Feb 2020 Devraj Mandal, Soma Biswas

For the second stage, we propose both a non-deep and deep architectures to learn the hash functions effectively.

Cross-Modal Retrieval Retrieval

A Novel Self-Supervised Re-labeling Approach for Training with Noisy Labels

no code implementations13 Oct 2019 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.

Label Prediction Framework for Semi-Supervised Cross-Modal Retrieval

no code implementations27 May 2019 Devraj Mandal, Pramod Rao, Soma Biswas

In this work, we propose a novel framework in a semi-supervised setting, which can predict the labels of the unlabeled data using complementary information from different modalities.

Cross-Modal Retrieval Retrieval

Unified Generator-Classifier for Efficient Zero-Shot Learning

no code implementations11 May 2019 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 encountered.

Action Classification General Classification +2

Multi-class Novelty Detection Using Mix-up Technique

no code implementations11 May 2019 Supritam Bhattacharjee, Devraj Mandal, Soma Biswas

Our model which is trained to reveal the constituent classes can then be used to determine whether the sample is novel or not.

Novelty Detection Test

Semi-Supervised Cross-Modal Retrieval with Label Prediction

no code implementations4 Dec 2018 Devraj Mandal, Pramod Rao, Soma Biswas

Due to abundance of data from multiple modalities, cross-modal retrieval tasks with image-text, audio-image, etc.

Cross-Modal Retrieval Retrieval

Preserving Semantic Relations for Zero-Shot Learning

no code implementations CVPR 2018 Yashas Annadani, Soma Biswas

We devise objective functions to preserve these relations in the embedding space, thereby inducing semanticity to the embedding space.

Attribute Zero-Shot Learning

Generalized Semantic Preserving Hashing for N-Label Cross-Modal Retrieval

no code implementations CVPR 2017 Devraj Mandal, Kunal. N. Chaudhury, Soma Biswas

Different scenarios of cross-modal matching are possible, for example, data from the different modalities can be associated with a single label or multiple labels, and in addition may or may not have one-to-one correspondence.

Cross-Modal Retrieval Retrieval +2

Sliding Dictionary Based Sparse Representation For Action Recognition

no code implementations1 Nov 2016 Yashas Annadani, D L Rakshith, Soma Biswas

This is used to compute the sparse coefficients of the input action sequence which is divided into overlapping windows and each window gives a probability score for each action class.

Action Recognition Temporal Action Localization

Cannot find the paper you are looking for? You can Submit a new open access paper.