Search Results for author:
Found 25 papers, 7 papers with code
Adaptive Margin Diversity Regularizer for handling Data Imbalance in Zero-Shot SBIR
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.
DPOD: Domain-Specific Prompt Tuning for Multimodal Fake News Detection
In this work, we explore whether out-of-domain data can help to improve out-of-context misinformation detection (termed here as multi-modal fake news detection) of a desired domain, to address this challenging problem.
Robust Feature Learning and Global Variance-Driven Classifier Alignment for Long-Tail Class Incremental Learning
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.
pSTarC: Pseudo Source Guided Target Clustering for Fully Test-Time Adaptation
This method draws inspiration from target clustering techniques and exploits the source classifier for generating pseudo-source samples.
Test Time Adaptation for Blind Image Quality Assessment
In this work, we introduce two novel quality-relevant auxiliary tasks at the batch and sample levels to enable TTA for blind IQA.
S3C: Self-Supervised Stochastic Classifiers for Few-Shot Class-Incremental Learning
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.
SATA: Source Anchoring and Target Alignment Network for Continual Test Time Adaptation
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
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
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.
Novel Class Discovery without Forgetting
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.
Spacing Loss for Discovering Novel Categories
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.
SITA: Single Image Test-time Adaptation
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
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
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.
A Novel Incremental Cross-Modal Hashing Approach
For the second stage, we propose both a non-deep and deep architectures to learn the hash functions effectively.
A Novel Self-Supervised Re-labeling Approach for Training with Noisy Labels
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
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.
Unified Generator-Classifier for Efficient Zero-Shot Learning
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.
Multi-class Novelty Detection Using Mix-up Technique
Our model which is trained to reveal the constituent classes can then be used to determine whether the sample is novel or not.
Semi-Supervised Cross-Modal Retrieval with Label Prediction
Due to abundance of data from multiple modalities, cross-modal retrieval tasks with image-text, audio-image, etc.
Preserving Semantic Relations for Zero-Shot Learning
We devise objective functions to preserve these relations in the embedding space, thereby inducing semanticity to the embedding space.
Generalized Semantic Preserving Hashing for N-Label Cross-Modal Retrieval
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.
Sliding Dictionary Based Sparse Representation For Action Recognition
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.
Discriminative Pose-Free Descriptors for Face and Object Matching
The DPFD of images taken from different viewpoints can be directly compared for matching.
Temporally Coherent Bayesian Models for Entity Discovery in Videos by Tracklet Clustering
The task of \emph{Entity Discovery} in videos can be naturally posed as tracklet clustering.
