3.3k citations · 4.2k across the 69 of their papers we have counts for
47 papers · 1 filter
-Patching: A Framework for Rapid Adaptation of Pre-trained Convolutional Networks without Base Performance Loss
Chaitanya Devaguptapu, Samarth Sinha, K J Joseph +2
Models pre-trained on large-scale datasets are often fine-tuned to support newer tasks and datasets that arrive over time. This process necessitates storing copies of the model ove…
Distilling the Undistillable: Learning from a Nasty Teacher
Surgan Jandial, Yash Khasbage, Arghya Pal +2
The inadvertent stealing of private/sensitive information using Knowledge Distillation (KD) has been getting significant attention recently and has guided subsequent defense effort…
ARUBA: An Architecture-Agnostic Balanced Loss for Aerial Object Detection
Rebbapragada V C Sairam, Monish Keswani, Uttaran Sinha +2
Deep neural networks tend to reciprocate the bias of their training dataset. In object detection, the bias exists in the form of various imbalances such as class, background-foregr…
Class-Incremental Learning with Cross-Space Clustering and Controlled Transfer
Arjun Ashok, K J Joseph, Vineeth Balasubramanian
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 mod…
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…
INDIGO: Intrinsic Multimodality for Domain Generalization
Puneet Mangla, Shivam Chandhok, Milan Aggarwal +2
For models to generalize under unseen domains (a.k.a domain generalization), it is crucial to learn feature representations that are domain-agnostic and capture the underlying sema…
On Conditioning the Input Noise for Controlled Image Generation with Diffusion Models
Vedant Singh, Surgan Jandial, Ayush Chopra +3
Conditional image generation has paved the way for several breakthroughs in image editing, generating stock photos and 3-D object generation. This continues to be a significant are…
Proto2Proto: Can you recognize the car, the way I do?
Monish Keswani, Sriranjani Ramakrishnan, Nishant Reddy +1
Prototypical methods have recently gained a lot of attention due to their intrinsic interpretable nature, which is obtained through the prototypes. With growing use cases of model…
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…
Unseen Classes at a Later Time? No Problem
Hari Chandana Kuchibhotla, Sumitra S Malagi, Shivam Chandhok +1
Recent progress towards learning from limited supervision has encouraged efforts towards designing models that can recognize novel classes at test time (generalized zero-shot learn…
Energy-based Latent Aligner for Incremental Learning
K J Joseph, Salman Khan, Fahad Shahbaz Khan +2
Deep learning models tend to forget their earlier knowledge while incrementally learning new tasks. This behavior emerges because the parameter updates optimized for the new tasks…
Feature Generation for Long-tail Classification
Rahul Vigneswaran, Marc T. Law, Vineeth N. Balasubramanian +1
The visual world naturally exhibits an imbalance in the number of object or scene instances resulting in a \emph{long-tailed distribution}. This imbalance poses significant challen…
Multi-Domain Incremental Learning for Semantic Segmentation
Prachi Garg, Rohit Saluja, Vineeth N Balasubramanian +3
Recent efforts in multi-domain learning for semantic segmentation attempt to learn multiple geographical datasets in a universal, joint model. A simple fine-tuning experiment perfo…
Context-Conditional Adaptation for Recognizing Unseen Classes in Unseen Domains
Puneet Mangla, Shivam Chandhok, Vineeth N Balasubramanian +1
Recent progress towards designing models that can generalize to unseen domains (i.e domain generalization) or unseen classes (i.e zero-shot learning) has embarked interest towards…
Learn from Anywhere: Rethinking Generalized Zero-Shot Learning with Limited Supervision
Gaurav Bhatt, Shivam Chandhok, Vineeth N Balasubramanian
A common problem with most zero and few-shot learning approaches is they suffer from bias towards seen classes resulting in sub-optimal performance. Existing efforts aim to utilize…
Structured Latent Embeddings for Recognizing Unseen Classes in Unseen Domains
Shivam Chandhok, Sanath Narayan, Hisham Cholakkal +4
The need to address the scarcity of task-specific annotated data has resulted in concerted efforts in recent years for specific settings such as zero-shot learning (ZSL) and domain…
Canonical Saliency Maps: Decoding Deep Face Models
Thrupthi Ann John, Vineeth N Balasubramanian, C V Jawahar
As Deep Neural Network models for face processing tasks approach human-like performance, their deployment in critical applications such as law enforcement and access control has se…
Towards Open World Object Detection
K J Joseph, Salman Khan, Fahad Shahbaz Khan +1
Humans have a natural instinct to identify unknown object instances in their environments. The intrinsic curiosity about these unknown instances aids in learning about them, when t…
Few Shot Learning With No Labels
Aditya Bharti, N. B. Vineeth, C. V. Jawahar
Few-shot learners aim to recognize new categories given only a small number of training samples. The core challenge is to avoid overfitting to the limited data while ensuring good…
Enhanced Regularizers for Attributional Robustness
Anindya Sarkar, Anirban Sarkar, Vineeth N Balasubramanian
Deep neural networks are the default choice of learning models for computer vision tasks. Extensive work has been carried out in recent years on explaining deep models for vision t…
Data InStance Prior (DISP) in Generative Adversarial Networks
Puneet Mangla, Nupur Kumari, Mayank Singh +2
Recent advances in generative adversarial networks (GANs) have shown remarkable progress in generating high-quality images. However, this gain in performance depends on the availab…
Beyond VQA: Generating Multi-word Answer and Rationale to Visual Questions
Radhika Dua, Sai Srinivas Kancheti, Vineeth N Balasubramanian
Visual Question Answering is a multi-modal task that aims to measure high-level visual understanding. Contemporary VQA models are restrictive in the sense that answers are obtained…
Meta-Consolidation for Continual Learning
K J Joseph, Vineeth N Balasubramanian
The ability to continuously learn and adapt itself to new tasks, without losing grasp of already acquired knowledge is a hallmark of biological learning systems, which current deep…
Evaluating and Mitigating Bias in Image Classifiers: A Causal Perspective Using Counterfactuals
Saloni Dash, Vineeth N Balasubramanian, Amit Sharma
Counterfactual examples for an input -- perturbations that change specific features but not others -- have been shown to be useful for evaluating bias of machine learning models, e…