2 citations · 2 across the 13 of their papers we have counts for
14 papers
Can Circuit Alignment Predict OOD Generalization?
Ayan Banerjee, Abhra Chaudhuri, Josep Llados +2
Can out-of-distribution (OOD) generalization be predicted from a trained model's weights alone, without any target-domain data? Existing representational similarity metrics (CKA, S…
On the Role of the Projector in Contrastive Self-Supervised Learning: Last-Layer Rank Dynamics Drive Representation Quality
Siladittya Manna, Priyangshu Mandal, Umapada Pal +1
The dimensional collapse of representations in self-supervised contrastive learning is an ever-present issue. One notable technique to prevent such a collapse of representations is…
Vision-Language Models are Fragile Multilingual Associators
Ritabrata Chakraborty, Rajatsubhra Chakraborty, Shivakumara Palaiahnakote +2
Vision-language models must associate visual entities with textual attributes. Whether these associations or concept bindings remain stable when the language of the input changes i…
TaleDiffusion: Multi-Character Story Generation with Dialogue Rendering
Ayan Banerjee, Josep Llados, Umapada Pal +1
Text-to-story visualization is challenging due to the need for consistent interaction among multiple characters across frames. Existing methods struggle with character consistency,…
Privacy-enhancing Sclera Segmentation Benchmarking Competition: SSBC 2025
Matej Vitek, Darian Tomašević, Abhijit Das +32
This paper presents a summary of the 2025 Sclera Segmentation Benchmarking Competition (SSBC), which focused on the development of privacy-preserving sclera-segmentation models tra…
d-Sketch: Improving Visual Fidelity of Sketch-to-Image Translation with Pretrained Latent Diffusion Models without Retraining
Prasun Roy, Saumik Bhattacharya, Subhankar Ghosh +2
Structural guidance in an image-to-image translation allows intricate control over the shapes of synthesized images. Generating high-quality realistic images from user-specified ro…
Exploring Mutual Cross-Modal Attention for Context-Aware Human Affordance Generation
Prasun Roy, Saumik Bhattacharya, Subhankar Ghosh +2
Human affordance learning investigates contextually relevant novel pose prediction such that the estimated pose represents a valid human action within the scene. While the task is…
Decorrelation-based Self-Supervised Visual Representation Learning for Writer Identification
Arkadip Maitra, Shree Mitra, Siladittya Manna +2
Self-supervised learning has developed rapidly over the last decade and has been applied in many areas of computer vision. Decorrelation-based self-supervised pretraining has shown…
Correlation Weighted Prototype-based Self-Supervised One-Shot Segmentation of Medical Images
Siladittya Manna, Saumik Bhattacharya, Umapada Pal
Medical image segmentation is one of the domains where sufficient annotated data is not available. This necessitates the application of low-data frameworks like few-shot learning.…
FastTextSpotter: A High-Efficiency Transformer for Multilingual Scene Text Spotting
Alloy Das, Sanket Biswas, Umapada Pal +2
The proliferation of scene text in both structured and unstructured environments presents significant challenges in optical character recognition (OCR), necessitating more efficien…
CraftSVG: Multi-Object Text-to-SVG Synthesis via Layout Guided Diffusion
Ayan Banerjee, Nityanand Mathur, Josep Llados +2
Generating VectorArt from text prompts is a challenging vision task, requiring diverse yet realistic depictions of the seen as well as unseen entities. However, existing research h…
GraphKD: Exploring Knowledge Distillation Towards Document Object Detection with Structured Graph Creation
Ayan Banerjee, Sanket Biswas, Josep Lladós +1
Object detection in documents is a key step to automate the structural elements identification process in a digital or scanned document through understanding the hierarchical struc…
Harnessing the Power of Multi-Lingual Datasets for Pre-training: Towards Enhancing Text Spotting Performance
Alloy Das, Sanket Biswas, Ayan Banerjee +3
The adaptation capability to a wide range of domains is crucial for scene text spotting models when deployed to real-world conditions. However, existing state-of-the-art (SOTA) app…
Diving into the Depths of Spotting Text in Multi-Domain Noisy Scenes
Alloy Das, Sanket Biswas, Umapada Pal +1
When used in a real-world noisy environment, the capacity to generalize to multiple domains is essential for any autonomous scene text spotting system. However, existing state-of-t…