25 citations · 56 across the 25 of their papers we have counts for
6 papers · 1 filter
TripletCLIP: Improving Compositional Reasoning of CLIP via Synthetic Vision-Language Negatives
Maitreya Patel, Abhiram Kusumba, Sheng Cheng +4
Contrastive Language-Image Pretraining (CLIP) models maximize the mutual information between text and visual modalities to learn representations. This makes the nature of the train…
REVISION: Rendering Tools Enable Spatial Fidelity in Vision-Language Models
Agneet Chatterjee, Yiran Luo, Tejas Gokhale +2
Text-to-Image (T2I) and multimodal large language models (MLLMs) have been adopted in solutions for several computer vision and multimodal learning tasks. However, it has been foun…
Grounding Stylistic Domain Generalization with Quantitative Domain Shift Measures and Synthetic Scene Images
Yiran Luo, Joshua Feinglass, Tejas Gokhale +3
Domain Generalization (DG) is a challenging task in machine learning that requires a coherent ability to comprehend shifts across various domains through extraction of domain-invar…
On the Robustness of Language Guidance for Low-Level Vision Tasks: Findings from Depth Estimation
Agneet Chatterjee, Tejas Gokhale, Chitta Baral +1
Recent advances in monocular depth estimation have been made by incorporating natural language as additional guidance. Although yielding impressive results, the impact of the langu…
Improving Shift Invariance in Convolutional Neural Networks with Translation Invariant Polyphase Sampling
Sourajit Saha, Tejas Gokhale
Downsampling operators break the shift invariance of convolutional neural networks (CNNs) and this affects the robustness of features learned by CNNs when dealing with even small p…
Getting it Right: Improving Spatial Consistency in Text-to-Image Models
Agneet Chatterjee, Gabriela Ben Melech Stan, Estelle Aflalo +8
One of the key shortcomings in current text-to-image (T2I) models is their inability to consistently generate images which faithfully follow the spatial relationships specified in…