167 citations · 520 across the 43 of their papers we have counts for
12 papers · 1 filter
TEA: Text Encoder Alignment for Robust Concept Erasure in Text-to-Image Models
Alireza Dehghanpour Farashah, Zhuan Shi, Negar Rostamzadeh +1
Text-to-image diffusion models can be misused to generate harmful content through adversarial or paraphrased prompts that bypass built-in safety mechanisms. Existing concept erasur…
Evaluation of Cultural Competence of Vision-Language Models
Srishti Yadav, Lauren Tilton, Maria Antoniak +10
Modern vision-language models (VLMs) often fail at cultural competency evaluations and benchmarks. Given the diversity of applications built upon VLMs, there is renewed interest in…
Erasing More Than Intended? How Concept Erasure Degrades the Generation of Non-Target Concepts
Ibtihel Amara, Ahmed Imtiaz Humayun, Ivana Kajic +12
Concept erasure techniques have recently gained significant attention for their potential to remove unwanted concepts from text-to-image models. While these methods often demonstra…
se-Shweshwe Inspired Fashion Generation
Lindiwe Brigitte Malobola, Negar Rostamzadeh, Shakir Mohamed
Fashion is one of the ways in which we show ourselves to the world. It is a reflection of our personal decisions and one of the ways in which people distinguish and represent thems…
Ethics and Creativity in Computer Vision
Negar Rostamzadeh, Emily Denton, Linda Petrini
This paper offers a retrospective of what we learnt from organizing the workshop *Ethical Considerations in Creative applications of Computer Vision* at CVPR 2021 conference and, p…
A Few-Shot Sequential Approach for Object Counting
Negin Sokhandan, Pegah Kamousi, Alejandro Posada +2
In this work, we address the problem of few-shot multi-class object counting with point-level annotations. The proposed technique leverages a class agnostic attention mechanism tha…
Reinforced active learning for image segmentation
Arantxa Casanova, Pedro O. Pinheiro, Negar Rostamzadeh +1
Learning-based approaches for semantic segmentation have two inherent challenges. First, acquiring pixel-wise labels is expensive and time-consuming. Second, realistic segmentation…
Instance Segmentation with Point Supervision
Issam H. Laradji, Negar Rostamzadeh, Pedro O. Pinheiro +2
Instance segmentation methods often require costly per-pixel labels. We propose a method that only requires point-level annotations. During training, the model only has access to a…
CLAREL: Classification via retrieval loss for zero-shot learning
Boris N. Oreshkin, Negar Rostamzadeh, Pedro O. Pinheiro +1
We address the problem of learning fine-grained cross-modal representations. We propose an instance-based deep metric learning approach in joint visual and textual space. The key n…
Adversarial Framing for Image and Video Classification
Konrad Zolna, Michal Zajac, Negar Rostamzadeh +1
Neural networks are prone to adversarial attacks. In general, such attacks deteriorate the quality of the input by either slightly modifying most of its pixels, or by occluding it…
Domain-Adaptive Single-View 3D Reconstruction
Pedro O. Pinheiro, Negar Rostamzadeh, Sungjin Ahn
Single-view 3D shape reconstruction is an important but challenging problem, mainly for two reasons. First, as shape annotation is very expensive to acquire, current methods rely o…
Where are the Blobs: Counting by Localization with Point Supervision
Issam H. Laradji, Negar Rostamzadeh, Pedro O. Pinheiro +2
Object counting is an important task in computer vision due to its growing demand in applications such as surveillance, traffic monitoring, and counting everyday objects. State-of-…