192 citations · 193 across the 9 of their papers we have counts for
10 papers
Multimodal Unlearning Across Vision, Language, Video, and Audio: Survey of Methods, Datasets, and Benchmarks
Nobin Sarwar, Shubhashis Roy Dipta, Zheyuan Liu +1
With the growing adoption of VLMs, DMs, LLMs, and AFMs, these multimodal foundation models can inadvertently encode sensitive, copyrighted, biased, or unsafe cross-modal associatio…
Benchmarking Large Vision-Language Models on Fine-Grained Image Tasks: From Evaluation to Diagnosis
Hong-Tao Yu, Chen-Wei Xie, Yuxin Peng +2
Recent advancements in Large Vision-Language Models (LVLMs) have demonstrated remarkable multimodal perception and reasoning capabilities. While numerous benchmarks have evaluated…
MMEarth-Bench: Global Model Adaptation via Multimodal Test-Time Training
Lucia Gordon, Serge Belongie, Christian Igel +1
Recent research in geospatial machine learning demonstrates that models pretrained with self-supervised learning on Earth observation data can perform well on downstream tasks with…
SuperF: Neural Implicit Fields for Multi-Image Super-Resolution
Sander Riisøen Jyhne, Christian Igel, Morten Goodwin +3
High-resolution imagery is often hindered by limitations in sensor technology, atmospheric conditions, and costs. Such challenges occur in satellite remote sensing, but also with h…
Taxonomy-Aware Evaluation of Vision-Language Models
Vésteinn Snæbjarnarson, Kevin Du, Niklas Stoehr +4
When a vision-language model (VLM) is prompted to identify an entity depicted in an image, it may answer 'I see a conifer,' rather than the specific label 'norway spruce'. This rai…
Better Language Models Exhibit Higher Visual Alignment
Jona Ruthardt, Gertjan J. Burghouts, Serge Belongie +1
How well do text-only large language models (LLMs) align with the visual world? We present a systematic evaluation of this question by incorporating frozen representations of vario…
Labeled Data Selection for Category Discovery
Bingchen Zhao, Nico Lang, Serge Belongie +1
Category discovery methods aim to find novel categories in unlabeled visual data. At training time, a set of labeled and unlabeled images are provided, where the labels correspond…
MMEarth: Exploring Multi-Modal Pretext Tasks For Geospatial Representation Learning
Vishal Nedungadi, Ankit Kariryaa, Stefan Oehmcke +3
The volume of unlabelled Earth observation (EO) data is huge, but many important applications lack labelled training data. However, EO data offers the unique opportunity to pair da…
Familiarity-Based Open-Set Recognition Under Adversarial Attacks
Philip Enevoldsen, Christian Gundersen, Nico Lang +2
Open-set recognition (OSR), the identification of novel categories, can be a critical component when deploying classification models in real-world applications. Recent work has sho…
Adaptively Learning the Crowd Kernel
Omer Tamuz, Ce Liu, Serge Belongie +2
We introduce an algorithm that, given n objects, learns a similarity matrix over all n^2 pairs, from crowdsourced data alone. The algorithm samples responses to adaptively chosen t…