Workshop
|
|
How to Determine the Preferred Image Distribution of a Black-Box Vision-Language Model?
Saeid Asgari · Joseph G Lambourne · Alana Mongkhounsavath
|
|
Poster
|
|
MaskFactory: Towards High-quality Synthetic Data Generation for Dichotomous Image Segmentation
Haotian Qian · Yinda Chen · Shengtao Lou · Fahad Shahbaz Khan · Xiaogang Jin · Deng-Ping Fan
|
|
Affinity Event
|
|
Improving Wild Pig Detection through Data Augmentation and Thermal Imagery: A Comparative Study of Model Performance.
Alhim Adonai Vera Gonzalez · Donghoon Kim
|
|
Workshop
|
|
Auxiliary objectives improve generalization performance but reduce model specification for low-data neuroimaging-based brain age prediction
Donghyun Kim · Eloy Geenjaar · Vince Calhoun
|
|
Poster
|
Thu 16:30
|
The Unmet Promise of Synthetic Training Images: Using Retrieved Real Images Performs Better
Scott Geng · Cheng-Yu Hsieh · Vivek Ramanujan · Matthew Wallingford · Chun-Liang Li · Pang Wei Koh · Ranjay Krishna
|
|
Workshop
|
|
Application of Contrastive Learning on ECG Data: Evaluating Performance in Japanese and Classification with Around 100 Labels
Junichiro Takahashi · JingChuan Guan · Kaito Baba · satoshi kodera
|
|
Workshop
|
|
Mix Data or Merge Models? Optimizing for Performance and Safety in Multilingual Contexts
Aakanksha · Arash Ahmadian · Seraphina Goldfarb-Tarrant · Beyza Ermis · Marzieh Fadaee · Sara Hooker
|
|
Poster
|
Wed 11:00
|
No "Zero-Shot" Without Exponential Data: Pretraining Concept Frequency Determines Multimodal Model Performance
Vishaal Udandarao · Ameya Prabhu · Adhiraj Ghosh · Yash Sharma · Philip Torr · Adel Bibi · Samuel Albanie · Matthias Bethge
|
|
Workshop
|
|
Pretraining Frequency Predicts Compositional Generalization of CLIP on Real-World Tasks
Thaddäus Wiedemer · Yash Sharma · Ameya Prabhu · Matthias Bethge · Wieland Brendel
|
|
Poster
|
Thu 11:00
|
Right this way: Can VLMs Guide Us to See More to Answer Questions?
Li Liu · Diji Yang · Sijia Zhong · Kalyana Suma Sree Tholeti · Lei Ding · Yi Zhang · Leilani Gilpin
|
|