Zobrazeno 1 - 10
of 486
pro vyhledávání: '"Perona, Pietro"'
There is a vast literature on representation learning based on principles such as coding efficiency, statistical independence, causality, controllability, or symmetry. In this paper we propose to learn representations from sequence data by factorizin
Externí odkaz:
http://arxiv.org/abs/2410.05564
The study of social interactions and collective behaviors through multi-agent video analysis is crucial in biology. While self-supervised keypoint discovery has emerged as a promising solution to reduce the need for manual keypoint annotations, exist
Externí odkaz:
http://arxiv.org/abs/2409.09455
We explore social perception of human faces in CLIP, a widely used open-source vision-language model. To this end, we compare the similarity in CLIP embeddings between different textual prompts and a set of face images. Our textual prompts are constr
Externí odkaz:
http://arxiv.org/abs/2408.14435
Autor:
Marks, Markus, Knott, Manuel, Kondapaneni, Neehar, Cole, Elijah, Defraeye, Thijs, Perez-Cruz, Fernando, Perona, Pietro
Self-supervised learning (SSL) is a machine learning approach where the data itself provides supervision, eliminating the need for external labels. The model is forced to learn about the data structure or context by solving a pretext task. With SSL,
Externí odkaz:
http://arxiv.org/abs/2407.12210
Model performance evaluation is a critical and expensive task in machine learning and computer vision. Without clear guidelines, practitioners often estimate model accuracy using a one-time completely random selection of the data. However, by employi
Externí odkaz:
http://arxiv.org/abs/2406.07320
We introduce Discovering Conceptual Network Explanations (DCNE), a new approach for generating human-comprehensible visual explanations to enhance the interpretability of deep neural image classifiers. Our method automatically finds visual explanatio
Externí odkaz:
http://arxiv.org/abs/2405.15243
Autor:
Kay, Justin, Haucke, Timm, Stathatos, Suzanne, Deng, Siqi, Young, Erik, Perona, Pietro, Beery, Sara, Van Horn, Grant
Object detectors often perform poorly on data that differs from their training set. Domain adaptive object detection (DAOD) methods have recently demonstrated strong results on addressing this challenge. Unfortunately, we identify systemic benchmarki
Externí odkaz:
http://arxiv.org/abs/2403.12029
Crowdsourced machine learning on competition platforms such as Kaggle is a popular and often effective method for generating accurate models. Typically, teams vie for the most accurate model, as measured by overall error on a holdout set, and it is c
Externí odkaz:
http://arxiv.org/abs/2402.10795
High-resolution semantic segmentation requires substantial computational resources. Traditional approaches in the field typically downscale the input images before processing and then upscale the low-resolution outputs back to their original dimensio
Externí odkaz:
http://arxiv.org/abs/2402.05398
Autor:
Israel, Uriah, Marks, Markus, Dilip, Rohit, Li, Qilin, Schwartz, Morgan, Pradhan, Elora, Pao, Edward, Li, Shenyi, Pearson-Goulart, Alexander, Perona, Pietro, Gkioxari, Georgia, Barnowski, Ross, Yue, Yisong, Van Valen, David
Cells are the fundamental unit of biological organization, and identifying them in imaging data - cell segmentation - is a critical task for various cellular imaging experiments. While deep learning methods have led to substantial progress on this pr
Externí odkaz:
http://arxiv.org/abs/2311.11004