Unsupervised Canine Emotion Recognition Using Momentum Contrast
We describe a system for identifying dog emotions based on dogs’ facial expressions and body posture. Towards that goal, we built a dataset with 2184 images of ten popular dog breeds, grouped into seven similarly sized primal mammalian emotion categories defined by neuroscientist and psychobiologist...
| Main Authors: | , , , |
|---|---|
| Other Authors: | |
| Format: | Article |
| Published: |
Multidisciplinary Digital Publishing Institute
2024
|
| Online Access: | https://hdl.handle.net/1721.1/157689 |
| _version_ | 1824458412111429632 |
|---|---|
| author | Bhave, Aarya Hafner, Alina Bhave, Anushka Gloor, Peter A. |
| author2 | System Design and Management Program. |
| author_facet | System Design and Management Program. Bhave, Aarya Hafner, Alina Bhave, Anushka Gloor, Peter A. |
| author_sort | Bhave, Aarya |
| collection | MIT |
| description | We describe a system for identifying dog emotions based on dogs’ facial expressions and body posture. Towards that goal, we built a dataset with 2184 images of ten popular dog breeds, grouped into seven similarly sized primal mammalian emotion categories defined by neuroscientist and psychobiologist Jaak Panksepp as ‘Exploring’, ‘Sadness’, ‘Playing’, ‘Rage’, ‘Fear’, ‘Affectionate’ and ‘Lust’. We modified the contrastive learning framework MoCo (Momentum Contrast for Unsupervised Visual Representation Learning) to train it on our original dataset and achieved an accuracy of 43.2% and a baseline of 14%. We also trained this model on a second publicly available dataset that resulted in an accuracy of 48.46% but had a baseline of 25%. We compared our unsupervised approach with a supervised model based on a ResNet50 architecture. This model, when tested on our dataset with the seven Panksepp labels, resulted in an accuracy of 74.32% |
| first_indexed | 2025-02-19T04:25:28Z |
| format | Article |
| id | mit-1721.1/157689 |
| institution | Massachusetts Institute of Technology |
| last_indexed | 2025-02-19T04:25:28Z |
| publishDate | 2024 |
| publisher | Multidisciplinary Digital Publishing Institute |
| record_format | dspace |
| spelling | mit-1721.1/1576892025-01-12T04:22:45Z Unsupervised Canine Emotion Recognition Using Momentum Contrast Bhave, Aarya Hafner, Alina Bhave, Anushka Gloor, Peter A. System Design and Management Program. We describe a system for identifying dog emotions based on dogs’ facial expressions and body posture. Towards that goal, we built a dataset with 2184 images of ten popular dog breeds, grouped into seven similarly sized primal mammalian emotion categories defined by neuroscientist and psychobiologist Jaak Panksepp as ‘Exploring’, ‘Sadness’, ‘Playing’, ‘Rage’, ‘Fear’, ‘Affectionate’ and ‘Lust’. We modified the contrastive learning framework MoCo (Momentum Contrast for Unsupervised Visual Representation Learning) to train it on our original dataset and achieved an accuracy of 43.2% and a baseline of 14%. We also trained this model on a second publicly available dataset that resulted in an accuracy of 48.46% but had a baseline of 25%. We compared our unsupervised approach with a supervised model based on a ResNet50 architecture. This model, when tested on our dataset with the seven Panksepp labels, resulted in an accuracy of 74.32% 2024-11-27T17:04:53Z 2024-11-27T17:04:53Z 2024-11-16 2024-11-26T17:42:59Z Article http://purl.org/eprint/type/JournalArticle https://hdl.handle.net/1721.1/157689 Bhave, A.; Hafner, A.; Bhave, A.; Gloor, P.A. Unsupervised Canine Emotion Recognition Using Momentum Contrast. Sensors 2024, 24, 7324. PUBLISHER_CC http://dx.doi.org/10.3390/s24227324 Sensors Creative Commons Attribution https://creativecommons.org/licenses/by/4.0/ application/pdf Multidisciplinary Digital Publishing Institute Multidisciplinary Digital Publishing Institute |
| spellingShingle | Bhave, Aarya Hafner, Alina Bhave, Anushka Gloor, Peter A. Unsupervised Canine Emotion Recognition Using Momentum Contrast |
| title | Unsupervised Canine Emotion Recognition Using Momentum Contrast |
| title_full | Unsupervised Canine Emotion Recognition Using Momentum Contrast |
| title_fullStr | Unsupervised Canine Emotion Recognition Using Momentum Contrast |
| title_full_unstemmed | Unsupervised Canine Emotion Recognition Using Momentum Contrast |
| title_short | Unsupervised Canine Emotion Recognition Using Momentum Contrast |
| title_sort | unsupervised canine emotion recognition using momentum contrast |
| url | https://hdl.handle.net/1721.1/157689 |
| work_keys_str_mv | AT bhaveaarya unsupervisedcanineemotionrecognitionusingmomentumcontrast AT hafneralina unsupervisedcanineemotionrecognitionusingmomentumcontrast AT bhaveanushka unsupervisedcanineemotionrecognitionusingmomentumcontrast AT gloorpetera unsupervisedcanineemotionrecognitionusingmomentumcontrast |