Article
Fine-Tuning MetaCLIP-2 for Image Classification on Downstream Tasks
ā¢
4
Dmitry Ryumin
DmitryRyumin
AI & ML interests
Machine Learning and Applications, Multi-Modal Understanding
Recent Activity
upvoted
an
article
17 days ago
Fine-Tuning MetaCLIP-2 for Image Classification on Downstream Tasks
reacted
to
prithivMLmods's
post
with š
17 days ago
Made a small write up and experimental finetuning guide for MetaCLIP2 for Image Classification on Downstream Tasks. The blog titled `Fine Tuning MetaCLIP 2 for Image Classification on Downstream Tasks` demonstrates the step by step finetuning using CIFAR10 and is also flexible for adapting to other datasets. For more details, check out the linked blog below. š¤āļø
ā® Blog Article: https://huggingface.co/blog/prithivMLmods/metaclip2-downstream-finetune
ā® Demo Space[Zero-Shot Classification]: https://huggingface.co/spaces/prithivMLmods/metaclip-2-demo
Some other models
ā°āŗ MetaCLIP-2-Cifar10: https://huggingface.co/prithivMLmods/MetaCLIP-2-Cifar10
ā°āŗ MetaCLIP-2-Age-Range-Estimator: https://huggingface.co/prithivMLmods/MetaCLIP-2-Age-Range-Estimator
ā°āŗ MetaCLIP-2-Gender-Identifier: https://huggingface.co/prithivMLmods/MetaCLIP-2-Gender-Identifier
ā°āŗ MetaCLIP-2-Open-Scene: https://huggingface.co/prithivMLmods/MetaCLIP-2-Open-Scene
ā® Collection: https://huggingface.co/collections/prithivMLmods/metaclip2-image-classification-experiments
To know more about it, visit the app page or the respective model page!
reacted
to
prithivMLmods's
post
with š
17 days ago
Made a small write up and experimental finetuning guide for MetaCLIP2 for Image Classification on Downstream Tasks. The blog titled `Fine Tuning MetaCLIP 2 for Image Classification on Downstream Tasks` demonstrates the step by step finetuning using CIFAR10 and is also flexible for adapting to other datasets. For more details, check out the linked blog below. š¤āļø
ā® Blog Article: https://huggingface.co/blog/prithivMLmods/metaclip2-downstream-finetune
ā® Demo Space[Zero-Shot Classification]: https://huggingface.co/spaces/prithivMLmods/metaclip-2-demo
Some other models
ā°āŗ MetaCLIP-2-Cifar10: https://huggingface.co/prithivMLmods/MetaCLIP-2-Cifar10
ā°āŗ MetaCLIP-2-Age-Range-Estimator: https://huggingface.co/prithivMLmods/MetaCLIP-2-Age-Range-Estimator
ā°āŗ MetaCLIP-2-Gender-Identifier: https://huggingface.co/prithivMLmods/MetaCLIP-2-Gender-Identifier
ā°āŗ MetaCLIP-2-Open-Scene: https://huggingface.co/prithivMLmods/MetaCLIP-2-Open-Scene
ā® Collection: https://huggingface.co/collections/prithivMLmods/metaclip2-image-classification-experiments
To know more about it, visit the app page or the respective model page!
Organizations
upvoted
an
article
17 days ago
reacted to
prithivMLmods's
post with ššā¤ļøš¤
17 days ago
Post
3723
Made a small write up and experimental finetuning guide for MetaCLIP2 for Image Classification on Downstream Tasks. The blog titled
ā® Blog Article: https://huggingface.co/blog/prithivMLmods/metaclip2-downstream-finetune
ā® Demo Space[Zero-Shot Classification]: prithivMLmods/metaclip-2-demo
Some other models
ā°āŗ MetaCLIP-2-Cifar10: prithivMLmods/MetaCLIP-2-Cifar10
ā°āŗ MetaCLIP-2-Age-Range-Estimator: prithivMLmods/MetaCLIP-2-Age-Range-Estimator
ā°āŗ MetaCLIP-2-Gender-Identifier: prithivMLmods/MetaCLIP-2-Gender-Identifier
ā°āŗ MetaCLIP-2-Open-Scene: prithivMLmods/MetaCLIP-2-Open-Scene
ā® Collection: https://huggingface.co/collections/prithivMLmods/metaclip2-image-classification-experiments
To know more about it, visit the app page or the respective model page!
Fine Tuning MetaCLIP 2 for Image Classification on Downstream Tasks demonstrates the step by step finetuning using CIFAR10 and is also flexible for adapting to other datasets. For more details, check out the linked blog below. š¤āļøā® Blog Article: https://huggingface.co/blog/prithivMLmods/metaclip2-downstream-finetune
ā® Demo Space[Zero-Shot Classification]: prithivMLmods/metaclip-2-demo
Some other models
ā°āŗ MetaCLIP-2-Cifar10: prithivMLmods/MetaCLIP-2-Cifar10
ā°āŗ MetaCLIP-2-Age-Range-Estimator: prithivMLmods/MetaCLIP-2-Age-Range-Estimator
ā°āŗ MetaCLIP-2-Gender-Identifier: prithivMLmods/MetaCLIP-2-Gender-Identifier
ā°āŗ MetaCLIP-2-Open-Scene: prithivMLmods/MetaCLIP-2-Open-Scene
ā® Collection: https://huggingface.co/collections/prithivMLmods/metaclip2-image-classification-experiments
To know more about it, visit the app page or the respective model page!
liked
a
Space
18 days ago
reacted to
their
post with š„
26 days ago
Post
1208
ššļøš New Research Alert - ICCV 2025 (Poster)! ššļøš
š Title: Is Less More? Exploring Token Condensation as Training-Free Test-Time Adaptation š
š Description: Token Condensation as Adaptation (TCA) improves the performance and efficiency of Vision Language Models in zero-shot inference by introducing domain anchor tokens.
š„ Authors: Zixin Wang, Dong Gong, Sen Wang, Zi Huang, Yadan Luo
š Conference: ICCV, 19 ā 23 Oct, 2025 | Honolulu, Hawai'i, USA šŗšø
š Paper: Is Less More? Exploring Token Condensation as Training-free Test-time Adaptation (2410.14729)
š Repository: https://github.com/Jo-wang/TCA
š ICCV-2023-25-Papers: https://github.com/DmitryRyumin/ICCV-2023-25-Papers
š Added to the Session 1: https://github.com/DmitryRyumin/ICCV-2023-25-Papers/blob/main/sections/2025/main/session-1.md
š More Papers: more cutting-edge research presented at other conferences in the DmitryRyumin/NewEraAI-Papers curated by @DmitryRyumin
š Keywords: #TestTimeAdaptation #TokenCondensation #VisionLanguageModels #TrainingFreeAdaptation #ZeroShotLearning #EfficientAI #AI #ICCV2025 #ResearchHighlight
š Title: Is Less More? Exploring Token Condensation as Training-Free Test-Time Adaptation š
š Description: Token Condensation as Adaptation (TCA) improves the performance and efficiency of Vision Language Models in zero-shot inference by introducing domain anchor tokens.
š„ Authors: Zixin Wang, Dong Gong, Sen Wang, Zi Huang, Yadan Luo
š Conference: ICCV, 19 ā 23 Oct, 2025 | Honolulu, Hawai'i, USA šŗšø
š Paper: Is Less More? Exploring Token Condensation as Training-free Test-time Adaptation (2410.14729)
š Repository: https://github.com/Jo-wang/TCA
š ICCV-2023-25-Papers: https://github.com/DmitryRyumin/ICCV-2023-25-Papers
š Added to the Session 1: https://github.com/DmitryRyumin/ICCV-2023-25-Papers/blob/main/sections/2025/main/session-1.md
š More Papers: more cutting-edge research presented at other conferences in the DmitryRyumin/NewEraAI-Papers curated by @DmitryRyumin
š Keywords: #TestTimeAdaptation #TokenCondensation #VisionLanguageModels #TrainingFreeAdaptation #ZeroShotLearning #EfficientAI #AI #ICCV2025 #ResearchHighlight
posted
an
update
26 days ago
Post
1208
ššļøš New Research Alert - ICCV 2025 (Poster)! ššļøš
š Title: Is Less More? Exploring Token Condensation as Training-Free Test-Time Adaptation š
š Description: Token Condensation as Adaptation (TCA) improves the performance and efficiency of Vision Language Models in zero-shot inference by introducing domain anchor tokens.
š„ Authors: Zixin Wang, Dong Gong, Sen Wang, Zi Huang, Yadan Luo
š Conference: ICCV, 19 ā 23 Oct, 2025 | Honolulu, Hawai'i, USA šŗšø
š Paper: Is Less More? Exploring Token Condensation as Training-free Test-time Adaptation (2410.14729)
š Repository: https://github.com/Jo-wang/TCA
š ICCV-2023-25-Papers: https://github.com/DmitryRyumin/ICCV-2023-25-Papers
š Added to the Session 1: https://github.com/DmitryRyumin/ICCV-2023-25-Papers/blob/main/sections/2025/main/session-1.md
š More Papers: more cutting-edge research presented at other conferences in the DmitryRyumin/NewEraAI-Papers curated by @DmitryRyumin
š Keywords: #TestTimeAdaptation #TokenCondensation #VisionLanguageModels #TrainingFreeAdaptation #ZeroShotLearning #EfficientAI #AI #ICCV2025 #ResearchHighlight
š Title: Is Less More? Exploring Token Condensation as Training-Free Test-Time Adaptation š
š Description: Token Condensation as Adaptation (TCA) improves the performance and efficiency of Vision Language Models in zero-shot inference by introducing domain anchor tokens.
š„ Authors: Zixin Wang, Dong Gong, Sen Wang, Zi Huang, Yadan Luo
š Conference: ICCV, 19 ā 23 Oct, 2025 | Honolulu, Hawai'i, USA šŗšø
š Paper: Is Less More? Exploring Token Condensation as Training-free Test-time Adaptation (2410.14729)
š Repository: https://github.com/Jo-wang/TCA
š ICCV-2023-25-Papers: https://github.com/DmitryRyumin/ICCV-2023-25-Papers
š Added to the Session 1: https://github.com/DmitryRyumin/ICCV-2023-25-Papers/blob/main/sections/2025/main/session-1.md
š More Papers: more cutting-edge research presented at other conferences in the DmitryRyumin/NewEraAI-Papers curated by @DmitryRyumin
š Keywords: #TestTimeAdaptation #TokenCondensation #VisionLanguageModels #TrainingFreeAdaptation #ZeroShotLearning #EfficientAI #AI #ICCV2025 #ResearchHighlight
upvoted
a
paper
26 days ago
liked
a
dataset
27 days ago
liked
a
model
27 days ago
reacted to
their
post with š
29 days ago
Post
2361
ššļøš New Research Alert - ICCV 2025 (Oral)! ššļøš
š Title: Diving into the Fusion of Monocular Priors for Generalized Stereo Matching š
š Description: The proposed method enhances stereo matching by efficiently combining unbiased monocular priors from vision foundation models. This method addresses misalignment and local optima issues using a binary local ordering map and pixel-wise linear regression.
š„ Authors: Chengtang Yao, Lidong Yu, Zhidan Liu, Jiaxi Zeng, Yuwei Wu, and Yunde Jia
š Conference: ICCV, 19 ā 23 Oct, 2025 | Honolulu, Hawai'i, USA šŗšø
š Paper: Diving into the Fusion of Monocular Priors for Generalized Stereo Matching (2505.14414)
š Repository: https://github.com/YaoChengTang/Diving-into-the-Fusion-of-Monocular-Priors-for-Generalized-Stereo-Matching
š ICCV-2023-25-Papers: https://github.com/DmitryRyumin/ICCV-2023-25-Papers
š Added to the 3D Pose Understanding Section: https://github.com/DmitryRyumin/ICCV-2023-25-Papers/blob/main/sections/2025/main/3d-pose-understanding.md
š More Papers: more cutting-edge research presented at other conferences in the DmitryRyumin/NewEraAI-Papers curated by @DmitryRyumin
š Keywords: #StereoMatching #MonocularDepth #VisionFoundationModels #3DReconstruction #Generalization #AI #ICCV2025 #ResearchHighlight
š Title: Diving into the Fusion of Monocular Priors for Generalized Stereo Matching š
š Description: The proposed method enhances stereo matching by efficiently combining unbiased monocular priors from vision foundation models. This method addresses misalignment and local optima issues using a binary local ordering map and pixel-wise linear regression.
š„ Authors: Chengtang Yao, Lidong Yu, Zhidan Liu, Jiaxi Zeng, Yuwei Wu, and Yunde Jia
š Conference: ICCV, 19 ā 23 Oct, 2025 | Honolulu, Hawai'i, USA šŗšø
š Paper: Diving into the Fusion of Monocular Priors for Generalized Stereo Matching (2505.14414)
š Repository: https://github.com/YaoChengTang/Diving-into-the-Fusion-of-Monocular-Priors-for-Generalized-Stereo-Matching
š ICCV-2023-25-Papers: https://github.com/DmitryRyumin/ICCV-2023-25-Papers
š Added to the 3D Pose Understanding Section: https://github.com/DmitryRyumin/ICCV-2023-25-Papers/blob/main/sections/2025/main/3d-pose-understanding.md
š More Papers: more cutting-edge research presented at other conferences in the DmitryRyumin/NewEraAI-Papers curated by @DmitryRyumin
š Keywords: #StereoMatching #MonocularDepth #VisionFoundationModels #3DReconstruction #Generalization #AI #ICCV2025 #ResearchHighlight
posted
an
update
29 days ago
Post
2361
ššļøš New Research Alert - ICCV 2025 (Oral)! ššļøš
š Title: Diving into the Fusion of Monocular Priors for Generalized Stereo Matching š
š Description: The proposed method enhances stereo matching by efficiently combining unbiased monocular priors from vision foundation models. This method addresses misalignment and local optima issues using a binary local ordering map and pixel-wise linear regression.
š„ Authors: Chengtang Yao, Lidong Yu, Zhidan Liu, Jiaxi Zeng, Yuwei Wu, and Yunde Jia
š Conference: ICCV, 19 ā 23 Oct, 2025 | Honolulu, Hawai'i, USA šŗšø
š Paper: Diving into the Fusion of Monocular Priors for Generalized Stereo Matching (2505.14414)
š Repository: https://github.com/YaoChengTang/Diving-into-the-Fusion-of-Monocular-Priors-for-Generalized-Stereo-Matching
š ICCV-2023-25-Papers: https://github.com/DmitryRyumin/ICCV-2023-25-Papers
š Added to the 3D Pose Understanding Section: https://github.com/DmitryRyumin/ICCV-2023-25-Papers/blob/main/sections/2025/main/3d-pose-understanding.md
š More Papers: more cutting-edge research presented at other conferences in the DmitryRyumin/NewEraAI-Papers curated by @DmitryRyumin
š Keywords: #StereoMatching #MonocularDepth #VisionFoundationModels #3DReconstruction #Generalization #AI #ICCV2025 #ResearchHighlight
š Title: Diving into the Fusion of Monocular Priors for Generalized Stereo Matching š
š Description: The proposed method enhances stereo matching by efficiently combining unbiased monocular priors from vision foundation models. This method addresses misalignment and local optima issues using a binary local ordering map and pixel-wise linear regression.
š„ Authors: Chengtang Yao, Lidong Yu, Zhidan Liu, Jiaxi Zeng, Yuwei Wu, and Yunde Jia
š Conference: ICCV, 19 ā 23 Oct, 2025 | Honolulu, Hawai'i, USA šŗšø
š Paper: Diving into the Fusion of Monocular Priors for Generalized Stereo Matching (2505.14414)
š Repository: https://github.com/YaoChengTang/Diving-into-the-Fusion-of-Monocular-Priors-for-Generalized-Stereo-Matching
š ICCV-2023-25-Papers: https://github.com/DmitryRyumin/ICCV-2023-25-Papers
š Added to the 3D Pose Understanding Section: https://github.com/DmitryRyumin/ICCV-2023-25-Papers/blob/main/sections/2025/main/3d-pose-understanding.md
š More Papers: more cutting-edge research presented at other conferences in the DmitryRyumin/NewEraAI-Papers curated by @DmitryRyumin
š Keywords: #StereoMatching #MonocularDepth #VisionFoundationModels #3DReconstruction #Generalization #AI #ICCV2025 #ResearchHighlight
reacted to
their
post with š¤š„
about 1 month ago
Post
2826
ššš New Research Alert - ICCV 2025 (Oral)! šš¤š
š Title: Understanding Co-speech Gestures in-the-wild š
š Description: JEGAL is a tri-modal model that learns from gestures, speech and text simultaneously, enabling devices to interpret co-speech gestures in the wild.
š„ Authors: @sindhuhegde , K R Prajwal, Taein Kwon, and Andrew Zisserman
š Conference: ICCV, 19 ā 23 Oct, 2025 | Honolulu, Hawai'i, USA šŗšø
š Paper: Understanding Co-speech Gestures in-the-wild (2503.22668)
š Web Page: https://www.robots.ox.ac.uk/~vgg/research/jegal
š Repository: https://github.com/Sindhu-Hegde/jegal
šŗ Video: https://www.youtube.com/watch?v=TYFOLKfM-rM
š ICCV-2023-25-Papers: https://github.com/DmitryRyumin/ICCV-2023-25-Papers
š Added to the Human Modeling Section: https://github.com/DmitryRyumin/ICCV-2023-25-Papers/blob/main/sections/2025/main/human-modeling.md
š More Papers: more cutting-edge research presented at other conferences in the DmitryRyumin/NewEraAI-Papers curated by @DmitryRyumin
š Keywords: #CoSpeechGestures #GestureUnderstanding #TriModalRepresentation #MultimodalLearning #AI #ICCV2025 #ResearchHighlight
š Title: Understanding Co-speech Gestures in-the-wild š
š Description: JEGAL is a tri-modal model that learns from gestures, speech and text simultaneously, enabling devices to interpret co-speech gestures in the wild.
š„ Authors: @sindhuhegde , K R Prajwal, Taein Kwon, and Andrew Zisserman
š Conference: ICCV, 19 ā 23 Oct, 2025 | Honolulu, Hawai'i, USA šŗšø
š Paper: Understanding Co-speech Gestures in-the-wild (2503.22668)
š Web Page: https://www.robots.ox.ac.uk/~vgg/research/jegal
š Repository: https://github.com/Sindhu-Hegde/jegal
šŗ Video: https://www.youtube.com/watch?v=TYFOLKfM-rM
š ICCV-2023-25-Papers: https://github.com/DmitryRyumin/ICCV-2023-25-Papers
š Added to the Human Modeling Section: https://github.com/DmitryRyumin/ICCV-2023-25-Papers/blob/main/sections/2025/main/human-modeling.md
š More Papers: more cutting-edge research presented at other conferences in the DmitryRyumin/NewEraAI-Papers curated by @DmitryRyumin
š Keywords: #CoSpeechGestures #GestureUnderstanding #TriModalRepresentation #MultimodalLearning #AI #ICCV2025 #ResearchHighlight
posted
an
update
about 1 month ago
Post
2826
ššš New Research Alert - ICCV 2025 (Oral)! šš¤š
š Title: Understanding Co-speech Gestures in-the-wild š
š Description: JEGAL is a tri-modal model that learns from gestures, speech and text simultaneously, enabling devices to interpret co-speech gestures in the wild.
š„ Authors: @sindhuhegde , K R Prajwal, Taein Kwon, and Andrew Zisserman
š Conference: ICCV, 19 ā 23 Oct, 2025 | Honolulu, Hawai'i, USA šŗšø
š Paper: Understanding Co-speech Gestures in-the-wild (2503.22668)
š Web Page: https://www.robots.ox.ac.uk/~vgg/research/jegal
š Repository: https://github.com/Sindhu-Hegde/jegal
šŗ Video: https://www.youtube.com/watch?v=TYFOLKfM-rM
š ICCV-2023-25-Papers: https://github.com/DmitryRyumin/ICCV-2023-25-Papers
š Added to the Human Modeling Section: https://github.com/DmitryRyumin/ICCV-2023-25-Papers/blob/main/sections/2025/main/human-modeling.md
š More Papers: more cutting-edge research presented at other conferences in the DmitryRyumin/NewEraAI-Papers curated by @DmitryRyumin
š Keywords: #CoSpeechGestures #GestureUnderstanding #TriModalRepresentation #MultimodalLearning #AI #ICCV2025 #ResearchHighlight
š Title: Understanding Co-speech Gestures in-the-wild š
š Description: JEGAL is a tri-modal model that learns from gestures, speech and text simultaneously, enabling devices to interpret co-speech gestures in the wild.
š„ Authors: @sindhuhegde , K R Prajwal, Taein Kwon, and Andrew Zisserman
š Conference: ICCV, 19 ā 23 Oct, 2025 | Honolulu, Hawai'i, USA šŗšø
š Paper: Understanding Co-speech Gestures in-the-wild (2503.22668)
š Web Page: https://www.robots.ox.ac.uk/~vgg/research/jegal
š Repository: https://github.com/Sindhu-Hegde/jegal
šŗ Video: https://www.youtube.com/watch?v=TYFOLKfM-rM
š ICCV-2023-25-Papers: https://github.com/DmitryRyumin/ICCV-2023-25-Papers
š Added to the Human Modeling Section: https://github.com/DmitryRyumin/ICCV-2023-25-Papers/blob/main/sections/2025/main/human-modeling.md
š More Papers: more cutting-edge research presented at other conferences in the DmitryRyumin/NewEraAI-Papers curated by @DmitryRyumin
š Keywords: #CoSpeechGestures #GestureUnderstanding #TriModalRepresentation #MultimodalLearning #AI #ICCV2025 #ResearchHighlight
liked
a
Space
about 1 month ago
upvoted
3
papers
about 1 month ago
SelectMix: Enhancing Label Noise Robustness through Targeted Sample Mixing
Paper
ā¢
2509.11265
ā¢
Published
ā¢
1
Intra-Cluster Mixup: An Effective Data Augmentation Technique for Complementary-Label Learning
Paper
ā¢
2509.17971
ā¢
Published
ā¢
1
Tongyi DeepResearch Technical Report
Paper
ā¢
2510.24701
ā¢
Published
ā¢
95