ViperGPT generates executable Python code to compose pre-trained vision-and-language modules into programs that answer visual queries, reaching state-of-the-art results with no additional training.
Selvaraju and Abhishek Das and Ramakrishna Vedantam and Michael Cogswell and Devi Parikh and Dhruv Batra , title =
6 Pith papers cite this work. Polarity classification is still indexing.
6
Pith papers citing it
representative citing papers
Adding register tokens to Vision Transformers eliminates high-norm background artifacts and raises state-of-the-art performance on dense visual prediction tasks.
Inpainting auxiliary task improves clustering of embeddings for individual zebrafish identification based on skin patterns.
E-PCN reaches 94.67% macro-accuracy on 10-class jet tagging by weighting graphs with angular separation, transverse momentum, momentum fraction, and invariant mass, with Grad-CAM showing the first two account for 76% of decisions and yielding gains over baseline PCN.
Shapley value and variational importance switch methods produce consistent rankings of filter importance in CNNs, enabling compression and interpretability.
Transfer learning with a Zoobot CNN on SDSS DR18 data identifies 3,679 lopsided spiral galaxies at 87% test accuracy, with lopsided systems showing higher star formation, bluer colors, lower mass and concentration.
citing papers explorer
-
ViperGPT: Visual Inference via Python Execution for Reasoning
ViperGPT generates executable Python code to compose pre-trained vision-and-language modules into programs that answer visual queries, reaching state-of-the-art results with no additional training.
-
Vision Transformers Need Registers
Adding register tokens to Vision Transformers eliminates high-norm background artifacts and raises state-of-the-art performance on dense visual prediction tasks.
-
Exploring Clustering Capability of Inpainting Model Embeddings for Pattern-based Individual Identification
Inpainting auxiliary task improves clustering of embeddings for individual zebrafish identification based on skin patterns.
-
E-PCN: Jet Tagging with Explainable Particle Chebyshev Networks Using Kinematic Features
E-PCN reaches 94.67% macro-accuracy on 10-class jet tagging by weighting graphs with angular separation, transverse momentum, momentum fraction, and invariant mass, with Grad-CAM showing the first two account for 76% of decisions and yielding gains over baseline PCN.
-
Neuron ranking -- an informed way to condense convolutional neural networks architecture
Shapley value and variational importance switch methods produce consistent rankings of filter importance in CNNs, enabling compression and interpretability.
-
Identifying lopsidedness in spiral galaxies using a Deep Convolutional Neural Network
Transfer learning with a Zoobot CNN on SDSS DR18 data identifies 3,679 lopsided spiral galaxies at 87% test accuracy, with lopsided systems showing higher star formation, bluer colors, lower mass and concentration.