facebookresearch / taskmodularnets
A set of neural network modules, which are small fully connected layers operating in semantic concept space. These modules are configured through a gating function conditioned on the task to produce features representing the compatibility between the input image and the concept under consideration.
☆58Updated 3 years ago
Alternatives and similar repositories for taskmodularnets:
Users that are interested in taskmodularnets are comparing it to the libraries listed below
- Attribute-Object Visual Composition using Attributes as Operators☆65Updated 2 years ago
- models and tools for -What makes ImageNet good for Transfer Learning?☆25Updated 7 years ago
- Learning Long-term Visual Dynamics with Region Proposal Interaction Networks (ICLR 2021)☆112Updated 2 years ago
- RareAct: A video dataset of unusual interactions☆32Updated 4 years ago
- CATER: A diagnostic dataset for Compositional Actions and TEmporal Reasoning☆103Updated 4 years ago
- Video Noise Contrastive Estimation☆66Updated last year
- PyTorch implementation of paper "Visual Concept-Metaconcept Learner", NeruIPS 2019☆48Updated 5 years ago
- Code for Learning to Learn Language from Narrated Video☆33Updated last year
- ☆11Updated 7 years ago
- ☆19Updated 2 years ago
- Code for reproducing experiments in "How Useful is Self-Supervised Pretraining for Visual Tasks?"☆60Updated 6 months ago
- Code release for Hu et al., Explainable Neural Computation via Stack Neural Module Networks. in ECCV, 2018☆71Updated 5 years ago
- A simple but well-performing "single-hop" visual attention model for the GQA dataset☆20Updated 5 years ago
- ☆88Updated 3 years ago
- sidetuning.berkeley.edu☆68Updated last year
- Shaping Visual Representations with Language for Few-shot Classification, ACL 2020☆16Updated 3 years ago
- VQS: Linking Segmentations to Questions and Answers for Supervised Attention in VQA and Question-Focused Semantic Segmentation☆22Updated 7 years ago
- This repo contains the pytorch implementation for Dynamic Concept Learner (accepted by ICLR 2021).☆37Updated 7 months ago
- Code for the paper "Marginalized Average Attentional Network for Weakly-Supervised Learning" (ICLR 2019)☆34Updated 5 years ago
- Official code for paper Context-aware Zero-shot Recognition (https://arxiv.org/abs/1904.09320 to appear at AAAI2020)☆58Updated 5 years ago
- ☆40Updated last year
- An unofficial PyTorch implementation of the HAN and AdaHAN models presented in the "Learning Visual Question Answering by Bootstrapping H…☆54Updated 6 years ago
- For replication of the experiments in the paper Learning Robust Representations by Projecting Superficial Statistics Out☆13Updated 5 years ago
- Code for CVPR'18 "Grounding Referring Expressions in Images by Variational Context"☆29Updated 6 years ago
- An implementation of the MONet model for unsupervised scene decomposition in PyTorch☆58Updated 2 years ago
- Measuring compositionality in representation learning☆72Updated 5 years ago
- dataset cleansing for Visual Genome☆30Updated 7 years ago
- Official implementation of ICCV19 oral paper Zero-Shot grounding of Objects from Natural Language Queries (https://arxiv.org/abs/1908.071…☆69Updated 4 years ago
- Scene Graph Prediction with Limited Labels☆54Updated last year
- Code for the Paper "Restricting the Flow: Information Bottlenecks for Attribution"☆76Updated 4 years ago