SYNTOLOGY HomeExplorerAtlasCodeMethodologyAboutDevelopersFeedPricing
Paper · 1912.08226 · 2019

Meshed-Memory Transformer for Image Captioning

arXiv · PDF · Open in the Atlas

Code that ran

We lifted 8 functions out of this paper's own repositories and ran 6 of them in a sandbox. "Ran" means the function executed on a synthesized input and returned a value. It is not a reproduction of the paper's results.

RepositoryRoleRan
aimagelab/meshed-memory-transformer canonical 6 of 8
FunctionStatusWhere it lives
cook_refs Ran aimagelab/meshed-memory-transformer/evaluation/cider/cider_scorer.py
code served (permissive licence) · get_code("26e17b0aeb64b34c")
cook_test Ran aimagelab/meshed-memory-transformer/evaluation/bleu/bleu_scorer.py
code served (permissive licence) · get_code("f5741ff28f6cb706")
cook_test Ran aimagelab/meshed-memory-transformer/evaluation/cider/cider_scorer.py
code served (permissive licence) · get_code("7cb89de9e327ddab")
position_embedding Ran aimagelab/meshed-memory-transformer/models/transformer/utils.py
code served (permissive licence) · get_code("e344c95038ed76fd")
precook Ran aimagelab/meshed-memory-transformer/evaluation/bleu/bleu_scorer.py
code served (permissive licence) · get_code("ec4448373d72d636")
sinusoid_encoding_table Ran aimagelab/meshed-memory-transformer/models/transformer/utils.py
code served (permissive licence) · get_code("35fbc756acf92321")
cook_refs Not yet run aimagelab/meshed-memory-transformer/evaluation/bleu/bleu_scorer.py
code served (permissive licence) · get_code("7586e1d32f7325f7")
precook Not yet run aimagelab/meshed-memory-transformer/evaluation/cider/cider_scorer.py
code served (permissive licence) · get_code("ca007f4b8a45fbdc")

Repositories linked to this paper

Some links come from the archived Papers with Code dataset (CC BY-SA 4.0): attribution and licence.

Abstract

Transformer-based architectures represent the state of the art in sequence modeling tasks like machine translation and language understanding. Their applicability to multi-modal contexts like image captioning, however, is still largely under-explored. With the aim of filling this gap, we present M$^2$ - a Meshed Transformer with Memory for Image Captioning. The architecture improves both the image encoding and the language generation steps: it learns a multi-level representation of the relationships between image regions integrating learned a priori knowledge, and uses a mesh-like connectivity at decoding stage to exploit low- and high-level features. Experimentally, we investigate the performance of the M$^2$ Transformer and different fully-attentive models in comparison with recurrent ones. When tested on COCO, our proposal achieves a new state of the art in single-model and ensemble configurations on the "Karpathy" test split and on the online test server. We also assess its performances when describing objects unseen in the training set. Trained models and code for reproducing the experiments are publicly available at: https://github.com/aimagelab/meshed-memory-transformer.

For agents

The same record, over MCP at https://syntology.ai/mcp:

get_harvested_code_for_paper("1912.08226")
get_code_for_paper("1912.08226")
have("1912.08226")

Connect an agent — have() is free.