SYNTOLOGY HomeExplorerAtlasCodeMethodologyAboutDevelopersFeedPricing
Paper · 2312.03046 · 2023

Diversified in-domain synthesis with efficient fine-tuning for few-shot classification

arXiv · PDF · Open in the Atlas

Code that ran

We lifted 6 functions out of this paper's own repositories and ran 5 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
vturrisi/disef canonical 5 of 6
FunctionStatusWhere it lives
accuracy_at_k Ran vturrisi/disef/fine-tune/src/utils/misc.py
code served (permissive licence) · get_code("88ec2296de41023f")
load_image Ran vturrisi/disef/generation/synthetic_augmentation_pipeline.py
code served (permissive licence) · get_code("52321defb194c04d")
omegaconf_select Ran vturrisi/disef/fine-tune/src/utils/misc.py
code served (permissive licence) · get_code("d8123d675f0b86f7")
pad_image Ran vturrisi/disef/generation/synthetic_augmentation_pipeline.py
code served (permissive licence) · get_code("a37d63f7ecc2e5c4")
weighted_mean Ran vturrisi/disef/fine-tune/src/utils/misc.py
code served (permissive licence) · get_code("a00b191edbcbba19")
pil_to_latents Not yet run vturrisi/disef/generation/synthetic_augmentation_pipeline.py
code served (permissive licence) · get_code("c77c4aa4396ed626")

Repositories linked to this paper

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

Abstract

Few-shot image classification aims to learn an image classifier using only a small set of labeled examples per class. A recent research direction for improving few-shot classifiers involves augmenting the labelled samples with synthetic images created by state-of-the-art text-to-image generation models. Following this trend, we propose Diversified In-domain Synthesis with Efficient Fine-tuning (DISEF), a novel approach which addresses the generalization challenge in few-shot learning using synthetic data. DISEF consists of two main components. First, we propose a novel text-to-image augmentation pipeline that, by leveraging the real samples and their rich semantics coming from an advanced captioning model, promotes in-domain sample diversity for better generalization. Second, we emphasize the importance of effective model fine-tuning in few-shot recognition, proposing to use Low-Rank Adaptation (LoRA) for joint adaptation of the text and image encoders in a Vision Language Model. We validate our method in ten different benchmarks, consistently outperforming baselines and establishing a new state-of-the-art for few-shot classification. Code is available at https://github.com/vturrisi/disef.

For agents

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

get_harvested_code_for_paper("2312.03046")
get_code_for_paper("2312.03046")
have("2312.03046")

Connect an agent — have() is free.