SYNTOLOGY HomeExplorerAtlasCodeMethodologyAboutDevelopersFeedPricing
Paper · 2407.15913 · 2024

Test-Time Low Rank Adaptation via Confidence Maximization for Zero-Shot Generalization of Vision-Language Models

arXiv · PDF · Open in the Atlas

Code that ran

We lifted 3 functions out of this paper's own repositories and ran 3 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
razaimam45/ttl-test-time-low-rank-adaptation canonical 2 of 2
copy not recorded — 1 of 1
FunctionStatusWhere it lives
list_of_ints Ran razaimam45/ttl-test-time-low-rank-adaptation/ttl.py
pointer only (licence: NONE) · get_code("7d1ac1a66da5f14c")
quartile_selection Ran razaimam45/ttl-test-time-low-rank-adaptation/ttl.py
pointer only (licence: NONE) · get_code("f9631d6340877fe9")
select_confident_samples Ran this paper's copy was not recorded; identical code first harvested from azshue/TPT
pointer only · get_code("3ce4d11e58de02ad")

Repositories linked to this paper

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

Abstract

The conventional modus operandi for adapting pre-trained vision-language models (VLMs) during test-time involves tuning learnable prompts, ie, test-time prompt tuning. This paper introduces Test-Time Low-rank adaptation (TTL) as an alternative to prompt tuning for zero-shot generalization of large-scale VLMs. Taking inspiration from recent advancements in efficiently fine-tuning large language models, TTL offers a test-time parameter-efficient adaptation approach that updates the attention weights of the transformer encoder by maximizing prediction confidence. The self-supervised confidence maximization objective is specified using a weighted entropy loss that enforces consistency among predictions of augmented samples. TTL introduces only a small amount of trainable parameters for low-rank adapters in the model space while keeping the prompts and backbone frozen. Extensive experiments on a variety of natural distribution and cross-domain tasks show that TTL can outperform other techniques for test-time optimization of VLMs in strict zero-shot settings. Specifically, TTL outperforms test-time prompt tuning baselines with a significant improvement on average. Our code is available at at https://github.com/Razaimam45/TTL-Test-Time-Low-Rank-Adaptation.

For agents

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

get_harvested_code_for_paper("2407.15913")
get_code_for_paper("2407.15913")
have("2407.15913")

Connect an agent — have() is free.