SYNTOLOGY HomeExplorerAtlasCodeMethodologyAboutDevelopersFeedPricing
Paper · 2103.08784 · NAACL · 2021

LightningDOT: Pre-training Visual-Semantic Embeddings for Real-Time Image-Text Retrieval

Yen-Chun Chen, Linjie Li, Jingjing Liu, Shuohang Wang, Siqi Sun, Yuwei Fang

arXiv · PDF · Open in the Atlas

Code that ran

1 of 1 samples (functions and classes) lifted from this paper's linked repositories executed on a synthesized input in Syntology's jail (0 of them constructed an object rather than computing a result; 0 honoured the contract we drafted, 0 violated it and 1 has no contract verdict; 0 failures of our instrument; 0 no recorded run), measured 2026-11-21; repository links from the Papers with Code archive attributed under CC BY-SA, no affiliation; bodies inline only under a permissive licence as GitHub detects it. Not a reproduction of the paper's results.

"Ran" means the function executed on a synthesized input and returned a value. It is not a reproduction of the paper's results. This record, dated, as JSON: /api/ran/2103.08784.json · badge: /api/ran/2103.08784.svg

Each repository's role is a label: a classifier's output recorded on the link, or, where no role is recorded, what the Papers with Code archive marked. The line under it names its basis. Neither says who wrote the code.

RepositoryRoleRan
towhee-io/towhee community
Papers with Code archive
1 ran · 0 no recorded run
FunctionStatusWhere it lives
BiEncoder Ran
ran on a synthesized input
towhee-io/towhee/towhee/models/lightning_dot/bi_encoder.py
code served (permissive licence) · get_code("b1d2979560699a3e")
How it ran

Ran in Syntology's sandbox on this synthesized input (drafted by a language model, class construct-then-call prompt, model not recorded) and returned tuple. The image it ran in was not recorded. If your copy returns the same type on these inputs, it matched what we observed; nothing here checks that. It does NOT mean the output is correct: nothing has compared it to the paper.

import torch
import torch.nn as nn
from typing import Any

# Mock encoder classes
class MockUniterEncoder(nn.Module):
    def __init__(self, hidden_size=8, project_dim=0):
        super().__init__()
        self.hidden_size = hidden_size
        self.project_dim = project_dim
        self.encoder = nn.Linear(hidden_size, hidden_size)
        if project_dim > 0:
            self.projection = nn.Linear(hidden_size, project_dim)
        
    @classmethod
    def init_encoder(cls, config, checkpoint_path=None, project_dim=0):
        return cls(hidden_size=8, project_dim=project_dim)
    
    def forward(self, input_ids, attention_mask, position_ids, img_feat, img_pos_feat, img_masks, gather_index):
        batch_size = 2
        seq_len = 5
        hidden_size = self.project_dim if self.project_dim > 0 else self.hidden_size
        
        sequence_output = torch.randn(batch_size, seq_len, hidden_size)
        pooled_output = torch.randn(batch_size, hidden_size)
        hidden_states = None
        
        return sequence_output, pooled_output, hidden_states

class MockBertEncoder(nn.Module):
    def __init__(self, hidden_size=8, project_dim=0):
        super().__init__()
        self.hidden_size = hidden_size
        self.project_dim = project_dim
        self.encoder = nn.Linear(hidden_size, hidden_size)
        if project_dim > 0:
            self.projection = nn.Linear(hidden_size, project_dim)
        
    @classmethod
    def init_encoder(cls, config, checkpoint_path=None, project_dim=0):
        return cls(hidden_size=8, project_dim=project_dim)
    
    def forward(self, input_ids, attention_mask, position_ids, img_feat, img_pos_feat, img_masks, gather_index):
        batch_size = 2
        seq_len = 5
        hidden_size = self.project_dim if self.project_dim > 0 else self.hidden_size
        
        sequence_output = torch.randn(batch_size, seq_len, hidden_size)
        pooled_output = torch.randn(batch_size, hidden_size)
        hidden_states = None
        
        return sequence_output, pooled_output, hidden_states

# Mock args object
class MockArgs:
    def __init__(self):
        self.img_model_type = 'uniter-base'
        self.img_model_config = 'config_img'
        self.img_checkpoint = None
        self.txt_model_type = 'bert-base'
        self.txt_model_config = 'config_txt'
        self.txt_checkpoint = None

args = MockArgs()

INIT_ARGS = {
    'UniterEncoder': MockUniterEncoder,
    'BertEncoder': MockBertEncoder,
    'args': args,
    'fix_img_encoder': False,
    'fix_txt_encoder': False,
    'project_dim': 6
}

# Create batch data
batch_size = 2
seq_len = 5
vocab_size = 100
img_feat_dim = 7
img_pos_dim = 4

batch = {
    'txts': {
        'input_ids': torch.randint(0, vocab_size, (batch_size, seq_len)),
        'attention_mask': torch.ones(batch_size, seq_len),
        'position_ids': torch.arange(seq_len).unsqueeze(0).expand(batch_size, -1),
        'img_feat': torch.randn(batch_size, 3, img_feat_dim),
        'img_pos_feat': torch.randn(batch_size, 3, img_pos_dim),
        'img_masks': torch.ones(batch_size, 3),
        'gather_index': None
    },
    'imgs': {
        'input_ids': torch.randint(0, vocab_size, (batch_size, seq_len)),
        'attention_mask': torch.ones(batch_size, seq_len),
        'position_ids': torch.arange(seq_len).unsqueeze(0).expand(batch_size, -1),
        'img_feat': torch.randn(batch_size, 3, img_feat_dim),
        'img_pos_feat': torch.randn(batch_size, 3, img_pos_dim),
        'img_masks': torch.ones(batch_size, 3),
        'gather_index': None
    },
    'caps': {
        'input_ids': torch.randint(0, vocab_size, (batch_size, seq_len)),
        'attention_mask': torch.ones(batch_size, seq_len),
        'position_ids': torch.arange(seq_len).unsqueeze(0).expand(batch_size, -1),
        'img_feat': torch.randn(batch_size, 3, img_feat_dim),
        'img_pos_feat': torch.randn(batch_size, 3, img_pos_dim),
        'img_masks': torch.ones(batch_size, 3),
        'gather_index': None
    }
}

ARGS = {
    'batch': batch,
    'output_all_encoded_layers': False
}
Setup block drafted by
a language model, class construct-then-call prompt, model not recorded
Imports
torch — import names as written, not package names to install; a name the repository itself provides is not a package
Returned
type tuple — a tuple output has no array shape of its own; none is stated
Environment
image not recorded; re-verify against syntology-harvest-sandbox:v5-deps; not recorded for this sample: the harness installs a cuda-to-cpu shim (cuda_shim.py) before every sample and no run records whether a sample needed it; seed: torch and numpy seeded to 0 by the harness immediately before the class was constructed from INIT_ARGS (fixture_check.py)

Also present in other papers' code

Of 1 samples lifted from this paper's linked repositories, 1 carry a function identity and 0 do not. Of the 1 distinct functions with an identity, 0 are also present in other papers whose code we hold (0 with at least one paper dated earlier, 0 the same month, 0 later) and 1 are only here among the 52,977 papers whose code Syntology holds (as of 2026-09-26).

Only here means: among the 52,977 papers whose code Syntology holds (51,887 with lifted samples, 1,090 through their assemblies only), as of 2026-09-26, no other paper's lifted samples or current assembly bricks contain an identical function body after normalisation.

Presence, not direction: an identical function body in two papers' repositories does not say who wrote it, which came from which, or that either paper's method rests on it. Matching is exact after normalisation, so a renamed or edited function is not matched. Dates are when papers appeared, not when code was written. Only .py files the harvester lifted are covered; notebooks are not read. A new-style arXiv id YYMM.NNNN dates a paper to the month 20YY-MM; otherwise Paper.year dates it to the year; otherwise it is undated. Dates are when the paper appeared, not when the code was written. Read 2026-11-21.

Repositories linked to this paper

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

Abstract

Multimodal pre-training has propelled great advancement in vision-and-language research. These large-scale pre-trained models, although successful, fatefully suffer from slow inference speed due to enormous computation cost mainly from cross-modal attention in Transformer architecture. When applied to reallife applications, such latency and computation demand severely deter the practical use of pre-trained models. In this paper, we study Image-text retrieval (ITR), the most mature scenario of V+L application, which has been widely studied even prior to the emergence of recent pre-trained models. We propose a simple yet highly effective approach, LightningDOT that accelerates the inference time of ITR by thousands of times, without sacrificing accuracy. LightningDOT removes the time-consuming cross-modal attention by pre-training on three novel learning objectives, extracting feature indexes offline, and employing instant dot-product matching with further re-ranking, which significantly speeds up retrieval process. In fact, Light-ningDOT achieves new state of the art across multiple ITR benchmarks such as Flickr30k, COCO and Multi30K, outperforming existing pre-trained models that consume 1000× magnitude of computational hours. 1

For agents

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

get_harvested_code_for_paper("2103.08784")
get_code_for_paper("2103.08784")
have("2103.08784")

The run record, dated, one paper per request, free:

curl https://syntology.ai/api/ran/2103.08784.json

A badge for a README (the split and the date, never a ratio):

[![Syntology run record](https://syntology.ai/api/ran/2103.08784.svg)](https://syntology.ai/paper/2103.08784)

Connect an agent — have() is free.