SYNTOLOGY HomeExplorerAtlasCodeMethodologyAboutDevelopersFeedPricing
Paper · 2406.14924 · NeurIPS · 2024

DiPEx: Dispersing Prompt Expansion for Class-Agnostic Object Detection

Xin Yu, Mahsa Baktashmotlagh, Zhi Chen, Zi Huang, Yadan Luo, Zhuoxiao Chen, Jia Lim

arXiv · PDF · Open in the Atlas

Code that ran

5 of 7 samples (functions and classes) lifted from this paper's linked repositories executed on a synthesized input in Syntology's jail (1 of them constructed an object rather than computing a result; 1 honoured the contract we drafted, 0 violated it and 1 has no contract verdict; 3 failures of our instrument; 2 no recorded run), measured 2026-11-22; 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/2406.14924.json · badge: /api/ran/2406.14924.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
jason-lim26/DiPEx canonical (classifier label)
classifier basis: census
4 ran · 2 no recorded run
jason-lim26/dipex canonical (classifier label)
classifier basis: classifier_2025
1 ran · 0 no recorded run
FunctionStatusWhere it lives
PromptTree Ran
ran on a synthesized input · constructed an object; no result was computed
jason-lim26/dipex/Open-GroundingDino/models/GroundingDINO/dipex.py
code served (permissive licence) · get_code("fa56de74aac836b3")
How it ran

Ran in Syntology's sandbox on this synthesized input (drafted by a language model, Claude Haiku 4.5, prompt python_fixture_v1, through the batch API) and returned an instance of its own class, PromptTree: the run constructed the object and did not call it, so no result was computed. 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
import math

torch.manual_seed(0)

# PromptTree expects:
# - prompt_dim: int (dimensionality of each prompt vector)
# - init_prompt_num: int (number of prompts to initialize)

ARGS = {
    "prompt_dim": 4,
    "init_prompt_num": 2,
}
Setup block drafted by
a language model, Claude Haiku 4.5, prompt python_fixture_v1, through the batch API
Imports
numpy, torch — import names as written, not package names to install; a name the repository itself provides is not a package
Returned
type PromptTree — the run constructed an instance of its own class and did not call it; no shape is stated — the instrument coerces any output to an array; for a PromptTree output the recorded ndim 0 and dtype family float describe that coercion, not the output, and are not 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: none by the harness; any seed is in the setup block
convert_to_xywh Ran
ran, honoured the contract we drafted
jason-lim26/DiPEx/Open-GroundingDino/datasets/coco_eval.py
pointer only (licence: Apache-2.0); the stored copy get_code serves, from yuhangzang/contextdet, is pointer only (licence: NOASSERTION) · get_code("f31a58bf6457ced5")
How it ran

The body of this sample is withheld: this paper's link allows the body inline (Apache-2.0), but get_code serves the stored copy, first harvested from yuhangzang/contextdet, and GitHub could not classify the licence of that repository (NOASSERTION). The setup block that called it is withheld with it, because it is written against that body. source_path and origin say where the code lives, to read under the repository's own terms. A run is recorded.

create_positive_map Ran
ran; our contract draft was wrong, not the code
jason-lim26/DiPEx/Open-GroundingDino/models/GroundingDINO/dipex.py
code served (permissive licence) · get_code("934833a6fa34d3a0")
How it ran

Ran in Syntology's sandbox on this synthesized input (drafted by a language model, Claude Haiku 4.5, prompt python_fixture_v1, through the batch API) and returned Tensor, ndim 2, dtype family float, shape (2, 256) as a later run recorded it. The image it ran in was not recorded. If your copy returns the same type, ndim and shape 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

torch.manual_seed(0)

# Stand-in class for tokenized object that has char_to_token method
class MockTokenized:
    def __init__(self):
        # Map character positions to token indices
        self.char_to_token_map = {
            0: 0,    # 'dog' starts at char 0, maps to token 0
            1: 0,
            2: 0,
            4: 1,    # 'cat' starts at char 4, maps to token 1
            5: 1,
            6: 1,
            8: 2,   # 'bird' starts at char 8, maps to token 2
            9: 2,
            10: 2,
            11: 2,
        }
    
    def char_to_token(self, char_idx):
        if char_idx in self.char_to_token_map:
            return self.char_to_token_map[char_idx]
        # Return None if character not in map (mimics tokenizer behavior)
        return None

# Create test data
tokenized = MockTokenized()

# tokens_positive: list of indices into cat_list that are positive
tokens_positive = [0, 1]

# cat_list: list of category names
cat_list = ["dog", "cat", "bird"]

# caption: the full caption text
caption = "dog and cat and bird"

ARGS = {
    "tokenized": tokenized,
    "tokens_positive": tokens_positive,
    "cat_list": cat_list,
    "caption": caption,
}
Setup block drafted by
a language model, Claude Haiku 4.5, prompt python_fixture_v1, through the batch API
Imports
torch — import names as written, not package names to install; a name the repository itself provides is not a package
Returned
type Tensor, ndim 2, dtype family float, shape (2, 256) — shape (2, 256) as a later run recorded it
dtype family
int means an integer dtype; float means any other dtype the instrument saw, bool and complex included (fixture_check.py records only these two families)
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: none by the harness; any seed is in the setup block
evaluate Ran
ran; our contract draft was wrong, not the code
jason-lim26/DiPEx/Open-GroundingDino/datasets/coco_eval.py
pointer only (licence: Apache-2.0); the stored copy get_code serves, from yuhangzang/contextdet, is pointer only (licence: NOASSERTION) · get_code("fe0ddcc2d420c9a0")
How it ran

The body of this sample is withheld: this paper's link allows the body inline (Apache-2.0), but get_code serves the stored copy, first harvested from yuhangzang/contextdet, and GitHub could not classify the licence of that repository (NOASSERTION). The setup block that called it is withheld with it, because it is written against that body. source_path and origin say where the code lives, to read under the repository's own terms. A run is recorded.

label2onehot Ran
ran; our contract draft was wrong, not the code
jason-lim26/DiPEx/Open-GroundingDino/datasets/coco.py
code served (permissive licence) · get_code("fb05961e12a99588")
How it ran

Ran in Syntology's sandbox on this synthesized input (drafted by a language model, Claude Haiku 4.5, prompt python_fixture_v1, through the batch API) and returned Tensor, ndim 1, dtype family float, shape (3,) as a later run recorded it. The image it ran in was not recorded. If your copy returns the same type, ndim and shape 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

torch.manual_seed(0)

# The function expects:
# - label: a Tensor of shape (K,) containing class indices
# - num_classes: an integer representing the number of classes

# Create a small label tensor with K=3 elements, each being a class index
# The values should be valid indices less than num_classes
label = torch.tensor([0, 2, 1], dtype=torch.long)

# Number of classes
num_classes = 3

ARGS = {
    "label": label,
    "num_classes": num_classes,
}
Setup block drafted by
a language model, Claude Haiku 4.5, prompt python_fixture_v1, through the batch API
Imports
torch — import names as written, not package names to install; a name the repository itself provides is not a package
Returned
type Tensor, ndim 1, dtype family float, shape (3,) — shape (3,) as a later run recorded it
dtype family
int means an integer dtype; float means any other dtype the instrument saw, bool and complex included (fixture_check.py records only these two families)
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: none by the harness; any seed is in the setup block
ciou Not yet run
unverified (harvested, no recorded run)
jason-lim26/DiPEx/Open-GroundingDino/util/box_loss.py
code served (permissive licence) · get_code("4373b99bf6b5fd7d")
How it ran

no invocation recorded.

diou Not yet run
unverified (harvested, no recorded run)
jason-lim26/DiPEx/Open-GroundingDino/util/box_loss.py
code served (permissive licence) · get_code("7818a5040676702a")
How it ran

no invocation recorded.

Also present in other papers' code

Of 7 samples lifted from this paper's linked repositories, 7 carry a function identity and 0 do not. Of the 7 distinct functions with an identity, 5 are also present in other papers whose code we hold (5 with at least one paper dated earlier, 2 the same month, 2 later) and 2 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.

FunctionAlso present inEarliest-datedOthers named
convert_to_xywh 24 other papers
22 dated earlier, 1 the same month, 1 same year, order not determinable
1512.02325 (2015-12)
SSD: Single Shot MultiBox Detector
2010.04159 (2020-10)
Deformable DETR: Deformable Transformers for End-to-End Object Detection
2103.11731 (2021-03)
Meta-DETR: Image-Level Few-Shot Object Detection with Inter-Class Correlation Exploitation
and 21 more not named here
evaluate 23 other papers
21 dated earlier, 1 the same month, 1 same year, order not determinable
1512.02325 (2015-12)
SSD: Single Shot MultiBox Detector
2010.04159 (2020-10)
Deformable DETR: Deformable Transformers for End-to-End Object Detection
2103.11731 (2021-03)
Meta-DETR: Image-Level Few-Shot Object Detection with Inter-Class Correlation Exploitation
and 20 more not named here
ciou 8 other papers
7 dated earlier, 1 later
2203.03605 (2022-03)
DINO: DETR with Improved DeNoising Anchor Boxes for End-to-End Object Detection
Liu_SAP-DETR_Bridging_the_Gap_Between_Salient_Points_and_Queries-Based_Transformer_CVPR_2023_paper (2023 (year only))
SAP-DETR: Bridging the Gap between Salient Points and Queries-Based Transformer Detector for Fast Model Convergency
and 5 more not named here
diou 7 other papers
6 dated earlier, 1 later
2203.03605 (2022-03)
DINO: DETR with Improved DeNoising Anchor Boxes for End-to-End Object Detection
Liu_SAP-DETR_Bridging_the_Gap_Between_Salient_Points_and_Queries-Based_Transformer_CVPR_2023_paper (2023 (year only))
SAP-DETR: Bridging the Gap between Salient Points and Queries-Based Transformer Detector for Fast Model Convergency
and 4 more not named here
label2onehot 1 other paper
1 dated earlier
2405.17913 (2024-05)
OV-DQUO: Open-Vocabulary DETR with Denoising Text Query Training and Open-World Unknown Objects Supervision

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 2026-11-22.

Repositories linked to this paper

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

Abstract

Class-agnostic object detection (OD) can be a cornerstone or a bottleneck for many downstream vision tasks. Despite considerable advancements in bottom-up and multi-object discovery methods that leverage basic visual cues to identify salient objects, consistently achieving a high recall rate remains difficult due to the diversity of object types and their contextual complexity. In this work, we investigate using vision-language models (VLMs) to enhance object detection via a self-supervised prompt learning strategy. Our initial findings indicate that manually crafted text queries often result in undetected objects, primarily because detection confidence diminishes when the query words exhibit semantic overlap. To address this, we propose a Dispersing Prompt Expansion (DiPEx) approach. DiPEx progressively learns to expand a set of distinct, non-overlapping hyperspherical prompts to enhance recall rates, thereby improving performance in downstream tasks such as out-of-distribution OD. Specifically, DiPEx initiates the process by self-training generic parent prompts and selecting the one with the highest semantic uncertainty for further expansion. The resulting child prompts are expected to inherit semantics from their parent prompts while capturing more fine-grained semantics. We apply dispersion losses to ensure high inter-class discrepancy among child prompts while preserving semantic consistency between parent-child prompt pairs. To prevent excessive growth of the prompt sets, we utilize the maximum angular coverage (MAC) of the semantic space as a criterion for early termination. We demonstrate the effectiveness of DiPEx through extensive class-agnostic OD and OOD-OD experiments on MS-COCO and LVIS, surpassing other prompting methods by up to 20.1% in AR and achieving a 21.3% AP improvement over SAM. The code is available at https://github.com/jason-lim26/DiPEx.

For agents

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

get_harvested_code_for_paper("2406.14924")
get_code_for_paper("2406.14924")
have("2406.14924")

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

curl https://syntology.ai/api/ran/2406.14924.json

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

[![Syntology run record](https://syntology.ai/api/ran/2406.14924.svg)](https://syntology.ai/paper/2406.14924)

Connect an agent — have() is free.