SYNTOLOGY HomeExplorerAtlasCodeMethodologyAboutDevelopersFeedPricing
Paper · 2407.08268 · 2024

Explore the Potential of CLIP for Training-Free Open Vocabulary Semantic Segmentation

arXiv · PDF · Open in the Atlas

Code that ran

3 of 5 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 0 have 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/2407.08268.json · badge: /api/ran/2407.08268.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
leaves162/cliptrase canonical (classifier label)
classifier basis: census
3 ran · 2 no recorded run
FunctionStatusWhere it lives
get_image_name_list Ran
ran; our contract draft was wrong, not the code
leaves162/cliptrase/clip_self_correlation.py
code served (permissive licence) · get_code("c98e9a8121ce0499")
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 list, ndim 1, dtype family float; no output shape is stated. The image it ran in was not recorded. If your copy returns the same type and ndim 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 os
import tempfile
import shutil

# Create a temporary directory structure to simulate the dataset
temp_dir = tempfile.mkdtemp()

# Create CITYS19 dataset structure
citys19_path = os.path.join(temp_dir, 'citys19_data')
os.makedirs(citys19_path)

# Create subdirectories for cities
city1_dir = os.path.join(citys19_path, 'city1')
city2_dir = os.path.join(citys19_path, 'city2')
os.makedirs(city1_dir)
os.makedirs(city2_dir)

# Create dummy image files
open(os.path.join(city1_dir, 'image1.png'), 'w').close()
open(os.path.join(city1_dir, 'image2.png'), 'w').close()
open(os.path.join(city2_dir, 'image3.png'), 'w').close()

# Create a simple dataset directory (non-CITYS19)
simple_dataset_path = os.path.join(temp_dir, 'simple_data')
os.makedirs(simple_dataset_path)
open(os.path.join(simple_dataset_path, 'photo1.jpg'), 'w').close()
open(os.path.join(simple_dataset_path, 'photo2.jpg'), 'w').close()

ARGS = {
    'dataset': 'CITYS19',
    'image_path': citys19_path
}
Setup block drafted by
a language model, Claude Haiku 4.5, prompt python_fixture_v1, through the batch API
Imports
none outside the standard library — import names as written, not package names to install; a name the repository itself provides is not a package
Returned
type list, ndim 1, dtype family float — a list output has no array shape of its own; none is stated
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
get_predefined_templates Ran
ran; our contract draft was wrong, not the code
leaves162/cliptrase/cliptrase_d2/cliptrase/model/utils.py
code served (permissive licence) · get_code("c266c766b74bafca")
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 list, ndim 1, dtype family float; no output shape is stated. The image it ran in was not recorded. If your copy returns the same type and ndim 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 numpy as np
from typing import List

torch.manual_seed(0)

# The function takes a single parameter: template_set_name
# It checks if the name exists in PREDEFINED_TEMPLATES dict
# and returns the corresponding list of template strings

ARGS = {
    'template_set_name': 'imagenet'
}
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 list, ndim 1, dtype family float — a list output has no array shape of its own; none is stated
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
gt_transform Ran
ran; our contract draft was wrong, not the code
leaves162/cliptrase/clip_self_correlation.py
code served (permissive licence) · get_code("1945566fa231150d")
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 Compose. 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
from torchvision.transforms import Compose, Resize, CenterCrop, ToTensor, Normalize
from torchvision.transforms import InterpolationMode

torch.manual_seed(0)

NEAREST = InterpolationMode.NEAREST

def gt_transform(n_px):
    return Compose([Resize(n_px, interpolation=NEAREST), CenterCrop(n_px)])

ARGS = {
    "n_px": 224
}
Setup block drafted by
a language model, Claude Haiku 4.5, prompt python_fixture_v1, through the batch API
Imports
torch, torchvision — import names as written, not package names to install; a name the repository itself provides is not a package
Returned
type Compose — a Compose output has no array shape of its own; none is stated — the instrument coerces any output to an array; for a Compose 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
build_model Not yet run
unverified (harvested, no recorded run)
leaves162/cliptrase/clip_utils/model.py
code served (permissive licence) · get_code("f55c8ae1a072eb4c")
How it ran

no invocation recorded.

get_image_and_gt Not yet run
unverified (harvested, no recorded run)
leaves162/cliptrase/clip_self_correlation.py
code served (permissive licence) · get_code("d9bd04969645298d")
How it ran

no invocation recorded.

Also present in other papers' code

Of 5 samples lifted from this paper's linked repositories, 5 carry a function identity and 0 do not. Of the 5 distinct functions with an identity, 1 are also present in other papers whose code we hold (1 with at least one paper dated earlier, 0 the same month, 0 later) and 4 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
get_predefined_templates 2 other papers
2 dated earlier
2302.12242 (2023-02)
Side Adapter Network for Open-Vocabulary Semantic Segmentation
2406.09829 (2024-06)
Open-Vocabulary Semantic Segmentation with Image Embedding Balancing

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

CLIP, as a vision-language model, has significantly advanced Open-Vocabulary Semantic Segmentation (OVSS) with its zero-shot capabilities. Despite its success, its application to OVSS faces challenges due to its initial image-level alignment training, which affects its performance in tasks requiring detailed local context. Our study delves into the impact of CLIP's [CLS] token on patch feature correlations, revealing a dominance of "global" patches that hinders local feature discrimination. To overcome this, we propose CLIPtrase, a novel training-free semantic segmentation strategy that enhances local feature awareness through recalibrated self-correlation among patches. This approach demonstrates notable improvements in segmentation accuracy and the ability to maintain semantic coherence across objects.Experiments show that we are 22.3% ahead of CLIP on average on 9 segmentation benchmarks, outperforming existing state-of-the-art training-free methods.The code are made publicly available at: https://github.com/leaves162/CLIPtrase.

For agents

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

get_harvested_code_for_paper("2407.08268")
get_code_for_paper("2407.08268")
have("2407.08268")

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

curl https://syntology.ai/api/ran/2407.08268.json

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

[![Syntology run record](https://syntology.ai/api/ran/2407.08268.svg)](https://syntology.ai/paper/2407.08268)

Connect an agent — have() is free.