SYNTOLOGY HomeExplorerAtlasCodeMethodologyAboutDevelopersFeedPricing
Paper · 2404.00741 · CVPR · 2024

Rethinking Interactive Image Segmentation with Low Latency, High Quality, and Diverse Prompts

Marc Niethammer, Jaemin Cho, Mohit Bansal, Qin Liu

arXiv · PDF · Open in the Atlas

Code that ran

2 of 3 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; 2 failures of our instrument; 1 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/2404.00741.json · badge: /api/ran/2404.00741.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
uncbiag/segnext canonical (classifier label)
classifier basis: census
2 ran · 1 no recorded run
FunctionStatusWhere it lives
handle_exception Ran
ran; our contract draft was wrong, not the code
uncbiag/segnext/segnext/interactive_demo/canvas.py
code served (permissive licence) · get_code("954d2116dbc85a7b")
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 function. 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 sys
import torch
import torch.nn as nn

torch.manual_seed(0)

# Analyze the function:
# handle_exception takes one parameter: exit_code (default 0)
# It returns a decorator that wraps functions
# The decorator catches exceptions and optionally calls sys.exit(exit_code)
# To test this, we need to provide an exit_code value

# Create a simple test function to decorate
def sample_function():
    """A simple function that can be decorated"""
    return "success"

def sample_function_with_error():
    """A function that raises an exception"""
    raise ValueError("Test exception")

ARGS = {
    "exit_code": 0
}
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 function — a function output has no array shape of its own; none is stated — the instrument coerces any output to an array; for a function 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
select_activation_function Ran
ran; our contract draft was wrong, not the code
uncbiag/segnext/segnext/isegm/model/ops.py
code served (permissive licence) · get_code("b6b0c52a17e3f320")
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 type. 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 torch import nn

torch.manual_seed(0)

# Test case 1: string activation 'relu'
activation_string_relu = 'relu'

# Test case 2: string activation 'softplus'
activation_string_softplus = 'softplus'

# Test case 3: nn.Module instance
activation_module = nn.ReLU()

# We'll use the string 'relu' as the primary test case
ARGS = {
    'activation': 'relu'
}
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 type — a type output has no array shape of its own; none is stated — the instrument coerces any output to an array; for a type 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
split_points_by_order Not yet run
unverified (harvested, no recorded run)
uncbiag/segnext/segnext/isegm/model/is_model.py
code served (permissive licence) · get_code("8bb23b71c17a0a25")
How it ran

no invocation recorded.

Also present in other papers' code

Of 3 samples lifted from this paper's linked repositories, 3 carry a function identity and 0 do not. Of the 3 distinct functions with an identity, 3 are also present in other papers whose code we hold (3 with at least one paper dated earlier, 0 the same month, 1 later) and 0 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
split_points_by_order 4 other papers
4 dated earlier
2204.02574 (2022-04)
FocalClick: Towards Practical Interactive Image Segmentation
2210.11006 (2022-10)
SimpleClick: Interactive Image Segmentation with Simple Vision Transformers
and 1 more not named here
handle_exception 3 other papers
2 dated earlier, 1 later
2210.11006 (2022-10)
SimpleClick: Interactive Image Segmentation with Simple Vision Transformers
2305.04276 (2023-05)
AdaptiveClick: Clicks-aware Transformer with Adaptive Focal Loss for Interactive Image Segmentation
2405.00587 (2024-05)
GraCo: Granularity-Controllable Interactive Segmentation
select_activation_function 1 other paper
1 dated earlier
1802.02611 (2018-02)
Encoder-Decoder with Atrous Separable Convolution for Semantic Image Segmentation

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

The goal of interactive image segmentation is to delineate specific regions within an image via visual or language prompts. Low-latency and high-quality interactive segmentation with diverse prompts remain challenging for existing specialist and generalist models. Specialist models, with their limited prompts and task-specific designs, experience high latency because the image must be recomputed every time the prompt is updated, due to the joint encoding of image and visual prompts. Generalist models, exemplified by the Segment Anything Model (SAM), have recently excelled in prompt diversity and efficiency, lifting image segmentation to the foundation model era. However, for high-quality segmentations, SAM still lags behind state-of-the-art specialist models despite SAM being trained with ×100 more segmentation masks. In this work, we delve deep into the architectural differences between the two types of models. We observe that dense representation and fusion of visual prompts are the key design choices contributing to the high segmentation quality of specialist models. In light of this, we reintroduce this dense design into the generalist models, to facilitate the development of generalist models with high segmentation quality. To densely represent diverse visual prompts, we propose to use a dense map to capture five types: clicks, boxes, polygons, scribbles, and masks. Thus, we propose SegNext, a next-generation interactive segmentation approach offering low latency, high quality, and diverse prompt support. Our method outperforms current state-of-the-art methods on HQSeg-44K and DAVIS, both quantitatively and qualitatively.

For agents

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

get_harvested_code_for_paper("2404.00741")
get_code_for_paper("2404.00741")
have("2404.00741")

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

curl https://syntology.ai/api/ran/2404.00741.json

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

[![Syntology run record](https://syntology.ai/api/ran/2404.00741.svg)](https://syntology.ai/paper/2404.00741)

Connect an agent — have() is free.