Pith. sign in

REVIEW 11 cited by

LaSagnA: Language-based Segmentation Assistant for Complex Queries

Not yet reviewed by Pith; the record is open.

This paper has not been read by Pith yet. Machine review is queued; the pith claim, tier, and objections will appear here once it completes.

SPECIMEN: schema-true, not a live event

T0 review · schema-true

One-sentence machine reading of the paper's core claim.

pith:XXXXXXXX · record.json · timestamp

arxiv 2404.08506 v1 pith:FT66N5C5 submitted 2024-04-12 cs.CV

LaSagnA: Language-based Segmentation Assistant for Complex Queries

classification cs.CV
keywords queriessegmentationcomplexvllmsformatlasagnamodelquery
verification ladder T0 review T1 audit T2 compute T3 formal T4 reserved
0 comments
read the original abstract

Recent advancements have empowered Large Language Models for Vision (vLLMs) to generate detailed perceptual outcomes, including bounding boxes and masks. Nonetheless, there are two constraints that restrict the further application of these vLLMs: the incapability of handling multiple targets per query and the failure to identify the absence of query objects in the image. In this study, we acknowledge that the main cause of these problems is the insufficient complexity of training queries. Consequently, we define the general sequence format for complex queries. Then we incorporate a semantic segmentation task in the current pipeline to fulfill the requirements of training data. Furthermore, we present three novel strategies to effectively handle the challenges arising from the direct integration of the proposed format. The effectiveness of our model in processing complex queries is validated by the comparable results with conventional methods on both close-set and open-set semantic segmentation datasets. Additionally, we outperform a series of vLLMs in reasoning and referring segmentation, showcasing our model's remarkable capabilities. We release the code at https://github.com/congvvc/LaSagnA.

discussion (0)

Sign in with ORCID, Apple, or X to comment. Anyone can read and Pith papers without signing in.

Forward citations

Cited by 11 Pith papers

Reviewed papers in the Pith corpus that reference this work. Sorted by Pith novelty score.

  1. IQA-Spider: Unifying Multi-Granularity Image Quality Assessment with Reasoning, Grounding and Referring

    cs.CV 2026-05 unverdicted novelty 7.0

    IQA-Spider unifies reasoning, grounding, and referring for multi-granularity image quality assessment via a four-task paradigm and two-stage LMM training with training-free text-to-point mapping.

  2. VISTAQA: Benchmarking Joint Visual Question Answering and Pixel-Level Evidence

    cs.CV 2026-05 unverdicted novelty 7.0

    VISTAQA is a new benchmark for joint visual question answering correctness and pixel-level grounding, evaluated with the GROVE metric that uses per-sample geometric mean to require both dimensions to succeed.

  3. PixDLM: A Dual-Path Multimodal Language Model for UAV Reasoning Segmentation

    cs.CV 2026-04 unverdicted novelty 7.0

    The work introduces the UAV Reasoning Segmentation task, the DRSeg benchmark dataset, and PixDLM as a baseline dual-path multimodal language model for reasoning-based segmentation in aerial imagery.

  4. Segmentation before Answering: Pixel Grounding for MLLM Visual Reasoning

    cs.CV 2026-07 conditional novelty 6.0

    SegAnswer trains an MLLM to generate segmentation masks instead of bounding boxes when zooming into image regions during visual reasoning, yielding consistent improvements across perception and hallucination benchmarks.

  5. InstanceControl: Controllable Complex Image Generation without Instance Labeling

    cs.CV 2026-06 unverdicted novelty 6.0

    InstanceControl uses VLMs to auto-generate instance masks from text and visual conditions, with adaptive refinement, to enable controllable multi-object image generation without manual labeling.

  6. Enhancing Part-Level Point Grounding for Any Open-Source MLLMs

    cs.CV 2026-06 unverdicted novelty 6.0

    A plug-in Q-Synth Module plus Attention-to-Point Decoder converts text-conditioned attention in frozen MLLMs into point heatmaps, improving part-level grounding accuracy on multiple datasets.

  7. MedSIGHT: Towards Grounded Visual Comprehension in Medical Large Vision-Language Models

    cs.CV 2026-06 unverdicted novelty 6.0

    MedSIGHT unifies medical image comprehension and segmentation in Med-LVLMs via a Region Perceiver module and region codebook, trained progressively on 72K pairs to reach SOTA on both tasks across modalities.

  8. X2SAM: Any Segmentation in Images and Videos

    cs.CV 2026-04 unverdicted novelty 6.0

    X2SAM unifies any-segmentation across images and videos in one MLLM by adding a Mask Memory module for temporal consistency and joint training on mixed datasets.

  9. GTPBD-MM: A Global Terraced Parcel and Boundary Dataset with Multi-Modality

    cs.CV 2026-04 unverdicted novelty 6.0

    GTPBD-MM is the first multimodal benchmark for global terraced parcel extraction, integrating image, text, and DEM data with experiments showing that textual and terrain cues improve delineation accuracy over image-on...

  10. Sa2VA: Marrying SAM2 with LLaVA for Dense Grounded Understanding of Images and Videos

    cs.CV 2025-01 conditional novelty 6.0

    Sa2VA unifies SAM-2 segmentation with MLLM reasoning into a single model for referring segmentation and conversation on images and videos, supported by a new 72k-expression Ref-SAV dataset.

  11. From Structure to Synergy: A Survey of Vision-Language Perception Paradigm Evolution in Multimodal Large Language Models

    cs.CL 2026-06 unverdicted novelty 5.0

    The survey formalizes MLLM perception as a unified vision-language capability and traces its evolution via a new five-stage taxonomy while outlining future challenges.