# PCA-Seg: Revisiting Cost Aggregation for Open-Vocabulary Semantic and Part Segmentation

arXiv: https://arxiv.org/abs/2603.17520 · HTML: https://mlsanity.com/paper/2603.17520/

## Key facts

- Cited by 5 papers in the map (data through 14 Oct 2026).
- Placed in Prompt learning and adaptation of CLIP, one of 16 directions in Multimodal LLMs / vision-language models.
- Builds on 52 of its 63 references that are in the map.
- First posted on arXiv 18 Mar 2026.

## Placed in

- Multimodal LLMs / vision-language models / [Prompt learning and adaptation of CLIP](https://mlsanity.com/mllm/prompt-learning-and-adaptation-of-clip/)

## Builds on (most cited first, 30 of 52)

- [Learning Transferable Visual Models From Natural Language Supervision](https://mlsanity.com/paper/2103.00020/) (2021)
- [Swin Transformer: Hierarchical Vision Transformer using Shifted Windows](https://mlsanity.com/paper/2103.14030/) (2021)
- [Scaling Up Visual and Vision-Language Representation Learning With Noisy Text Supervision](https://mlsanity.com/paper/2102.05918/) (2021)
- [Masked-attention Mask Transformer for Universal Image Segmentation](https://mlsanity.com/paper/2112.01527/) (2021)
- [Transformers are RNNs: Fast Autoregressive Transformers with Linear Attention](https://mlsanity.com/paper/2006.16236/) (2020)
- [Align before Fuse: Vision and Language Representation Learning with Momentum Distillation](https://mlsanity.com/paper/2107.07651/) (2021)
- [Semantic Understanding of Scenes through the ADE20K Dataset](https://mlsanity.com/paper/1608.05442/) (2016)
- [COCO-Stuff: Thing and Stuff Classes in Context](https://mlsanity.com/paper/1612.03716/) (2016)
- [Extract Free Dense Labels from CLIP](https://mlsanity.com/paper/2112.01071/) (2021)
- [Open-Vocabulary Semantic Segmentation with Mask-adapted CLIP](https://mlsanity.com/paper/2210.04150/) (2022)
- [Image Segmentation Using Text and Image Prompts](https://mlsanity.com/paper/2112.10003/) (2021)
- [Scaling Open-Vocabulary Image Segmentation with Image-Level Labels](https://mlsanity.com/paper/2112.12143/) (2021)
- [Side Adapter Network for Open-Vocabulary Semantic Segmentation](https://mlsanity.com/paper/2302.12242/) (2023)
- [Detect What You Can: Detecting and Representing Objects using Holistic Models and Body Parts](https://mlsanity.com/paper/1406.2031/) (2014)
- [A Simple Baseline for Open-Vocabulary Semantic Segmentation with Pre-trained Vision-language Model](https://mlsanity.com/paper/2112.14757/) (2021)
- [CAT-Seg: Cost Aggregation for Open-Vocabulary Semantic Segmentation](https://mlsanity.com/paper/2303.11797/) (2023)
- [Convolutions Die Hard: Open-Vocabulary Segmentation with Single Frozen Convolutional CLIP](https://mlsanity.com/paper/2308.02487/) (2023)
- [GLU-Net: Global-Local Universal Network for Dense Flow and Correspondences](https://mlsanity.com/paper/1912.05524/) (2019)
- [CLIPSelf: Vision Transformer Distills Itself for Open-Vocabulary Dense Prediction](https://mlsanity.com/paper/2310.01403/) (2023)
- [Cost Aggregation with 4D Convolutional Swin Transformer for Few-Shot Segmentation](https://mlsanity.com/paper/2207.10866/) (2022)
- [Learning Open-vocabulary Semantic Segmentation Models From Natural Language Supervision](https://mlsanity.com/paper/2301.09121/) (2023)
- [SED: A Simple Encoder-Decoder for Open-Vocabulary Semantic Segmentation](https://mlsanity.com/paper/2311.15537/) (2023)
- [CLIP-DINOiser: Teaching CLIP a few DINO tricks for open-vocabulary semantic segmentation](https://mlsanity.com/paper/2312.12359/) (2023)
- [FreeSeg: Unified, Universal and Open-Vocabulary Image Segmentation](https://mlsanity.com/paper/2303.17225/) (2023)
- [CATs: Cost Aggregation Transformers for Visual Correspondence](https://mlsanity.com/paper/2106.02520/) (2021)
- [Unsupervised Part Discovery from Contrastive Reconstruction](https://mlsanity.com/paper/2111.06349/) (2021)
- [Hyperpixel Flow: Semantic Correspondence with Multi-layer Neural Features](https://mlsanity.com/paper/1908.06537/) (2019)
- [CATs++: Boosting Cost Aggregation with Convolutions and Transformers](https://mlsanity.com/paper/2202.06817/) (2022)
- [Poly Kernel Inception Network for Remote Sensing Detection](https://mlsanity.com/paper/2403.06258/) (2024)
- [Going Denser with Open-Vocabulary Part Segmentation](https://mlsanity.com/paper/2305.11173/) (2023)

## Built on by (most cited first, 5 of 5)

- [ResilPhase: Plug-and-Play Phase Mapping and Noise-Resilient Macro-Trajectory Extrapolation for Diffusion Acceleration](https://mlsanity.com/paper/2606.26769/) (2026)
- [Layer-Specific Prompt Fusion Discovery via Differentiable Search in Vision Foundation Models](https://mlsanity.com/paper/2606.26379/) (2026)
- [Cut-ViT: Task-Specific Model Pruning via Gram Anchoring Subspace Consistency](https://mlsanity.com/paper/2608.28205/) (2026)
- [T2LDM++: A Self-Conditioned Representation Guided Diffusion Model for Realistic Text-to-LiDAR Scene Generation](https://mlsanity.com/paper/2606.30147/) (2026)
- [DT-LoRA: Reaching Beyond the Tangent Space of Low-Rank Adaptation](https://mlsanity.com/paper/2610.17730/) (2026)

## Abstract (arXiv)

Recent advances in vision-language models (VLMs) have garnered substantial attention in open-vocabulary semantic and part segmentation (OSPS). However, existing methods extract image-text alignment cues from cost volumes through a serial structure of spatial and class aggregations, leading to knowledge interference between class-level semantics and spatial context. Therefore, this paper proposes a simple yet effective parallel cost aggregation (PCA-Seg) paradigm to alleviate the above challenge, enabling the model to capture richer vision-language alignment information from cost volumes. Specifically, we design an expert-driven perceptual learning (EPL) module that efficiently integrates semantic and contextual streams. It incorporates a multi-expert parser to extract complementary features from multiple perspectives. In addition, a coefficient mapper is designed to adaptively learn pixel-specific weights for each feature, enabling the integration of complementary knowledge into a unified and robust feature embedding. Furthermore, we propose a feature orthogonalization decoupling (FOD) strategy to mitigate redundancy between the semantic and contextual streams, which allows the EPL module to learn diverse knowledge from orthogonalized features. Extensive experiments on eight benchmarks show that each parallel block in PCA-Seg adds merely 0.35M parameters while achieving state-of-the-art OSPS performance.