# Learning Mask-aware CLIP Representations for Zero-Shot Segmentation

arXiv: https://arxiv.org/abs/2310.00240 · HTML: https://mlsanity.com/paper/2310.00240/

## Key facts

- Cited by 57 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 30 of its 39 references that are in the map.
- First posted on arXiv 30 Sep 2023.

## 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 30)

- [Deep Residual Learning for Image Recognition](https://mlsanity.com/paper/1512.03385/) (2015)
- [Learning Transferable Visual Models From Natural Language Supervision](https://mlsanity.com/paper/2103.00020/) (2021)
- [Scaling Up Visual and Vision-Language Representation Learning With Noisy Text Supervision](https://mlsanity.com/paper/2102.05918/) (2021)
- [DeepLab: Semantic Image Segmentation with Deep Convolutional Nets, Atrous Convolution, and Fully Connected CRFs](https://mlsanity.com/paper/1606.00915/) (2016)
- [Pyramid Scene Parsing Network](https://mlsanity.com/paper/1612.01105/) (2016)
- [Conditional Prompt Learning for Vision-Language Models](https://mlsanity.com/paper/2203.05557/) (2022)
- [Per-Pixel Classification is Not All You Need for Semantic Segmentation](https://mlsanity.com/paper/2107.06278/) (2021)
- [COCO-Stuff: Thing and Stuff Classes in Context](https://mlsanity.com/paper/1612.03716/) (2016)
- [CCNet: Criss-Cross Attention for Semantic Segmentation](https://mlsanity.com/paper/1811.11721/) (2018)
- [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)
- [GroupViT: Semantic Segmentation Emerges from Text Supervision](https://mlsanity.com/paper/2202.11094/) (2022)
- [Scaling Open-Vocabulary Image Segmentation with Image-Level Labels](https://mlsanity.com/paper/2112.12143/) (2021)
- [One-Shot Learning for Semantic Segmentation](https://mlsanity.com/paper/1709.03410/) (2017)
- [Zero-Shot Semantic Segmentation](https://mlsanity.com/paper/1906.00817/) (2019)
- [A Simple Baseline for Open-Vocabulary Semantic Segmentation with Pre-trained Vision-language Model](https://mlsanity.com/paper/2112.14757/) (2021)
- [Decoupling Zero-Shot Semantic Segmentation](https://mlsanity.com/paper/2112.07910/) (2021)
- [Hypercorrelation Squeeze for Few-Shot Segmentation](https://mlsanity.com/paper/2104.01538/) (2021)
- [Mask2Former for Video Instance Segmentation](https://mlsanity.com/paper/2112.10764/) (2021)
- [Few-Shot Segmentation via Cycle-Consistent Transformer](https://mlsanity.com/paper/2106.02320/) (2021)
- [FreeSeg: Unified, Universal and Open-Vocabulary Image Segmentation](https://mlsanity.com/paper/2303.17225/) (2023)
- [Context-aware Feature Generation for Zero-shot Semantic Segmentation](https://mlsanity.com/paper/2008.06893/) (2020)
- [A Closer Look at Self-training for Zero-Label Semantic Segmentation](https://mlsanity.com/paper/2104.11692/) (2021)
- [AlignSeg: Feature-Aligned Segmentation Networks](https://mlsanity.com/paper/2003.00872/) (2020)
- [Texts as Images in Prompt Tuning for Multi-Label Image Recognition](https://mlsanity.com/paper/2211.12739/) (2022)
- [Singular Value Fine-tuning: Few-shot Segmentation requires Few-parameters Fine-tuning](https://mlsanity.com/paper/2206.06122/) (2022)
- [Global Knowledge Calibration for Fast Open-Vocabulary Segmentation](https://mlsanity.com/paper/2303.09181/) (2023)
- [Mining Unseen Classes via Regional Objectness: A Simple Baseline for Incremental Segmentation](https://mlsanity.com/paper/2211.06866/) (2022)
- [Semantic Segmentation In-the-Wild Without Seeing Any Segmentation Examples](https://mlsanity.com/paper/2112.03185/) (2021)
- [Mask Matching Transformer for Few-Shot Segmentation](https://mlsanity.com/paper/2301.01208/) (2022)

## Built on by (most cited first, 30 of 57)

- [Forgery-aware Adaptive Transformer for Generalizable Synthetic Image Detection](https://mlsanity.com/paper/2312.16649/) (2023)
- [ClearCLIP: Decomposing CLIP Representations for Dense Vision-Language Inference](https://mlsanity.com/paper/2407.12442/) (2024)
- [Explore the Potential of CLIP for Training-Free Open Vocabulary Semantic Segmentation](https://mlsanity.com/paper/2407.08268/) (2024)
- [TripletCLIP: Improving Compositional Reasoning of CLIP via Synthetic Vision-Language Negatives](https://mlsanity.com/paper/2411.02545/) (2024)
- [Open-Vocabulary Segmentation with Semantic-Assisted Calibration](https://mlsanity.com/paper/2312.04089/) (2023)
- [Image Segmentation in Foundation Model Era: A Survey](https://mlsanity.com/paper/2408.12957/) (2024)
- [DeCLIP: Decoupled Learning for Open-Vocabulary Dense Perception](https://mlsanity.com/paper/2505.04410/) (2025)
- [ResCLIP: Residual Attention for Training-free Dense Vision-language Inference](https://mlsanity.com/paper/2411.15851/) (2024)
- [Rethinking Prior Information Generation with CLIP for Few-Shot Segmentation](https://mlsanity.com/paper/2405.08458/) (2024)
- [Mask-Adapter: The Devil is in the Masks for Open-Vocabulary Segmentation](https://mlsanity.com/paper/2412.04533/) (2024)
- [Cascade Prompt Learning for Vision-Language Model Adaptation](https://mlsanity.com/paper/2409.17805/) (2024)
- [Cascade-CLIP: Cascaded Vision-Language Embeddings Alignment for Zero-Shot Semantic Segmentation](https://mlsanity.com/paper/2406.00670/) (2024)
- [Effective SAM Combination for Open-Vocabulary Semantic Segmentation](https://mlsanity.com/paper/2411.14723/) (2024)
- [Towards the Uncharted: Density-Descending Feature Perturbation for Semi-supervised Semantic Segmentation](https://mlsanity.com/paper/2403.06462/) (2024)
- [Frozen CLIP: A Strong Backbone for Weakly Supervised Semantic Segmentation](https://mlsanity.com/paper/2406.11189/) (2024)
- [DetailCLIP: Detail-Oriented CLIP for Fine-Grained Tasks](https://mlsanity.com/paper/2409.06809/) (2024)
- [Open-Vocabulary Remote Sensing Image Semantic Segmentation](https://mlsanity.com/paper/2409.07683/) (2024)
- [Vision-Language Model for Object Detection and Segmentation: A Review and Evaluation](https://mlsanity.com/paper/2504.09480/) (2025)
- [Generalized Decoupled Learning for Enhancing Open-Vocabulary Dense Perception](https://mlsanity.com/paper/2508.11256/) (2025)
- [Unbiased Region-Language Alignment for Open-Vocabulary Dense Prediction](https://mlsanity.com/paper/2412.06244/) (2024)
- [ITACLIP: Boosting Training-Free Semantic Segmentation with Image, Text, and Architectural Enhancements](https://mlsanity.com/paper/2411.12044/) (2024)
- [CLIP-GS: Unifying Vision-Language Representation with 3D Gaussian Splatting](https://mlsanity.com/paper/2412.19142/) (2024)
- [Language-Driven Visual Consensus for Zero-Shot Semantic Segmentation](https://mlsanity.com/paper/2403.08426/) (2024)
- [Tuning-free Universally-Supervised Semantic Segmentation](https://mlsanity.com/paper/2405.14294/) (2024)
- [AlignZeg: Mitigating Objective Misalignment for Zero-shot Semantic Segmentation](https://mlsanity.com/paper/2404.05667/) (2024)
- [High-Quality Mask Tuning Matters for Open-Vocabulary Segmentation](https://mlsanity.com/paper/2412.11464/) (2024)
- [Stepping Out of Similar Semantic Space for Open-Vocabulary Segmentation](https://mlsanity.com/paper/2506.16058/) (2025)
- [Target Refocusing via Attention Redistribution for Open-Vocabulary Semantic Segmentation: An Explainability Perspective](https://mlsanity.com/paper/2511.16170/) (2025)
- [Revisiting Prompt Pretraining of Vision-Language Models](https://mlsanity.com/paper/2409.06166/) (2024)
- [SAM-MI: A Mask-Injected Framework for Enhancing Open-Vocabulary Semantic Segmentation with SAM](https://mlsanity.com/paper/2511.20027/) (2025)

## Abstract (arXiv)

Recently, pre-trained vision-language models have been increasingly used to tackle the challenging zero-shot segmentation task. Typical solutions follow the paradigm of first generating mask proposals and then adopting CLIP to classify them. To maintain the CLIP's zero-shot transferability, previous practices favour to freeze CLIP during training. However, in the paper, we reveal that CLIP is insensitive to different mask proposals and tends to produce similar predictions for various mask proposals of the same image. This insensitivity results in numerous false positives when classifying mask proposals. This issue mainly relates to the fact that CLIP is trained with image-level supervision. To alleviate this issue, we propose a simple yet effective method, named Mask-aware Fine-tuning (MAFT). Specifically, Image-Proposals CLIP Encoder (IP-CLIP Encoder) is proposed to handle arbitrary numbers of image and mask proposals simultaneously. Then, mask-aware loss and self-distillation loss are designed to fine-tune IP-CLIP Encoder, ensuring CLIP is responsive to different mask proposals while not sacrificing transferability. In this way, mask-aware representations can be easily learned to make the true positives stand out. Notably, our solution can seamlessly plug into most existing methods without introducing any new parameters during the fine-tuning process. We conduct extensive experiments on the popular zero-shot benchmarks. With MAFT, the performance of the state-of-the-art methods is promoted by a large margin: 50.4% (+ 8.2%) on COCO, 81.8% (+ 3.2%) on Pascal-VOC, and 8.7% (+4.3%) on ADE20K in terms of mIoU for unseen classes. The code is available at https://github.com/jiaosiyu1999/MAFT.git.