paper-with-me

Papers

Multi-Label Prototype Visual Spatial Search for Weakly Supervised Semantic Segmentation

2025-01-01 · CVPR 2025 1 · Songsong Duan, Xi Yang, Nannan Wang

Existing Weakly Supervised Semantic Segmentation (WSSS) relies on the CNN-based Class Activation Map (CAM) and Transformer-based self-attention map to generate class-specific masks for semantic segmentation. However, CAM and self-attention maps usually cause incomplete segmentation due to classification bias issue. To address this issue, we propose a Multi-Label Prototype Visual Spatial Search (MuP-VSS) method with a spatial query mechanism, which learns a set of learnable class token vectors as queries to search the similarity visual tokens from image patch tokens. Specifically, MuP-VSS consists of two key components: multi-label prototype representation and multi-label prototype optimization. The former designs a global embedding to learn the global tokens from the images, and then proposes a Prototype Embedding Module (PEM) to interact with patch tokens to understand the local semantic information. The latter utilizes the exclusivity and consistency principles of the multi-label prototypes to design three prototype losses to optimize them, which contain cross-class prototype (CCP) contrastive loss, cross-image prototype (CIP) contrastive loss, and patch-to-prototype (P2P) consistency loss. CCP loss models exclusivity of multi-label prototypes learned from a single image to enhance the discriminative properties of each class better. CCP loss learns the consistency of the same class-specific prototypes extracted from multiple images to enhance the semantic consistency. P2P loss is proposed to control the semantic response of the prototype to the image patches. Experimental results on Pascal VOC 2012 and MS COCO show that MuP-VSS significantly outperforms recent methods and achieves state-of-the-art performance.

📄 PDF Abstract BibTeX

Code (0)

등록된 구현이 없습니다.

Tasks

Semantic SegmentationWeakly supervised Semantic SegmentationWeakly-Supervised Semantic Segmentation

Methods 이 논문이 사용한 방법론

SET Dynamic Sparse Training method where weight mask is updated randomly periodically
CAM Class activation maps could be used to interpret the prediction decision made by the convolutional neural network (CNN). Image source: [Learning Deep Features for…

Similar Papers 제목 키워드 기반

3DFroMLLM: 3D Prototype Generation only from Pretrained Multimodal LLMs

2025-08-12 · Noor Ahmed, Cameron Braunstein, Steffen Eger, Eddy Ilg arxiv

Recent Multi-Modal Large Language Models (MLLMs) have demonstrated strong capabilities in learning joint representations from text and images. However, their spatial reasoning remains limited. We introduce 3DFroMLLM, a n…

Image ClassificationSpatial Reasoning

Spatio-temporal Decoupled Knowledge Compensator for Few-Shot Action Recognition

2026-02-20 · Hongyu Qu, Xiangbo Shu, Rui Yan, Hailiang Gao 외 arxiv

Few-Shot Action Recognition (FSAR) is a challenging task that requires recognizing novel action categories with a few labeled videos. Recent works typically apply semantically coarse category names as auxiliary contexts …

Action Recognition

Multimodal Prototype-Enhanced Network for Few-Shot Action Recognition

2022-12-09 · Xinzhe Ni, Yong liu, Hao Wen, Yatai Ji 외

Current methods for few-shot action recognition mainly fall into the metric learning framework following ProtoNet, which demonstrates the importance of prototypes. Although they achieve relatively good performance, the e…

Action RecognitionFew-Shot action recognitionFew Shot Action RecognitionMetric Learning

Test-time Ego-Exo-centric Adaptation for Action Anticipation via Multi-Label Prototype Growing and Dual-Clue Consistency

2026-03-10 · Zhaofeng Shi, Heqian Qiu, Lanxiao Wang, Qingbo Wu 외 arxiv

Efficient adaptation between Egocentric (Ego) and Exocentric (Exo) views is crucial for applications such as human-robot cooperation. However, the success of most existing Ego-Exo adaptation methods relies heavily on tar…

Test-time AdaptationAction Anticipation

Locality-aware Concept Bottleneck Model

2025-08-20 · Sujin Jeon, Hyundo Lee, Eungseo Kim, Sanghack Lee 외 arxiv

Concept bottleneck models (CBMs) are inherently interpretable models that make predictions based on human-understandable visual cues, referred to as concepts. As obtaining dense concept annotations with human labeling is…