paper-with-me

홈 › Papers

Similarity Maps for Self-Training Weakly-Supervised Phrase Grounding

2023-01-01 · CVPR 2023 1 · Tal Shaharabany, Lior Wolf

A phrase grounding model receives an input image and a text phrase and outputs a suitable localization map. We present an effective way to refine a phrase ground model by considering self-similarity maps extracted from the latent representation of the model's image encoder. Our main insights are that these maps resemble localization maps and that by combining such maps, one can obtain useful pseudo-labels for performing self-training. Our results surpass, by a large margin, the state-of-the-art in weakly supervised phrase grounding. A similar gap in performance is obtained for a recently proposed downstream task called WWbL, in which the input image is given without any text. Our code is available as supplementary.

📄 PDF Abstract BibTeX

Code (1)

talshaharabany/similarity-maps-for-self-training-weakly-supervised-phrase-grounding 공식 구현

Tasks

Phrase Grounding

Similar Papers 제목 키워드 기반

Unsupervised Object Localization with Representer Point Selection

2023-09-08 · ICCV 2023 1 · Yeonghwan Song, Seokwoo Jang, Dina Katabi, Jeany Son

We propose a novel unsupervised object localization method that allows us to explain the predictions of the model by utilizing self-supervised pre-trained models without additional finetuning. Existing unsupervised and s…

ObjectObject LocalizationUnsupervised Object Localization

Generating Self-Guided Dense Annotations for Weakly Supervised Semantic Segmentation

2018-10-16 · Zi-Yi Ke, Chiou-Ting Hsu

Learning semantic segmentation models under image-level supervision is far more challenging than under fully supervised setting. Without knowing the exact pixel-label correspondence, most weakly-supervised methods rely o…

SegmentationSemantic SegmentationWeakly supervised Semantic SegmentationWeakly-Supervised Semantic Segmentation

A Self-Training Framework Based on Multi-Scale Attention Fusion for Weakly Supervised Semantic Segmentation

2023-05-10 · Guoqing Yang, Chuang Zhu, Yu Zhang

Weakly supervised semantic segmentation (WSSS) based on image-level labels is challenging since it is hard to obtain complete semantic regions. To address this issue, we propose a self-training method that utilizes fused…

DenoisingSemantic SegmentationWeakly supervised Semantic SegmentationWeakly-Supervised Semantic Segmentation

Self-Supervised Transformers for Unsupervised Object Discovery using Normalized Cut

2022-02-23 · CVPR 2022 1 · Yangtao Wang, Xi Shen, Shell Hu, Yuan Yuan 외

Transformers trained with self-supervised learning using self-distillation loss (DINO) have been shown to produce attention maps that highlight salient foreground objects. In this paper, we demonstrate a graph-based appr…

Objectobject-detectionObject DetectionObject Discovery+5

MapRF: Weakly Supervised Online HD Map Construction via NeRF-Guided Self-Training

2025-11-24 · Hongyu Lyu, Thomas Monninger, Julie Stephany Berrio Perez, Mao Shan 외 arxiv

Autonomous driving systems benefit from high-definition (HD) maps that provide critical information about road infrastructure. The online construction of HD maps offers a scalable approach to generate local maps from on-…

Autonomous Driving