Weakly-Supervised Object Localization

75 papers with code • 8 benchmarks • 3 datasets

Weakly supervised object localization (WSOL) learns to localize objects with only image-level labels, no object level labels (bonding boxes, etc.,) is needed. It is more attractive since image-level labels are much easier and cheaper to obtain.

Libraries

Use these libraries to find Weakly-Supervised Object Localization models and implementations

CAM Back Again: Large Kernel CNNs from a Weakly Supervised Object Localization Perspective

snskysk/cam-back-again 11 Mar 2024

The reason for the high-performance of large kernel CNNs in downstream tasks has been attributed to the large effective receptive field (ERF) produced by large size kernels, but this view has not been fully tested.

3
11 Mar 2024

DiPS: Discriminative Pseudo-Label Sampling with Self-Supervised Transformers for Weakly Supervised Object Localization

shakeebmurtaza/dips 9 Oct 2023

Subsequently, these proposals are used as pseudo-labels to train our new transformer-based WSOL model designed to perform classification and localization tasks.

1
09 Oct 2023

Background Activation Suppression for Weakly Supervised Object Localization and Semantic Segmentation

wpy1999/bas 22 Sep 2023

In addition, our method also achieves state-of-the-art weakly supervised semantic segmentation performance on the PASCAL VOC 2012 and MS COCO 2014 datasets.

42
22 Sep 2023

FDCNet: Feature Drift Compensation Network for Class-Incremental Weakly Supervised Object Localization

Vision-sejin/FDCNet 17 Sep 2023

To the best of our knowledge, we are the first to address this task.

11
17 Sep 2023

Generative Prompt Model for Weakly Supervised Object Localization

callsys/genpromp ICCV 2023

During training, GenPromp converts image category labels to learnable prompt embeddings which are fed to a generative model to conditionally recover the input image with noise and learn representative embeddings.

51
19 Jul 2023

Open-World Weakly-Supervised Object Localization

ryylcc/owsol 17 Apr 2023

To handle such data, we propose a novel paradigm of contrastive representation co-learning using both labeled and unlabeled data to generate a complete G-CAM (Generalized Class Activation Map) for object localization, without the requirement of bounding box annotation.

14
17 Apr 2023

Spatial-Aware Token for Weakly Supervised Object Localization

wpy1999/sat ICCV 2023

Specifically, a spatial token is first introduced in the input space to aggregate representations for localization task.

15
18 Mar 2023

Knowledge-guided Causal Intervention for Weakly-supervised Object Localization

shaofeifei11/kd-ci-cam 3 Jan 2023

Previous weakly-supervised object localization (WSOL) methods aim to expand activation map discriminative areas to cover the whole objects, yet neglect two inherent challenges when relying solely on image-level labels.

6
03 Jan 2023

Adversarial Normalization: I Can Visualize Everything (ICE)

hanyang-hcc-lab/ice CVPR 2023

Vision transformers use [CLS] tokens to predict image classes.

1
01 Jan 2023

Expeditious Saliency-guided Mix-up through Random Gradient Thresholding

minhlong94/random-mixup 9 Dec 2022

Mix-up training approaches have proven to be effective in improving the generalization ability of Deep Neural Networks.

8
09 Dec 2022