DLWL: Improving Detection for Lowshot Classes With Weakly Labelled Data

2020-06-01 · CVPR 2020 6 · Vignesh Ramanathan, Rui Wang, Dhruv Mahajan

Large detection datasets have a long tail of lowshot classes with very few bounding box annotations. We wish to improve detection for lowshot classes with weakly labelled web-scale datasets only having image-level labels. This requires a detection framework that can be jointly trained with limited number of bounding box annotated images and large number of weakly labelled images. Towards this end, we propose a modification to the FRCNN model to automatically infer label assignment for objects proposals from weakly labelled images during training. We pose this label assignment as a Linear Program with constraints on the number and overlap of object instances in an image. We show that this can be solved efficiently during training for weakly labelled images. Compared to just training with few annotated examples, augmenting with weakly labelled examples in our framework provides significant gains. We demonstrate this on the LVIS dataset 3.5 gain in AP as well as different lowshot variants of the COCO dataset. We provide a thorough analysis of the effect of amount of weakly labelled and fully labelled data required to train the detection model. Our DLWL framework can also outperform self-supervised baselines like omni-supervision for lowshot classes.

📄 PDF Abstract BibTeX

Code (0)

등록된 구현이 없습니다.

Bayesian Joint Modelling for Object Localisation in Weakly Labelled Images

2017-06-19 · Zhiyuan Shi, Timothy M. Hospedales, Tao Xiang

We address the problem of localisation of objects as bounding boxes in images and videos with weak labels. This weakly supervised object localisation problem has been tackled in the past using discriminative models where…

Domain Adaptation Object Transfer Learning

Data-Efficient Weakly Supervised Learning for Low-Resource Audio Event Detection Using Deep Learning

2018-07-17 · Veronica Morfi, Dan Stowell

We propose a method to perform audio event detection under the common constraint that only limited training data are available. In training a deep learning system to perform audio event detection, two practical problems …

Event Detection Weakly-supervised Learning

Bayesian Joint Topic Modelling for Weakly Supervised Object Localisation

2017-05-09 · Zhiyuan Shi, Timothy M. Hospedales, Tao Xiang

We address the problem of localisation of objects as bounding boxes in images with weak labels. This weakly supervised object localisation problem has been tackled in the past using discriminative models where each objec…

Object

Positive-Unlabelled Active Learning to Curate a Dataset for Orca Resident Interpretation

2026-02-10 · Bret Nestor, Bohan Yao, Jasmine Moore, Jasper Kanes arxiv

This work presents the largest curation of Southern Resident Killer Whale (SRKW) acoustic data to date, also containing other marine mammals in their environment. We systematically search all available public archival hy…

Unsupervised Machine Translation Active Learning

Multi-Task Learning for Interpretable Weakly Labelled Sound Event Detection

2020-08-17 · Soham Deshmukh, Bhiksha Raj, Rita Singh

Weakly Labelled learning has garnered lot of attention in recent years due to its potential to scale Sound Event Detection (SED) and is formulated as Multiple Instance Learning (MIL) problem. This paper proposes a Multi-…

Event Detection Multiple Instance Learning Multi-Task Learning Sound Event Detection+1