Webly Supervised Learning of Convolutional Networks
We present an approach to utilize large amounts of web data for learning CNNs. Specifically inspired by curriculum learning, we present a two-step approach for CNN training. First, we use easy images to train an initial visual representation. We then use this initial CNN and adapt it to harder, more realistic images by leveraging the structure of data and categories. We demonstrate that our two-stage CNN outperforms a fine-tuned CNN trained on ImageNet on Pascal VOC 2012. We also demonstrate the strength of webly supervised learning by localizing objects in web images and training a R-CNN style detector. It achieves the best performance on VOC 2007 where no VOC training data is used. Finally, we show our approach is quite robust to noise and performs comparably even when we use image search results from March 2013 (pre-CNN image search era).
Code (0)
등록된 구현이 없습니다.
Tasks
Image RetrievalSimilar Papers 제목 키워드 기반
Webly Supervised Fine-Grained Recognition: Benchmark Datasets and An Approach
Learning from the web can ease the extreme dependence of deep learning on large-scale manually labeled datasets. Especially for fine-grained recognition, which targets at distinguishing subordinate categories, it will si…
BenchmarkingImage to Video Domain Adaptation Using Web Supervision
Training deep neural networks typically requires large amounts of labeled data which may be scarce or expensive to obtain for a particular target domain. As an alternative, we can leverage webly-supervised data (i.e. res…
Domain AdaptationLearning without Prejudice: Avoiding Bias in Webly-Supervised Action Recognition
Webly-supervised learning has recently emerged as an alternative paradigm to traditional supervised learning based on large-scale datasets with manual annotations. The key idea is that models such as CNNs can be learned …
Action RecognitionOptical Flow EstimationTemporal Action LocalizationVideo UnderstandingMoPro: Webly Supervised Learning with Momentum Prototypes
We propose a webly-supervised representation learning method that does not suffer from the annotation unscalability of supervised learning, nor the computation unscalability of self-supervised learning. Most existing wor…
Contrastive Learningimage-classificationImage ClassificationRepresentation Learning+1Webly Supervised Multi-Label Recognition: Evaluation Benchmark and Dual-Branch Multi-Label Contrastive Learning
Training deep learning models with freely available web images can reduce their dependence on costly manual annotations. Although webly supervised learning has been widely studied for single-label recognition, its multi-…
Contrastive Learning