Weakly Supervised Cascaded Convolutional Networks

By Ali Diba, Vivek Sharma, Ali Mohammad Pazandeh, Hamed Pirsiavash, Luc Van Gool. 2016

312 citations recorded by the source corpus.

Object detection is a challenging task in visual understanding domain, and even more so if the supervision is to be weak. Recently, few efforts to handle the task without expensive human annotations is established by promising deep neural network. A new architecture of cascaded networks is proposed to learn a convolutional neural network (CNN) under such conditions. We introduce two such architectures, with either two cascade stages or three which are trained in an end-to-end pipeline. The first stage of both architectures extracts best candidate of class specific region proposals by training a fully convolutional network. In the case of the three stage architecture, the middle stage provides object segmentation, using the output of the activation maps of first stage. The final stage of both architectures is a part of a convolutional neural network that performs multiple instance learning on proposals extracted in the previous stage(s). Our experiments on the PASCAL VOC 2007, 2010, 2012 and large scale object datasets, ILSVRC 2013, 2014 datasets show improvements in the areas of weakly-supervised object detection, classification and localization.

Subfields: Artificial Intelligence, Computer Vision and Pattern Recognition, Representation & Self-Supervised Learning

How researchers see this paper

The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.

In Artificial Intelligence

In Computer Vision and Pattern Recognition

In Representation & Self-Supervised Learning

Citations in the corpus

Learning Open-World Object Proposals without Learning to Classify (2021, background): “Weakly-supervised approaches [5, 7, 17, 54, 62] aim to utilize abundant image-level labels and leverage classagnostic box proposals to build detectors.”
Incremental Few-Shot Object Detection (2020, neutral): “There are other techniques that aim to minimise the amount of data labelling for object detection such as weakly supervised learning [4, 10] and zero-shot learning [58, 37, 2].”
Few-Shot Object Detection via Feature Reweighting (2018, background): “The weakly-supervised setting [3, 7, 36] considers the problem of training object detectors with only image-level labels, but without bounding box annotations, which are more expensive to obtain.”
A Survey of Deep Learning-Based Object Detection (2019, methodology): “Context information [223], instance classifier refinement [224] and image segmentation [225], [226] are adopted to tackle hardly optimized problems.”
C-MIL: Continuation Multiple Instance Learning for Weakly Supervised Object Detection (2019, methodology): “With VGGF, C-MIL respectively outperformed the WCCN [14], OICR [34], and MELM [37] by 3.”
LSTD: A Low-Shot Transfer Detector for Object Detection (2018, methodology): “In this case, weakly-supervised (Diba et al. 2016; Kantorov et al. 2016; Bilen and Vedaldi 2016; Li et al. 2016; Cinbis, Verbeek, and Schmid 2017; Tang et al. 2017) or semi-supervised approaches (Tang et al. 2016; Singh, Xiao, and Lee 2016; Liang et al. 2016; Dong et al. 2017) can be used to…”
W-TALC: Weakly-supervised Temporal Activity Localization and Classification (2018, background): “On the other hand, end-to-end learning with categorical loss functions are presented in [15,16,13,47] and recently, the authors in [71] incorporated the proposal generation network in an end-to-end manner.”
Weakly Supervised Object Localization and Detection: A Survey (2021, unknown): “The whole weakly supervised learning framework may be designed in a compact network model, such as in [46], [76], [101], [106], [117], [180], [182], [204], [219], [221], or contain several function-distinct DNN components, such as in [27], [98], [140], [160], [172], [193], [209].”
Small Sample Learning in Big Data Era (2018, methodology): “The method can achieve competitive performance compared to state-of-the-art weakly supervised object detection approaches (Diba et al., 2017), with only requirement of about 1% of the images in the the entire dataset to be annotated.”
Few-Shot Object Detection and Viewpoint Estimation for Objects in the Wild (2020, background): “Object detection with limited labeled samples is also addressed by approaches targeting weak supervision [49, 5, 6, 47] and zero-shot learning [3, 40, 66], but these settings are different from ours.”
PCL: Proposal Cluster Learning for Weakly Supervised Object Detection (2018, methodology): “, ensemble of models) [17], [19], [43], [54].”
Deep Learning for Generic Object Detection: A Survey (2018, methodology): “rvised learning is not scalable in the absence of fully labelled training data, therefore it is valuable to study how the power of CNNs can be leveraged in weakly supervised or unsupervised detection [15,45,187]. (8) 3D Object Detection: The progress of depth cameras has enabled the acquisition of d”
Attention-Based Dropout Layer for Weakly Supervised Object Localization (2019, background): “Existing approaches mine and track discriminative features of each class for object detection [45, 36, 37, 9, 45, 25, 21, 41, 19, 2, 39, 15, 63, 7, 5, 4, 48, 14, 65, 32, 31, 58, 62, 8, 6] and segmentation [33, 29, 18, 16, 24, 52, 50].”
C-MIDN: Coupled Multiple Instance Detection Network With Segmentation Guidance for Weakly Supervised Object Detection (2019, methodology): “Some methods propose to leverage Weakly Supervised Semantic Segmentation to improve WSOD [12, 9, 40].”
Self-produced Guidance for Weakly-supervised Object Localization (2018, background): “Diba et al. [34] proposed the attention maps can be leveraged to produce region proposals.”
Deep Learning for Computer Vision: A Brief Review (2018, background): “(in which a new def-pooling layer and new learning strategy are proposed), [9] (weakly supervised cascaded CNNs), and [69] (subcategory-aware CNNs).”
Comprehensive Attention Self-Distillation for Weakly-Supervised Object Detection (2020, background): “[14] and [15] leverage segmentation maps to generate instance proposals with rich contextual information.”
SIXray: A Large-Scale Security Inspection X-Ray Benchmark for Prohibited Item Discovery in Overlapping Images (2019, background): “This is related to the research in weakly-supervised object localization [3] [6] [33], or a series of work in localizing objects using top-down class activation [8] [7] [40].”