Min-Entropy Latent Model for Weakly Supervised Object Detection

By Fang Wan, Pengxu Wei, Jianbin Jiao, Zhenjun Han, Qixiang Ye. 2018

230 citations recorded by the source corpus.

Weakly supervised object detection is a challenging task when provided with image category supervision but required to learn, at the same time, object locations and object detectors. The inconsistency between the weak supervision and learning objectives introduces randomness to object locations and ambiguity to detectors. In this paper, a min-entropy latent model (MELM) is proposed for weakly supervised object detection. Min-entropy is used as a metric to measure the randomness of object localization during learning, as well as serving as a model to learn object locations. It aims to principally reduce the variance of positive instances and alleviate the ambiguity of detectors. MELM is deployed as two sub-models, which respectively discovers and localizes objects by minimizing the global and local entropy. MELM is unified with feature learning and optimized with a recurrent learning algorithm, which progressively transfers the weak supervision to object locations. Experiments demonstrate that MELM significantly improves the performance of weakly supervised detection, weakly supervised localization, and image classification, against the state-of-the-art approaches.

Subfields: Artificial Intelligence, Computer Vision and Pattern Recognition

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

1. Qixiang Ye
2. Tal Hakim
3. Rami Ben-Ari
4. Wei Ke
5. L. Jiao
6. Rong Qu
7. Chi Su
8. Yalin Zheng

In Computer Vision and Pattern Recognition

1. Qixiang Ye
2. Jianbin Jiao
3. Lingxi Xie
4. Yi Yang
5. Xiangyang Ji
6. Chang Liu
7. Chi Su
8. A. Bronstein

Citations in the corpus

• Attention on Attention for Image Captioning (2019, methodology): “Earlier approaches to image captioning are rule/template-based [48, 34] which generate slotted caption templates and use the outputs of object detection [30, 39, 38], attribute prediction and scene recognition to fill in the slots.”
• DTFD-MIL: Double-Tier Feature Distillation Multiple Instance Learning for Histopathology Whole Slide Image Classification (2022, background): “For example, one notable capability of CAM is the target localization of a model trained only with image labels; therefore, it prevails in weakly supervised tasks, such as segmentation [4, 13, 16, 43] and detection [38,45,50], or even knowledge distillation [39].”
• C-MIL: Continuation Multiple Instance Learning for Weakly Supervised Object Detection (2019, methodology): “In [37], a recurrent learning algorithm was proposed to integrate image classification with object detection, and then to progressively optimize the classifiers and detectors.”
• Toward Self-Supervised Object Detection in Unlabeled Videos (2019, background): “The task is similar to weakly supervised object detection (WSOD), yet is distinct from it in the high level of label noise.”
• SIXray: A Large-Scale Security Inspection X-Ray Benchmark for Prohibited Item Discovery in Overlapping Images (2019, background): “There were also efforts about formulating the object localization in multiple instance learning frameworks where convolutional filters behave as detectors which activate regions of interest on the feature maps [3] [37] [33] [35].”
• A Survey of Deep Learning-Based Object Detection (2019, methodology): “[228] design a min-entropy latent model optimized with a recurrent learning algorithm for weakly supervised object detection.”
• Learning to Match Anchors for Visual Object Detection (2021, background): “To represent objects of various appearance, aspect ratios and poses with limited convolutional features, many CNN-based detectors leverage anchor boxes as reference points for object localization [1]–[7], [9], [10].”
• Weakly Supervised Object Localization and Detection: A Survey (2021, unknown): “Wan et al. [155] propose a min-entropy latent model (MELM) for weakly supervised object detection based on the assumption that minimizing entropy results in minimum randomness of a sys-tem.”
• Mixed supervision for surface-defect detection: from weakly to fully supervised learning (2021, unknown): “Weakly supervised learning Various weakly supervised deep-learning approaches have been developed in the context of semantic segmentation and object detection [26, 29, 2, 16, 37, 36].”
• Weakly Supervised Instance Segmentation Using Class Peak Response (2018, methodology): “Previous works usually involve time-consuming training strategies, e.g ., repeatedly model learning [40] or online proposal selection [29, 39].”
• C-MIDN: Coupled Multiple Instance Detection Network With Segmentation Guidance for Weakly Supervised Object Detection (2019, unknown): “Multiple Instance Detection Network In recent years, many end-to-end frameworks have been proposed to combine MIL and CNN [4, 31, 30, 15, 42, 36, 35, 34, 37, 25, 32, 9].”