Multi-Label Image Classification via Knowledge Distillation from Weakly-Supervised Detection

By Yongcheng Liu, Lu Sheng, Jing Shao, Junjie Yan, Shiming Xiang, Chunhong Pan. 2018

130 citations recorded by the source corpus.

Multi-label image classification is a fundamental but challenging task towards general visual understanding. Existing methods found the region-level cues (e.g., features from RoIs) can facilitate multi-label classification. Nevertheless, such methods usually require laborious object-level annotations (i.e., object labels and bounding boxes) for effective learning of the object-level visual features. In this paper, we propose a novel and efficient deep framework to boost multi-label classification by distilling knowledge from weakly-supervised detection task without bounding box annotations. Specifically, given the image-level annotations, (1) we first develop a weakly-supervised detection (WSD) model, and then (2) construct an end-to-end multi-label image classification framework augmented by a knowledge distillation module that guides the classification model by the WSD model according to the class-level predictions for the whole image and the object-level visual features for object RoIs. The WSD model is the teacher model and the classification model is the student model. After this cross-task knowledge distillation, the performance of the classification model is significantly improved and the efficiency is maintained since the WSD model can be safely discarded in the test phase. Extensive experiments on two large-scale datasets (MS-COCO and NUS-WIDE) show that our framework achieves superior performances over the state-of-the-art methods on both performance and efficiency.

Subfields: Artificial Intelligence, Computer Vision and Pattern Recognition, Molecular Biology

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 Molecular Biology

Citations in the corpus

Elucidating image-to-set prediction: An analysis of models, losses and datasets (2019, methodology): “2018 [35] VGG 3 82081 n/a 40137 n/a 74.”
Imbalanced Continual Learning with Partitioning Reservoir Sampling (2020, background): “In recent multi-label image classification [84,87,54,88,33], it is a common practice to fine-tune a pre-trained model to a target dataset.”
The Emerging Trends of Multi-Label Learning (2020, background): “Instead of requiring laborious object-level annotations, [143] proposes to distill knowl-”
Learning Semantic-Specific Graph Representation for Multi-Label Image Recognition (2019, unknown): “0 - - - - - KD-WSD [20] 74.”
More Grounded Image Captioning by Distilling Image-Text Matching Model (2020, methodology): “To this end, we propose a novel knowledge distillation [15, 34, 63] approach to regularize the visual attention in captioner, by treating an image-text matching model as a weak supervision of grounding [19, 48].”
CKD: Cross-Task Knowledge Distillation for Text-to-Image Synthesis (2020, background): “[42] propose a deep framework to boost multi-label classification by distilling knowledge from weakly-supervised detection task, which is a cross-task distillation process.”
Asymmetric Loss For Multi-Label Classification (2020, methodology): “For testing ASL on object detection, we used the MS-COCO [20] dataset (object detection task), which contains a training set of 118k images, and an evaluation set of 5k images.”
Deep Streaming Label Learning (2020, methodology): “, 2019), image classification (Liu et al., 2018), machine translation (Zhou et al.”