Jinlu Liu

Jinlu Liu, Liang Song, Yongqiang Qin

Few-shot segmentation is a challenging task that aims to segment objects of new classes given scarce support images. In the inductive setting, existing prototype-based methods focus on extracting prototypes from the support images; however, they fail to utilize semantic information of the query images. In this paper, we propose Bi-level Optimization (BiOpt), which succeeds to compute class prototypes from the query images under inductive setting. The learning procedure of BiOpt is decomposed into two nested loops: inner and outer loop. On each task, the inner loop aims to learn optimized prototypes from the query images. An init step is conducted to fully exploit knowledge from both support and query features, so as to give reasonable initialized prototypes into the inner loop. The outer loop aims to learn a discriminative embedding space across different tasks. Extensive experiments on two benchmarks verify the superiority of our proposed BiOpt algorithm. In particular, we consistently achieve the state-of-the-art performance on 5-shot PASCAL-$5^i$ and 1-shot COCO-$20^i$.

Jinlu Liu, Yongqiang Qin

Few-shot segmentation targets to segment new classes with few annotated images provided. It is more challenging than traditional semantic segmentation tasks that segment known classes with abundant annotated images. In this paper, we propose a Prototype Refinement Network (PRNet) to attack the challenge of few-shot segmentation. It firstly learns to bidirectionally extract prototypes from both support and query images of the known classes. Furthermore, to extract representative prototypes of the new classes, we use adaptation and fusion for prototype refinement. The step of adaptation makes the model to learn new concepts which is directly implemented by retraining. Prototype fusion is firstly proposed which fuses support prototypes with query prototypes, incorporating the knowledge from both sides. It is effective in prototype refinement without importing extra learnable parameters. In this way, the prototypes become more discriminative in low-data regimes. Experiments on PASAL-$5^i$ and COCO-$20^i$ demonstrate the superiority of our method. Especially on COCO-$20^i$, PRNet significantly outperforms existing methods by a large margin of 13.1\% in 1-shot setting.

Liang Song, Jinlu Liu, Yongqiang Qin

Many Few-Shot Learning research works have two stages: pre-training base model and adapting to novel model. In this paper, we propose to use closed-form base learner, which constrains the adapting stage with pre-trained base model to get better generalized novel model. Following theoretical analysis proves its rationality as well as indication of how to train a well-generalized base model. We then conduct experiments on four benchmarks and achieve state-of-the-art performance in all cases. Notably, we achieve the accuracy of 87.75% on 5-shot miniImageNet which approximately outperforms existing methods by 10%.

Gang Yang, Jinlu Liu, Xirong Li

Zero-shot learning (ZSL) which aims to recognize unseen classes with no labeled training sample, efficiently tackles the problem of missing labeled data in image retrieval. Nowadays there are mainly two types of popular methods for ZSL to recognize images of unseen classes: probabilistic reasoning and feature projection. Different from these existing types of methods, we propose a new method: sample construction to deal with the problem of ZSL. Our proposed method, called Imagination Based Sample Construction (IBSC), innovatively constructs image samples of target classes in feature space by mimicking human associative cognition process. Based on an association between attribute and feature, target samples are constructed from different parts of various samples. Furthermore, dissimilarity representation is employed to select high-quality constructed samples which are used as labeled data to train a specific classifier for those unseen classes. In this way, zero-shot learning is turned into a supervised learning problem. As far as we know, it is the first work to construct samples for ZSL thus, our work is viewed as a baseline for future sample construction methods. Experiments on four benchmark datasets show the superiority of our proposed method.