paper-with-me

Papers

Triplet Knowledge Distillation

2023-05-25 · Xijun Wang, Dongyang Liu, Meina Kan, Chunrui Han, Zhongqin Wu, Shiguang Shan

In Knowledge Distillation, the teacher is generally much larger than the student, making the solution of the teacher likely to be difficult for the student to learn. To ease the mimicking difficulty, we introduce a triplet knowledge distillation mechanism named TriKD. Besides teacher and student, TriKD employs a third role called anchor model. Before distillation begins, the pre-trained anchor model delimits a subspace within the full solution space of the target problem. Solutions within the subspace are expected to be easy targets that the student could mimic well. Distillation then begins in an online manner, and the teacher is only allowed to express solutions within the aforementioned subspace. Surprisingly, benefiting from accurate but easy-to-mimic hints, the student can finally perform well. After the student is well trained, it can be used as the new anchor for new students, forming a curriculum learning strategy. Our experiments on image classification and face recognition with various models clearly demonstrate the effectiveness of our method. Furthermore, the proposed TriKD is also effective in dealing with the overfitting issue. Moreover, our theoretical analysis supports the rationality of our triplet distillation.

📄 PDF Abstract BibTeX arXiv:2305.15975

Code (0)

등록된 구현이 없습니다.

Tasks

Face Recognitionimage-classificationImage ClassificationKnowledge DistillationTriplet

Methods 이 논문이 사용한 방법론

Knowledge Distillation A very simple way to improve the performance of almost any machine learning algorithm is to train many different models on the same data and then to average their predictions.…

Similar Papers 제목 키워드 기반

Teacher-Student Training and Triplet Loss to Reduce the Effect of Drastic Face Occlusion

2021-11-20 · Mariana-Iuliana Georgescu, Georgian Duta, Radu Tudor Ionescu

We study a series of recognition tasks in two realistic scenarios requiring the analysis of faces under strong occlusion. On the one hand, we aim to recognize facial expressions of people wearing Virtual Reality (VR) hea…

Age EstimationFacial Expression RecognitionFacial Expression Recognition (FER)Knowledge Distillation+1

Triplet Loss for Knowledge Distillation

2020-04-17 · Hideki Oki, Motoshi Abe, Junichi Miyao, Takio Kurita

In recent years, deep learning has spread rapidly, and deeper, larger models have been proposed. However, the calculation cost becomes enormous as the size of the models becomes larger. Various techniques for compressing…

Knowledge DistillationMetric LearningTriplet

Teacher-Student Training and Triplet Loss for Facial Expression Recognition under Occlusion

2020-08-03 · Mariana-Iuliana Georgescu, Radu Tudor Ionescu

In this paper, we study the task of facial expression recognition under strong occlusion. We are particularly interested in cases where 50% of the face is occluded, e.g. when the subject wears a Virtual Reality (VR) head…

Facial Expression RecognitionFacial Expression Recognition (FER)Knowledge DistillationTriplet

Distilling GANs with Style-Mixed Triplets for X2I Translation with Limited Data

2021-09-29 · ICLR 2022 4 · Yaxing Wang, Joost Van de Weijer, Lu Yu, Shangling Jui

Conditional image synthesis is an integral part of many X2I translation systems, including image-to-image, text-to-image and audio-to-image translation systems. Training these large systems generally requires huge amount…

Image GenerationKnowledge DistillationSemantic SegmentationTranslation

A Recipe for Efficient SBIR Models: Combining Relative Triplet Loss with Batch Normalization and Knowledge Distillation

2023-05-30 · Omar Seddati, Nathan Hubens, Stéphane Dupont, Thierry Dutoit

Sketch-Based Image Retrieval (SBIR) is a crucial task in multimedia retrieval, where the goal is to retrieve a set of images that match a given sketch query. Researchers have already proposed several well-performing solu…

Data AugmentationImage RetrievalKnowledge DistillationRetrieval+2