Learning Purified Feature Representations from Task-irrelevant Labels
Learning an empirically effective model with generalization using limited data is a challenging task for deep neural networks. In this paper, we propose a novel learning framework called PurifiedLearning to exploit task-irrelevant features extracted from task-irrelevant labels when training models on small-scale datasets. Particularly, we purify feature representations by using the expression of task-irrelevant information, thus facilitating the learning process of classification. Our work is built on solid theoretical analysis and extensive experiments, which demonstrate the effectiveness of PurifiedLearning. According to the theory we proved, PurifiedLearning is model-agnostic and doesn't have any restrictions on the model needed, so it can be combined with any existing deep neural networks with ease to achieve better performance. The source code of this paper will be available in the future for reproducibility.
Code (0)
등록된 구현이 없습니다.
Similar Papers 제목 키워드 기반
Denoise-then-Retrieve: Text-Conditioned Video Denoising for Video Moment Retrieval
Current text-driven Video Moment Retrieval (VMR) methods encode all video clips, including irrelevant ones, disrupting multimodal alignment and hindering optimization. To this end, we propose a denoise-then-retrieve para…
Moment RetrievalVideo DenoisingPowerful Speaker Embedding Training Framework by Adversarially Disentangled Identity Representation
The main challenge of speaker verification in the wild is the interference caused by irrelevant information in speech and the lack of speaker labels in speech datasets. In order to solve the above problems, we propose a …
Speaker VerificationSubspace Alignment for Vision-Language Model Test-time Adaptation
Vision-language models (VLMs), despite their extraordinary zero-shot capabilities, are vulnerable to distribution shifts. Test-time adaptation (TTA) emerges as a predominant strategy to adapt VLMs to unlabeled test data …
Test-time AdaptationTask-oriented Embedding Counts: Heuristic Clustering-driven Feature Fine-tuning for Whole Slide Image Classification
In the field of whole slide image (WSI) classification, multiple instance learning (MIL) serves as a promising approach, commonly decoupled into feature extraction and aggregation. In this paradigm, our observation revea…
Clusteringimage-classificationImage ClassificationMultiple Instance LearningLearning from Noisy Labels with Decoupled Meta Label Purifier
Training deep neural networks(DNN) with noisy labels is challenging since DNN can easily memorize inaccurate labels, leading to poor generalization ability. Recently, the meta-learning based label correction strategy is …
Image ClassificationMeta-LearningRepresentation Learning