Boosting Discriminative Visual Representation Learning with
Scenario-Agnostic Mixup
- URL: http://arxiv.org/abs/2111.15454v3
- Date: Tue, 23 May 2023 17:51:28 GMT
- Title: Boosting Discriminative Visual Representation Learning with
Scenario-Agnostic Mixup
- Authors: Siyuan Li, Zicheng Liu, Zedong Wang, Di Wu, Zihan Liu, Stan Z. Li
- Abstract summary: We propose textbfScenario-textbfAgnostic textbfMixup (SAMix) for both Self-supervised Learning (SSL) and supervised learning (SL) scenarios.
Specifically, we hypothesize and verify the objective function of mixup generation as optimizing local smoothness between two mixed classes.
A label-free generation sub-network is designed, which effectively provides non-trivial mixup samples and improves transferable abilities.
- Score: 54.09898347820941
- License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
- Abstract: Mixup is a well-known data-dependent augmentation technique for DNNs,
consisting of two sub-tasks: mixup generation and classification. However, the
recent dominant online training method confines mixup to supervised learning
(SL), and the objective of the generation sub-task is limited to selected
sample pairs instead of the whole data manifold, which might cause trivial
solutions. To overcome such limitations, we comprehensively study the objective
of mixup generation and propose \textbf{S}cenario-\textbf{A}gnostic
\textbf{Mix}up (SAMix) for both SL and Self-supervised Learning (SSL)
scenarios. Specifically, we hypothesize and verify the objective function of
mixup generation as optimizing local smoothness between two mixed classes
subject to global discrimination from other classes. Accordingly, we propose
$\eta$-balanced mixup loss for complementary learning of the two
sub-objectives. Meanwhile, a label-free generation sub-network is designed,
which effectively provides non-trivial mixup samples and improves transferable
abilities. Moreover, to reduce the computational cost of online training, we
further introduce a pre-trained version, SAMix$^\mathcal{P}$, achieving more
favorable efficiency and generalizability. Extensive experiments on nine SL and
SSL benchmarks demonstrate the consistent superiority and versatility of SAMix
compared with existing methods.
Related papers
- ItTakesTwo: Leveraging Peer Representations for Semi-supervised LiDAR Semantic Segmentation [24.743048965822297]
This paper introduces a novel semi-supervised LiDAR semantic segmentation framework called ItTakesTwo (IT2)
IT2 is designed to ensure consistent predictions from peer LiDAR representations, thereby improving the perturbation effectiveness in consistency learning.
Results on public benchmarks show that our approach achieves remarkable improvements over the previous state-of-the-art (SOTA) methods in the field.
arXiv Detail & Related papers (2024-07-09T18:26:53Z) - BECLR: Batch Enhanced Contrastive Few-Shot Learning [1.450405446885067]
Unsupervised few-shot learning aspires to bridge this gap by discarding the reliance on annotations at training time.
We propose a novel Dynamic Clustered mEmory (DyCE) module to promote a highly separable latent representation space.
We then tackle the, somehow overlooked yet critical, issue of sample bias at the few-shot inference stage.
arXiv Detail & Related papers (2024-02-04T10:52:43Z) - Semi-Supervised Class-Agnostic Motion Prediction with Pseudo Label
Regeneration and BEVMix [59.55173022987071]
We study the potential of semi-supervised learning for class-agnostic motion prediction.
Our framework adopts a consistency-based self-training paradigm, enabling the model to learn from unlabeled data.
Our method exhibits comparable performance to weakly and some fully supervised methods.
arXiv Detail & Related papers (2023-12-13T09:32:50Z) - Learning with Noisy Labels Using Collaborative Sample Selection and
Contrastive Semi-Supervised Learning [76.00798972439004]
Collaborative Sample Selection (CSS) removes noisy samples from identified clean set.
We introduce a co-training mechanism with a contrastive loss in semi-supervised learning.
arXiv Detail & Related papers (2023-10-24T05:37:20Z) - Expeditious Saliency-guided Mix-up through Random Gradient Thresholding [89.59134648542042]
Mix-up training approaches have proven to be effective in improving the generalization ability of Deep Neural Networks.
In this paper, inspired by the superior qualities of each direction over one another, we introduce a novel method that lies at the junction of the two routes.
We name our method R-Mix following the concept of "Random Mix-up"
In order to address the question of whether there exists a better decision protocol, we train a Reinforcement Learning agent that decides the mix-up policies.
arXiv Detail & Related papers (2022-12-09T14:29:57Z) - Trash to Treasure: Harvesting OOD Data with Cross-Modal Matching for
Open-Set Semi-Supervised Learning [101.28281124670647]
Open-set semi-supervised learning (open-set SSL) investigates a challenging but practical scenario where out-of-distribution (OOD) samples are contained in the unlabeled data.
We propose a novel training mechanism that could effectively exploit the presence of OOD data for enhanced feature learning.
Our approach substantially lifts the performance on open-set SSL and outperforms the state-of-the-art by a large margin.
arXiv Detail & Related papers (2021-08-12T09:14:44Z) - Mixture-based Feature Space Learning for Few-shot Image Classification [6.574517227976925]
We propose to model base classes with mixture models by simultaneously training the feature extractor and learning the mixture model parameters in an online manner.
Results in a richer and more discriminative feature space which can be employed to classify novel examples from very few samples.
arXiv Detail & Related papers (2020-11-24T03:16:27Z) - Revisiting LSTM Networks for Semi-Supervised Text Classification via
Mixed Objective Function [106.69643619725652]
We develop a training strategy that allows even a simple BiLSTM model, when trained with cross-entropy loss, to achieve competitive results.
We report state-of-the-art results for text classification task on several benchmark datasets.
arXiv Detail & Related papers (2020-09-08T21:55:22Z)
This list is automatically generated from the titles and abstracts of the papers in this site.
This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.