Papers Self-Supervised Image Classification
“Self-Supervised Image Classification” 태그가 달린 논문 110편 · 필터 해제
Stabilize the Latent Space for Image Autoregressive Modeling: A Unified Perspective
Latent-based image generative models, such as Latent Diffusion Models (LDMs) and Mask Image Models (MIMs), have achieved notable success in image generation tasks. These models typically leverage reconstructive autoencod…
Conditional Image GenerationImage GenerationLinear-Probe ClassificationSelf-Supervised Image Classification+2SynCo: Synthetic Hard Negatives in Contrastive Learning for Better Unsupervised Visual Representations
Contrastive learning has become a dominant approach in self-supervised visual representation learning. Hard negatives - samples closely resembling the anchor - are key to enhancing learned representations' discriminative…
Contrastive LearningImage ClassificationImage SegmentationInstance Segmentation+8Unsupervised Representation Learning by Balanced Self Attention Matching
Many leading self-supervised methods for unsupervised representation learning, in particular those for embedding image features, are built on variants of the instance discrimination task, whose optimization is known to b…
Representation LearningSelf-Supervised Image ClassificationSelf-Supervised Image Classification on ImageNetTransfer LearningMulti-label Cluster Discrimination for Visual Representation Learning
Contrastive Language Image Pre-training (CLIP) has recently demonstrated success across various tasks due to superior feature representation empowered by image-text contrastive learning. However, the instance discriminat…
Contrastive LearningImage-text RetrievalMulti-Label ClassificationMUlTI-LABEL-ClASSIFICATION+8Estimating Physical Information Consistency of Channel Data Augmentation for Remote Sensing Images
The application of data augmentation for deep learning (DL) methods plays an important role in achieving state-of-the-art results in supervised, semi-supervised, and self-supervised image classification. In particular, c…
Data Augmentationimage-classificationImage ClassificationMulti-Label Image Classification+1IPCL: Iterative Pseudo-Supervised Contrastive Learning to Improve Self-Supervised Feature Representation
Self-supervised learning with a contrastive batch approach has become a powerful tool for representation learning in computer vision. The performance of downstream tasks is proportional to the quality of visual features …
Contrastive LearningData Augmentationimage-classificationImage Classification+5MIM-Refiner: A Contrastive Learning Boost from Intermediate Pre-Trained Representations
We introduce MIM (Masked Image Modeling)-Refiner, a contrastive learning boost for pre-trained MIM models. MIM-Refiner is motivated by the insight that strong representations within MIM models generally reside in interme…
Contrastive LearningImage ClusteringSelf-Supervised Image ClassificationSemantic SegmentationPerceptual Group Tokenizer: Building Perception with Iterative Grouping
Human visual recognition system shows astonishing capability of compressing visual information into a set of tokens containing rich representations without label supervision. One critical driving principle behind it is p…
Representation LearningSelf-Supervised Image ClassificationSelf-Supervised LearningSuperpixelsVision Transformers Need Registers
Transformers have recently emerged as a powerful tool for learning visual representations. In this paper, we identify and characterize artifacts in feature maps of both supervised and self-supervised ViT networks. The ar…
Object DiscoverySelf-Supervised Image ClassificationMasked Image Residual Learning for Scaling Deeper Vision Transformers
Deeper Vision Transformers (ViTs) are more challenging to train. We expose a degradation problem in deeper layers of ViT when using masked image modeling (MIM) for pre-training. To ease the training of deeper ViTs, we in…
Image Classificationobject-detectionObject DetectionSelf-Supervised Image Classification+2DINO-CXR: A self supervised method based on vision transformer for chest X-ray classification
The limited availability of labeled chest X-ray datasets is a significant bottleneck in the development of medical imaging methods. Self-supervised learning (SSL) can mitigate this problem by training models on unlabeled…
COVID-19 DiagnosisImage ClassificationMedical Image AnalysisMedical Image Classification+4Masking meets Supervision: A Strong Learning Alliance
Pre-training with random masked inputs has emerged as a novel trend in self-supervised training. However, supervised learning still faces a challenge in adopting masking augmentations, primarily due to unstable training.…
Image ClassificationSelf-Supervised Image ClassificationTransfer LearningONE-PEACE: Exploring One General Representation Model Toward Unlimited Modalities
In this work, we explore a scalable way for building a general representation model toward unlimited modalities. We release ONE-PEACE, a highly extensible model with 4B parameters that can seamlessly align and integrate …
1 Image, 2*2 StitchiAction ClassificationAudioCapsAudio Classification+18Contrastive Tuning: A Little Help to Make Masked Autoencoders Forget
Masked Image Modeling (MIM) methods, like Masked Autoencoders (MAE), efficiently learn a rich representation of the input. However, for adapting to downstream tasks, they require a sufficient amount of labeled data since…
ClusteringContrastive LearningImage ClusteringSelf-Supervised Image ClassificationDINOv2: Learning Robust Visual Features without Supervision
The recent breakthroughs in natural language processing for model pretraining on large quantities of data have opened the way for similar foundation models in computer vision. These models could greatly simplify the use …
Depth EstimationDomain GeneralizationFine-Grained Image ClassificationImage Classification+5Unicom: Universal and Compact Representation Learning for Image Retrieval
Modern image retrieval methods typically rely on fine-tuning pre-trained encoders to extract image-level descriptors. However, the most widely used models are pre-trained on ImageNet-1K with limited classes. The pre-trai…
Image ClassificationImage RetrievalMetric LearningRepresentation Learning+3VNE: An Effective Method for Improving Deep Representation by Manipulating Eigenvalue Distribution
Since the introduction of deep learning, a wide scope of representation properties, such as decorrelation, whitening, disentanglement, rank, isotropy, and mutual information, have been studied to improve the quality of r…
DisentanglementDomain GeneralizationFew-Shot Image ClassificationGeneral Classification+7MV-MR: multi-views and multi-representations for self-supervised learning and knowledge distillation
We present a new method of self-supervised learning and knowledge distillation based on the multi-views and multi-representations (MV-MR). The MV-MR is based on the maximization of dependence between learnable embeddings…
ClusteringContrastive LearningKnowledge DistillationLinear evaluation+3All4One: Symbiotic Neighbour Contrastive Learning via Self-Attention and Redundancy Reduction
Nearest neighbour based methods have proved to be one of the most successful self-supervised learning (SSL) approaches due to their high generalization capabilities. However, their computational efficiency decreases when…
Computational EfficiencyContrastive LearningSelf-Supervised Image ClassificationSelf-Supervised LearningDesigning BERT for Convolutional Networks: Sparse and Hierarchical Masked Modeling
We identify and overcome two key obstacles in extending the success of BERT-style pre-training, or the masked image modeling, to convolutional networks (convnets): (i) convolution operation cannot handle irregular, rando…
2D Object DetectionContrastive LearningDecoderImage Classification+5