Search Results for author:
Found 12 papers, 8 papers with code
Fed-GraB: Federated Long-tailed Learning with Self-Adjusting Gradient Balancer
Data privacy and long-tailed distribution are the norms rather than the exception in many real-world tasks.
Robustness-Guided Image Synthesis for Data-Free Quantization
Quantization has emerged as a promising direction for model compression.
Towards Distribution-Agnostic Generalized Category Discovery
In this paper, we formally define a more realistic task as distribution-agnostic generalized category discovery (DA-GCD): generating fine-grained predictions for both close- and open-set classes in a long-tailed open-world setting.
Uniformly Distributed Category Prototype-Guided Vision-Language Framework for Long-Tail Recognition
Category prototype-guided mechanism for image-text matching makes the features of different classes converge to these distinct and uniformly distributed category prototypes, which maintain a uniform distribution in the feature space, and improve class boundaries.
CLIPN for Zero-Shot OOD Detection: Teaching CLIP to Say No
Subsequently, we introduce two loss functions: the image-text binary-opposite loss and the text semantic-opposite loss, which we use to teach CLIPN to associate images with no prompts, thereby enabling it to identify unknown samples.
Federated Model Aggregation via Self-Supervised Priors for Highly Imbalanced Medical Image Classification
Existing federated methods under highly imbalanced datasets primarily focus on optimizing a global model without incorporating the intra-class variations that can arise in medical imaging due to different populations, findings, and scanners.
On the Effectiveness of Out-of-Distribution Data in Self-Supervised Long-Tail Learning
Recent work shows that the long-tailed learning performance could be boosted by sampling extra in-domain (ID) data for self-supervised training, however, large-scale ID data which can rebalance the minority classes are expensive to collect.
CLIP Surgery for Better Explainability with Enhancement in Open-Vocabulary Tasks
Contrastive Language-Image Pre-training (CLIP) is a powerful multimodal large vision model that has demonstrated significant benefits for downstream tasks, including many zero-shot learning and text-guided vision tasks.
Ranked #2 on
Open Vocabulary Semantic Segmentation
on COCO-Stuff-171
(mIoU metric)
Interactive Segmentation
Open Vocabulary Semantic Segmentation
+4
FreeSeg: Free Mask from Interpretable Contrastive Language-Image Pretraining for Semantic Segmentation
We call the proposed framework as FreeSeg, where the mask is freely available from raw feature map of pretraining model.
Exploring Visual Interpretability for Contrastive Language-Image Pre-training
For this problem, we propose the Explainable Contrastive Language-Image Pre-training (ECLIP), which corrects the explainability via the Masked Max Pooling.
Towards Calibrated Hyper-Sphere Representation via Distribution Overlap Coefficient for Long-tailed Learning
To our knowledge, this is the first work to measure representation quality of classifiers and features from the perspective of distribution overlap coefficient.
Towards Federated Long-Tailed Learning
Data privacy and class imbalance are the norm rather than the exception in many machine learning tasks.
