thu-vis / Uni-Evaluator
A visual analysis tool to support a unified model evaluation for different computer vision tasks, including classification, object detection, and instance segmentation
☆14Updated 11 months ago
Related projects ⓘ
Alternatives and complementary repositories for Uni-Evaluator
- A word cloud package for web☆11Updated 6 years ago
- A web-based tool for analyzing out-of-distribution samples.☆42Updated last year
- A web-based tool for interative improving graph-based semi-supervised learning models☆26Updated 3 years ago
- A library of sampling algorithms☆72Updated last year
- Implementation of CDR - Interactive Visual Cluster Analysis by Contrastive Dimensionality Reduction☆21Updated last year
- ☆14Updated last year
- ☆35Updated 5 months ago
- Let the Chart Spark: Embedding Semantic Context into Chart with Text-to-Image Generative Model☆35Updated 5 months ago
- ☆12Updated 7 months ago
- ☆10Updated last year
- ncNet is a Transformer-based model for supporting NL2VIS.☆36Updated 2 months ago
- [Paper][AAAI2024]Structure-CLIP: Towards Scene Graph Knowledge to Enhance Multi-modal Structured Representations☆113Updated 4 months ago
- ☆16Updated 3 years ago
- A web-based tool for diagnosing ensemble few-shot classifiers☆15Updated 2 years ago
- XCurve is an end-to-end PyTorch library for X-Curve metrics optimizations in machine learning.☆141Updated last year
- [CVPR 2024] Official PyTorch Code for "PromptKD: Unsupervised Prompt Distillation for Vision-Language Models"☆230Updated last month
- [ICLR 23 oral] The Modality Focusing Hypothesis: Towards Understanding Crossmodal Knowledge Distillation☆39Updated last year
- ☆68Updated 3 years ago
- ☆43Updated 3 years ago
- ☆22Updated 8 months ago
- Awesome Learn From Model Beyond Fine-Tuning: A Survey☆49Updated 11 months ago
- [CVPR 2021] A Peek Into the Reasoning of Neural Networks: Interpreting with Structural Visual Concepts☆62Updated last year
- Multimodal Prompting with Missing Modalities for Visual Recognition, CVPR'23☆172Updated 10 months ago
- [ICLR2023] PLOT: Prompt Learning with Optimal Transport for Vision-Language Models☆145Updated 10 months ago
- About Code Release for "CLIPood: Generalizing CLIP to Out-of-Distributions" (ICML 2023), https://arxiv.org/abs/2302.00864☆59Updated last year
- A curated list of researches in object-centric learning☆11Updated 3 weeks ago
- Differences and similarities between TVCG and VIS papers. Also, crowdsourced submission data for TVCG. Enter anonymous submission data at…☆25Updated 2 years ago
- Vega-Zero is a sequence-based visualization grammar based on Vega-Lite.☆20Updated 2 months ago
- ☆16Updated 2 years ago
- [NeurIPS 2023] Generalized Logit Adjustment☆34Updated 6 months ago