2021Q1 | 🍎 Paper Today I Read 🦔

[153] Contrastive Explanations for Model Interpretability

2021Q1 XAI emnlp AI2

[147] Generic Attention-model Explainability for Interpreting Bi-Modal and Encoder-Decoder Transformers

ICCV 2021Q1 XAI

[131] Re-labeling ImageNet: from Single to Multi-Labels, from Global to Localized Labels

2021Q1 CVPR naver

[126] ViLT: Vision-and-Language Transformer Without Convolution or Region Supervision

multimodal 2021Q1 25min kakao

feat: add open-clip

[106] Prefix-Tuning: Optimizing Continuous Prompts for Generation

2021Q1 25min finetuning LLM ACL

[104] GPT Understands, too

2021Q1 prompt GPT finetuning LLM

[82] Estimating and Evaluating Regression Predictive Uncertainty in Deep Object Detectors

2021Q1 ICLR object detection uncertainty later..

[11] DALL-E : Zero-Shot Text-to-Image Generation

multimodal 2021Q1 zero-shot openAI

[10] CLIP: Connecting Text and Images

multimodal 2021Q1 few-shot SSL zero-shot CLIP

[5] An Image is Worth 16x16 Words: Transformers for Image Recognition at Scale

ViT backbone 2021Q1 re-read

[4] Conditional Positional Encodings for Vision Transformers

[3] Twins: Revisiting the Design of Spatial Attention in Vision Transformers

ViT backbone 2021Q1