https://github.com/nanzhaogang/contrib/tree/master/application/circle-loss
Circle Loss: A Unified Perspective of Pair Similarity Optimization
태스크의 하위 분류와 논문·코드·평가·기법·데이터셋을 탐색하세요.
A methodology that involves selecting relevant data or examples from a large dataset to support tasks like prediction, learning, or inference. It enhances models by providing context or additional information, often used in systems like retrieval-augmented generation or in-context learning.
관련 논문과 평가 결과에 연결된 구현입니다. 출처에서 확인된 저자 구현에는 공식 코드 표시가 있습니다.
Circle Loss: A Unified Perspective of Pair Similarity Optimization
Perspectives on Large Language Models for Relevance Judgment
Large-Scale Image Retrieval with Attentive Deep Local Features
Particular object retrieval with integral max-pooling of CNN activations
Proxy Synthesis: Learning with Synthetic Classes for Deep Metric Learning
CodeSearchNet Challenge: Evaluating the State of Semantic Code Search
A Large-scale Dataset and Benchmark for Similar Trademark Retrieval
A Large-scale Dataset and Benchmark for Similar Trademark Retrieval
LaSO: Label-Set Operations networks for multi-label few-shot learning
Sinkhorn Distances: Lightspeed Computation of Optimal Transportation Distances
Knowledge Guided Text Retrieval and Reading for Open Domain Question Answering
Marvin: Semantic annotation using multiple knowledge sources
ClimateGPT: Towards AI Synthesizing Interdisciplinary Research on Climate Change
Revisiting the Inverted Indices for Billion-Scale Approximate Nearest Neighbors
Revisiting the Inverted Indices for Billion-Scale Approximate Nearest Neighbors
IMU2CLIP: Multimodal Contrastive Learning for IMU Motion Sensors from Egocentric Videos and Text
TransferTransfo: A Transfer Learning Approach for Neural Network Based Conversational Agents
M2D2: Exploring General-purpose Audio-Language Representations Beyond CLAP
M2D2: Exploring General-purpose Audio-Language Representations Beyond CLAP
Open-Domain Question Answering Goes Conversational via Question Rewriting
SCDV : Sparse Composite Document Vectors using soft clustering over distributional representations
Latent Retrieval for Weakly Supervised Open Domain Question Answering
출처: Papers with Code · CC BY-SA 4.0. 아카이브 자료와 새로 수집한 논문은 별도로 관리합니다.