BatchFormer
learn to explore the sample relationships via transformer networks
BatchFormer: Learning to Explore Sample Relationships for Robust Representation Learning
Papers with Code 아카이브
Compositional Zero-Shot Learning
태스크의 하위 분류와 논문·코드·평가·기법·데이터셋을 탐색하세요.
- 하위 태스크
- 0
- 평가표
- 4
- 보존된 평가 기록
- 6
Compositional Zero-Shot Learning (CZSL) is a computer vision task in which the goal is to recognize unseen compositions fromed from seen state and object during training. The key challenge in CZSL is the inherent entanglement between the state and object within the context of an image. Some example benchmarks for this task are MIT-states, UT-Zappos, and C-GQA. Models are usually evaluated with the Accuracy for both seen and unseen compositions, as well as their Harmonic Mean(HM).
<span style="color:grey; opacity: 0.6">( Image credit: Heosuab )</span>
기법
관련 논문에서 소개한 기법입니다. 이 태스크에서의 평가 여부는 평가 결과에서 확인하세요.
NAIL OR
NAIL OR is a two-dimensional activation function which takes two logits as input and produces a single output. It is a piece-wise linear approximation of the probabilistic OR operator in logit-space. $$\begin{equation} \text{OR_{AIL}}(x, y) := \begin{cases} x + y, & x > 0, \, y > 0 \\ \max(x, y), & \text{otherwise} \end{cases} \end{equation} $$
Logical Activation Functions: Logit-space equivalents of Probabilistic Boolean Operators
출처: Papers with Code · CC BY-SA 4.0. 아카이브 자료와 새로 수집한 논문은 별도로 관리합니다.