Original paper : Integrating Constraints and Metric Learning in Semi-Supervised Clustering, Bilenko et al. 2004

ALBEF introduces a contrastive loss to align the image and text representations before fusing them through cross-modal attention. This enables more grounded vision and language representation learning. ALBEF also doesn't require bounding box annotations. The model consists of an image encode, a text encoder, and a multimodal encoder. The image-text contrastive loss helps to align the unimodal representations of an image-text pair before fusion. The image-text matching loss and a masked language modeling loss are applied to learn multimodal interactions between image and text. In addition, momentum distillation is used to generate pseudo-targets. This improves learning with noisy data.

ALBEF

Align before Fuse: Vision and Language Representation Learning with Momentum Distillation

MPCK-Means

**Go-Explore** is a family of algorithms aiming to tackle two challenges with effective exploration in reinforcement learning: algorithms forgetting how to reach previously visited states ("detachment") and from failing to first return to a state before exploring from it ("derailment").

To avoid detachment, Go-Explore builds an archive of the different states it has visited in the environment, thus ensuring that states cannot be forgotten. Starting with an archive beginning with the initial state, the archive is built iteratively. In Go-Explore we:

(a) Probabilistically select a state from the archive, preferring states associated with promising cells. 

(b) Return to the selected state, such as by restoring simulator state or by running a goal-conditioned policy. 

(c) Explore from that state by taking random actions or sampling from a trained policy. 

(d) Map every state encountered during returning and exploring to a low-dimensional cell representation. 

(e) Add states that map to new cells to the archive and update other archive entries.

Year	2000
Data Source	CC BY-SA - https://paperswithcode.com

Viet-Anh on Software

What is: Metric Pairwise Constrained KMeans?

Viet-Anh on Software