2.7k citations · 7.3k across the 172 of their papers we have counts for
12 papers · 1 filter
Unveiling Backbone Effects in CLIP: Exploring Representational Synergies and Variances
Cristian Rodriguez-Opazo, Edison Marrese-Taylor, Ehsan Abbasnejad +4
Contrastive Language-Image Pretraining (CLIP) stands out as a prominent method for image representation learning. Various neural architectures, spanning Transformer-based models li…
Weakly Supervised Video Individual CountingWeakly Supervised Video Individual Counting
Xinyan Liu, Guorong Li, Yuankai Qi +5
Video Individual Counting (VIC) aims to predict the number of unique individuals in a single video. % Existing methods learn representations based on trajectory labels for individu…
Zero-shot Retrieval: Augmenting Pre-trained Models with Search Engines
Hamed Damirchi, Cristian Rodríguez-Opazo, Ehsan Abbasnejad +4
Large pre-trained models can dramatically reduce the amount of task-specific data required to solve a problem, but they often fail to capture domain-specific nuances out of the box…
Identifiable Latent Polynomial Causal Models Through the Lens of Change
Yuhang Liu, Zhen Zhang, Dong Gong +5
Causal representation learning aims to unveil latent high-level causal representations from observed low-level data. One of its primary tasks is to provide reliable assurance of id…
Domain Generalization via Rationale Invariance
Liang Chen, Yong Zhang, Yibing Song +2
This paper offers a new perspective to ease the challenge of domain generalization, which involves maintaining robust results even in unseen environments. Our design focuses on the…
RanPAC: Random Projections and Pre-trained Models for Continual Learning
Mark D. McDonnell, Dong Gong, Amin Parveneh +2
Continual learning (CL) aims to incrementally learn different tasks (such as classification) in a non-stationary data stream without forgetting old ones. Most CL works focus on tac…