Search Results for author:
Found 13 papers, 4 papers with code
Active Data Curation Effectively Distills Large-Scale Multimodal Models
Knowledge distillation (KD) is the de facto standard for compressing large-scale models into smaller ones.
Context-Aware Multimodal Pretraining
Large-scale multimodal representation learning successfully optimizes for zero-shot transfer at test time.
Reflecting on the State of Rehearsal-free Continual Learning with Pretrained Models
(2) Indeed, we show how most often, P-RFCL techniques can be matched by a simple and lightweight PEFT baseline.
Memory Consolidation Enables Long-Context Video Understanding
Most transformer-based video encoders are limited to short temporal contexts due to their quadratic complexity.
Layerwise complexity-matched learning yields an improved model of cortical area V2
Finally, when the two-stage model is used as a fixed front-end for a deep network trained to perform object recognition, the resultant model (LCL-V2Net) is significantly better than standard end-to-end self-supervised, supervised, and adversarially-trained models in terms of generalization to out-of-distribution tasks and alignment with human behavior.
Three ways to improve feature alignment for open vocabulary detection
The core problem in zero-shot open vocabulary detection is how to align visual and text features, so that the detector performs well on unseen classes.
Self-supervised video pretraining yields robust and more human-aligned visual representations
Humans learn powerful representations of objects and scenes by observing how they evolve over time.
Object discovery and representation networks
The promise of self-supervised learning (SSL) is to leverage large amounts of unlabeled data to solve complex tasks.
Efficient Visual Pretraining with Contrastive Detection
Self-supervised pretraining has been shown to yield powerful representations for transfer learning.
Ranked #64 on
Semantic Segmentation
on Cityscapes val
(using extra training data)
Data-Efficient Image Recognition with Contrastive Predictive Coding
Human observers can learn to recognize new categories of images from a handful of examples, yet doing so with artificial ones remains an open challenge.
Ranked #6 on
Contrastive Learning
on imagenet-1k
Geodesics of learned representations
We develop a new method for visualizing and refining the invariances of learned representations.
The local low-dimensionality of natural images
We develop a new statistical model for photographic images, in which the local responses of a bank of linear filters are described as jointly Gaussian, with zero mean and a covariance that varies slowly over spatial position.
