Intermediate layers of a contrastively trained vision-language encoder yield stronger general embeddings than the output layer, enabling state-of-the-art performance across image/video classification, multimodal QA, and dense prediction after simple alignment.
Good practice in cnn feature transfer
2 Pith papers cite this work. Polarity classification is still indexing.
2
Pith papers citing it
abstract
The objective of this paper is the effective transfer of the Convolutional Neural Network (CNN) feature in image search and classification. Systematically, we study three facts in CNN transfer. 1) We demonstrate the advantage of using images with a properly large size as input to CNN instead of the conventionally resized one. 2) We benchmark the performance of different CNN layers improved by average/max pooling on the feature maps. Our observation suggests that the Conv5 feature yields very competitive accuracy under such pooling step. 3) We find that the simple combination of pooled features extracted across various CNN layers is effective in collecting evidences from both low and high level descriptors. Following these good practices, we are capable of improving the state of the art on a number of benchmarks to a large margin.
citation-role summary
background 1
citation-polarity summary
fields
cs.CV 2verdicts
UNVERDICTED 2roles
background 1polarities
background 1representative citing papers
Growing CNN capacity by widening or deepening layers with normalized new units outperforms standard fine-tuning on vision benchmarks.
citing papers explorer
-
Perception Encoder: The best visual embeddings are not at the output of the network
Intermediate layers of a contrastively trained vision-language encoder yield stronger general embeddings than the output layer, enabling state-of-the-art performance across image/video classification, multimodal QA, and dense prediction after simple alignment.
-
Growing a Brain: Fine-Tuning by Increasing Model Capacity
Growing CNN capacity by widening or deepening layers with normalized new units outperforms standard fine-tuning on vision benchmarks.