It is commonly believed that more pre-training data leads to better transfer learning
performance. However, recent evidence suggests that removing data from the source …

Computer vision systems require large amounts of manually annotated data to properly
learn challenging visual concepts. Crowdsourcing platforms offer an inexpensive method to …

Abstract 3D object modeling and fine-grained classification are often treated as separate
tasks. We propose to optimize 3D model fitting and fine-grained classification jointly …

Given a food image, can a fine-grained object recognition engine tell" which restaurant
which dish" the food belongs to? Such ultra-fine grained image recognition is the key for …

Using transfer learning to adapt a pre-trained" source model" to a downstream" target task"
can dramatically increase performance with seemingly no downside. In this work, we …

Semi-supervised learning acts as an effective way to leverage massive unlabeled data. In
this paper, we propose a novel training strategy, termed as Semi-supervised Contrastive …

Previous arts built an intimate link between knowledge distillation (KD) and label smoothing
(LS) that they both impose regularization on the model training. In this paper, we delve …

Data augmentation (DA) is widely used to improve the generalization of neural networks by
enforcing the invariances and symmetries to pre-defined transformations applied to input …

The visual models pretrained on large-scale benchmarks encode general knowledge and
prove effective in building more powerful representations for downstream tasks. Most …

Abstract Vision Language Model (VLM) is a popular research field located at the fusion of
computer vision and natural language processing (NLP). With the emergence of transformer …