Small CNN-based models usually require transferring knowledge from a lar...
The hybrid model of self-attention and convolution is one of the methods...
Recently large-scale language-image models (e.g., text-guided diffusion
...
Pretraining on large-scale datasets can boost the performance of object
...
Robust Model-Agnostic Meta-Learning (MAML) is usually adopted to train a...
Masked image modeling (MIM) learns visual representation by masking and
...
Vision Transformer and its variants have demonstrated great potential in...
We present a novel masked image modeling (MIM) approach, context autoenc...
Object detection with Transformers (DETR) has achieved a competitive
per...
Transformers with remarkable global representation capacities achieve
co...
Model ensembles are becoming one of the most effective approaches for
im...
Object detection is a basic but challenging task in computer vision, whi...
Being effective and efficient is essential to an object detector for
pra...
Anomaly detection is a challenging task and usually formulated as an
uns...
This paper addresses representational block named Hierarchical-Split Blo...
The 1st Tiny Object Detection (TOD) Challenge aims toencourage research ...
Object detection is one of the most important areas in computer vision, ...
We present an object detection framework based on PaddlePaddle. We put a...
Many advances of deep learning techniques originate from the efforts of
...