AAF framework

Framework generalities

This repository contains the code of the AAF framework proposed in this paper. The main idea behind this work is to propose a flexible framework to implement various attention mechanisms for Few-Shot Object Detection. The framework is composed of 3 different modules: Spatial Alignment, Global Attention and Fusion Layer, which are applied successively to combine features from query and support images.

The inputs of the framework are:

• query_features List[Tensor(B, C, H, W)]: Query features at different levels. For each level, the features are of shape Batch x Channels x Height x Width.
• support_features List[Tensor(N, C, H', W')] : Support features at different level. First dimension correspond to the number of support images, regrouped by class: N = N_WAY * K_SHOT.
• support_targets List[BoxList] bounding boxes for object in each support image.

The framework can be configured using a separate config file. Examples of such files are available under /config_files/aaf_framework/. The structure of these files is simple:

ALIGN_FIRST: #True/False Run Alignment before Attention when True
OUT_CH: # Number of features output by the fusion layer
ALIGNMENT:
    MODE: # Name of the alignment module selected
ATTENTION:
    MODE: # Name of the attention module selected
FUSION:
    MODE: # Name of the fusion module selected

The path to the AAF config file should be specified inside the master config file (i.e. for the whole network) under FEWSHOT.AAF.CFG.

For each module, classes implementing the available choices are regrouped under a single file: /modelling/aaf/alignment.py, /modelling/aaf/attention.py and /modelling/aaf/fusion.py.

Spatial Alignment

Spatial Alignment reorganizes spatially the features of one feature map to match another one. The idea is to align similar features in both maps so that comparison is easier.

### Global Attention Global Attention highlights some features of a map accordingly to an attention vector computed globally on another one. The idea is to leverage global and hopefully semantic information.

Fusion Layer

Combine directly the features from support and query. These maps must be of the same dimension for point-wise operation. Hence fusion is often employed along with alignment.

Training and evaluation

Training and evaluation scripts are available.

TODO: Give code snippet to run training with a specified config file (modify main) Basically create 2 scripts train.py and eval.py with arg config file.

DataHandler

Explain DataHandler class a bit.

Installation

Dependencies used for this projects can be installed through conda create --name <env> --file requirements.txt. Please note that these requirements are not all necessary and it will be updated soon.

FCOS must be installed from sources. But there might be some issue after installation depending on the version of the python packages you use.

• cpu/vision.h file not found: replace all occurences in the FCOS source by vision.h (see this issue).
• Error related to AT_CHECK with pytorch > 1.5 : replace all occurences by TORCH_CHECK (see this issue.
• Error related to torch._six.PY36: replace all occurence of PY36 by PY37.

Results

Results on pascal VOC, COCO and DOTA.